{"id":1383552,"date":"2021-10-28T12:45:50","date_gmt":"2021-10-28T19:45:50","guid":{"rendered":"https:\/\/www.esri.com\/arcgis-blog\/?post_type=blog&p=1383552"},"modified":"2021-11-04T15:37:58","modified_gmt":"2021-11-04T22:37:58","slug":"looking-to-the-future-using-gis-to-model-and-predict-population","status":"publish","type":"blog","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/looking-to-the-future-using-gis-to-model-and-predict-population","title":{"rendered":"Looking to the future: Using GIS to model and predict population"},"author":55021,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"open","ping_status":"closed","template":"","format":"standard","meta":{"_acf_changed":false,"_searchwp_excluded":""},"categories":[23341],"tags":[431062,25491,762462,725501,26171],"industry":[],"product":[36561],"class_list":["post-1383552","blog","type-blog","status-publish","format-standard","hentry","category-analytics","tag-city-planning","tag-population","tag-population-forecast","tag-time-series-forecasting","tag-urban-planning","product-arcgis-pro"],"acf":{"short_description":"We\u2019ll share a source of historical county population data and introduce a set of exciting, easy-to-use forecasting tools available in ArcGIS Pro.","flexible_content":[{"acf_fc_layout":"content","content":"

Planning is about the future and having reliable estimates of the future population is critical for assessing demand for housing, energy, food, and infrastructure.\u00a0 While there are many different methods for predicting the future population, most methods follow a similar pattern. You gather historical population data, fit a mathematical model to that data, extend or extrapolate the model into the future to predict population, and finally, evaluate how well the model did.\u00a0 This can be an uphill task, particularly if you need to predict the population for many different areas.\u00a0 Often, finding reliable historical population data in an easy-to-use format can be the most challenging part.\u00a0 In this blog, we\u2019ll share a source of historical county population data and introduce a set of exciting, easy-to-use forecasting tools available in ArcGIS Pro.<\/p>\n"},{"acf_fc_layout":"sidebar","content":"

A note on terminology: In the language of urban and regional planning, this blog outlines a workflow for population projection<\/em>.\u00a0 However, the geoprocessing tools use the term forecast<\/em>.\u00a0 The term projection has a specific meaning in GIS and we felt reusing the term would be confusing. We opted to name the geoprocessing tools using the more generic term forecast.<\/p>\n","image_reference":false,"layout":"standard","image_reference_figure":"","snippet":"","spotlight_name":"","section_title":"","position":"Right","spotlight_image":false},{"acf_fc_layout":"content","content":"

Historical population data<\/strong><\/p>\n

The National Cancer Institute provides two historical population datasets; Historical County Population (1969 – 2019) by Race (White, Black, Other)<\/a> and Historical County Population (1990 – 2019) by Expanded Races & Hispanic\/Non-Hispanic<\/a>.\u00a0 Esri has made these datasets available in ArcGIS Online. If you\u2019re interested in forecasting the total population, we recommend the 1969-2019 dataset since it contains a long history. However, suppose your project requires a more detailed analysis by racial or ethnic group (for example, White, Black, American Indian\/Alaska Native, Asian\/Pacific Islander). In that case, you\u2019ll need to use the 1990-2019 dataset.<\/p>\n

Time series forecasting tools<\/strong><\/p>\n

Understanding how the population has increased or decreased across time is the basis for predicting future population. Past behavior is often the best predictor of future behavior.\u00a0 There are many ways to describe (model) historic population patterns, and choosing the best model is essential and challenging.\u00a0 Fortunately, a set of new time series forecasting tools available in ArcGIS Pro 2.6 allows you to model and project population data in various ways.<\/p>\n

The workflow
\n<\/strong>Using step by step instructions, we will show you how to:<\/p>\n

    \n
  1. Prepare data for analysis<\/li>\n
  2. Create a space-time cube using county-level population data (total population)<\/li>\n
  3. Run three different forecasting models (Curve Fit Forecast, Exponential Smoothing Forecast, and Forest-based Forecast)<\/li>\n
  4. Evaluate the forecasts for each county in the US<\/li>\n<\/ol>\n"},{"acf_fc_layout":"content","content":"

    Prepare data for analysis<\/h2>\n

    1. Create a new Pro project with the name population_forecasts.<\/p>\n

    2. On the Map<\/strong> tab, in the Layer<\/strong> group, click the Add Data <\/strong>button.<\/p>\n"},{"acf_fc_layout":"image","image":{"ID":1383562,"id":1383562,"title":"prepare data step 2","filename":"prepare-data-step-2.png","filesize":9733,"url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-2.png","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/looking-to-the-future-using-gis-to-model-and-predict-population\/prepare-data-step-2","alt":"","author":"55021","description":"","caption":"","name":"prepare-data-step-2","status":"inherit","uploaded_to":1383552,"date":"2021-10-27 18:55:27","modified":"2021-10-27 18:55:27","menu_order":0,"mime_type":"image\/png","type":"image","subtype":"png","icon":"https:\/\/www.esri.com\/arcgis-blog\/wp-includes\/images\/media\/default.png","width":555,"height":88,"sizes":{"thumbnail":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-2-213x88.png","thumbnail-width":213,"thumbnail-height":88,"medium":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-2.png","medium-width":464,"medium-height":74,"medium_large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-2.png","medium_large-width":555,"medium_large-height":88,"large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-2.png","large-width":555,"large-height":88,"1536x1536":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-2.png","1536x1536-width":555,"1536x1536-height":88,"2048x2048":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-2.png","2048x2048-width":555,"2048x2048-height":88,"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-2.png","card_image-width":555,"card_image-height":88,"wide_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-2.png","wide_image-width":555,"wide_image-height":88}},"image_position":"center","orientation":"horizontal","hyperlink":""},{"acf_fc_layout":"content","content":"

    3. In the Add Data<\/strong> window, under Portal<\/strong>, click ArcGIS Online<\/strong>. Then, type Historical County Population (1990 – 2019)<\/em> in the search bar and press Enter. Select Historical County Population (1990 \u2013 2019) by Race (White, Black, Other)<\/strong> and click OK<\/strong>.<\/p>\n"},{"acf_fc_layout":"image","image":{"ID":1383572,"id":1383572,"title":"prepare data step 3","filename":"prepare-data-step-3.png","filesize":28493,"url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-3.png","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/looking-to-the-future-using-gis-to-model-and-predict-population\/prepare-data-step-3","alt":"","author":"55021","description":"","caption":"","name":"prepare-data-step-3","status":"inherit","uploaded_to":1383552,"date":"2021-10-27 18:55:28","modified":"2021-10-27 18:55:28","menu_order":0,"mime_type":"image\/png","type":"image","subtype":"png","icon":"https:\/\/www.esri.com\/arcgis-blog\/wp-includes\/images\/media\/default.png","width":960,"height":329,"sizes":{"thumbnail":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-3-213x200.png","thumbnail-width":213,"thumbnail-height":200,"medium":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-3.png","medium-width":464,"medium-height":159,"medium_large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-3.png","medium_large-width":768,"medium_large-height":263,"large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-3.png","large-width":960,"large-height":329,"1536x1536":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-3.png","1536x1536-width":960,"1536x1536-height":329,"2048x2048":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-3.png","2048x2048-width":960,"2048x2048-height":329,"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-3-826x283.png","card_image-width":826,"card_image-height":283,"wide_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-3.png","wide_image-width":960,"wide_image-height":329}},"image_position":"center","orientation":"horizontal","hyperlink":""},{"acf_fc_layout":"content","content":"

    Next, you\u2019ll add a layer for the US counties from the Living Atlas.<\/p>\n

    4. On the Map<\/strong> tab, in the Layer<\/strong> group, click the Add Data<\/strong> button.<\/p>\n"},{"acf_fc_layout":"image","image":{"ID":1383582,"id":1383582,"title":"prepare data step 4","filename":"prepare-data-step-4.png","filesize":9733,"url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-4.png","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/looking-to-the-future-using-gis-to-model-and-predict-population\/prepare-data-step-4","alt":"","author":"55021","description":"","caption":"","name":"prepare-data-step-4","status":"inherit","uploaded_to":1383552,"date":"2021-10-27 18:55:29","modified":"2021-10-27 18:55:29","menu_order":0,"mime_type":"image\/png","type":"image","subtype":"png","icon":"https:\/\/www.esri.com\/arcgis-blog\/wp-includes\/images\/media\/default.png","width":555,"height":88,"sizes":{"thumbnail":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-4-213x88.png","thumbnail-width":213,"thumbnail-height":88,"medium":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-4.png","medium-width":464,"medium-height":74,"medium_large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-4.png","medium_large-width":555,"medium_large-height":88,"large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-4.png","large-width":555,"large-height":88,"1536x1536":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-4.png","1536x1536-width":555,"1536x1536-height":88,"2048x2048":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-4.png","2048x2048-width":555,"2048x2048-height":88,"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-4.png","card_image-width":555,"card_image-height":88,"wide_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-4.png","wide_image-width":555,"wide_image-height":88}},"image_position":"center","orientation":"horizontal","hyperlink":""},{"acf_fc_layout":"content","content":"

    5. In the Add Data<\/strong> window, under Portal<\/strong>, click Living Atlas<\/strong>. Then, type USA Counties Generalized<\/em> in the search bar and press Enter. Next, select USA Counties (Generalized)<\/strong> and click OK<\/strong>.<\/p>\n"},{"acf_fc_layout":"image","image":{"ID":1383592,"id":1383592,"title":"prepare data step 5","filename":"prepare-data-step-5.png","filesize":24475,"url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-5.png","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/looking-to-the-future-using-gis-to-model-and-predict-population\/prepare-data-step-5","alt":"","author":"55021","description":"","caption":"","name":"prepare-data-step-5","status":"inherit","uploaded_to":1383552,"date":"2021-10-27 18:55:30","modified":"2021-10-27 18:55:30","menu_order":0,"mime_type":"image\/png","type":"image","subtype":"png","icon":"https:\/\/www.esri.com\/arcgis-blog\/wp-includes\/images\/media\/default.png","width":788,"height":355,"sizes":{"thumbnail":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-5-213x200.png","thumbnail-width":213,"thumbnail-height":200,"medium":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-5.png","medium-width":464,"medium-height":209,"medium_large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-5.png","medium_large-width":768,"medium_large-height":346,"large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-5.png","large-width":788,"large-height":355,"1536x1536":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-5.png","1536x1536-width":788,"1536x1536-height":355,"2048x2048":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-5.png","2048x2048-width":788,"2048x2048-height":355,"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-5.png","card_image-width":788,"card_image-height":355,"wide_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-5.png","wide_image-width":788,"wide_image-height":355}},"image_position":"center","orientation":"horizontal","hyperlink":""},{"acf_fc_layout":"content","content":"

    Your map now contains a US counties layer and a table with historical population data for each county (1969 \u2013 2019).\u00a0 When creating a space-time cube using the Create Space Time Cube From Defined Locations tool, you need a unique numeric identifier to link (relate) the population data in the table to the features in the map.<\/p>\n

    Since you can\u2019t modify data stored in the Living Atlas, you\u2019ll make a local copy of the US counties layer.<\/p>\n

    6. On the ribbon, on the Analysis<\/strong> tab, in the Geoprocessing<\/strong> group, click Tools<\/strong>.<\/p>\n"},{"acf_fc_layout":"image","image":{"ID":1383602,"id":1383602,"title":"prepare data step 6","filename":"prepare-data-step-6.png","filesize":8029,"url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-6.png","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/looking-to-the-future-using-gis-to-model-and-predict-population\/prepare-data-step-6","alt":"","author":"55021","description":"","caption":"","name":"prepare-data-step-6","status":"inherit","uploaded_to":1383552,"date":"2021-10-27 18:55:31","modified":"2021-10-27 18:55:31","menu_order":0,"mime_type":"image\/png","type":"image","subtype":"png","icon":"https:\/\/www.esri.com\/arcgis-blog\/wp-includes\/images\/media\/default.png","width":339,"height":118,"sizes":{"thumbnail":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-6-213x118.png","thumbnail-width":213,"thumbnail-height":118,"medium":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-6.png","medium-width":339,"medium-height":118,"medium_large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-6.png","medium_large-width":339,"medium_large-height":118,"large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-6.png","large-width":339,"large-height":118,"1536x1536":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-6.png","1536x1536-width":339,"1536x1536-height":118,"2048x2048":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-6.png","2048x2048-width":339,"2048x2048-height":118,"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-6.png","card_image-width":339,"card_image-height":118,"wide_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-6.png","wide_image-width":339,"wide_image-height":118}},"image_position":"center","orientation":"horizontal","hyperlink":""},{"acf_fc_layout":"content","content":"

    The Geoprocessing<\/strong> pane opens.<\/p>\n

    7. In the Geoprocessing<\/strong> pane, in the search box, type Copy Features<\/em>. In the search results, click Copy Features to open the tool dialog.<\/p>\n"},{"acf_fc_layout":"image","image":{"ID":1383612,"id":1383612,"title":"prepare data step 7","filename":"prepare-data-step-7.png","filesize":5279,"url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-7.png","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/looking-to-the-future-using-gis-to-model-and-predict-population\/prepare-data-step-7","alt":"","author":"55021","description":"","caption":"","name":"prepare-data-step-7","status":"inherit","uploaded_to":1383552,"date":"2021-10-27 18:55:32","modified":"2021-10-27 18:55:32","menu_order":0,"mime_type":"image\/png","type":"image","subtype":"png","icon":"https:\/\/www.esri.com\/arcgis-blog\/wp-includes\/images\/media\/default.png","width":399,"height":142,"sizes":{"thumbnail":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-7-213x142.png","thumbnail-width":213,"thumbnail-height":142,"medium":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-7.png","medium-width":399,"medium-height":142,"medium_large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-7.png","medium_large-width":399,"medium_large-height":142,"large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-7.png","large-width":399,"large-height":142,"1536x1536":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-7.png","1536x1536-width":399,"1536x1536-height":142,"2048x2048":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-7.png","2048x2048-width":399,"2048x2048-height":142,"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-7.png","card_image-width":399,"card_image-height":142,"wide_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-7.png","wide_image-width":399,"wide_image-height":142}},"image_position":"center","orientation":"horizontal","hyperlink":""},{"acf_fc_layout":"content","content":"

    8. In the Copy Features<\/strong> geoprocessing tool, select USA_Counties_Generalized<\/strong> from the Input Features<\/strong> dropdown. For Output Feature Class<\/strong>, type counties<\/em>.<\/p>\n"},{"acf_fc_layout":"image","image":{"ID":1383622,"id":1383622,"title":"prepare data step 8","filename":"prepare-data-step-8.png","filesize":3955,"url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-8.png","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/looking-to-the-future-using-gis-to-model-and-predict-population\/prepare-data-step-8","alt":"","author":"55021","description":"","caption":"","name":"prepare-data-step-8","status":"inherit","uploaded_to":1383552,"date":"2021-10-27 18:55:34","modified":"2021-10-27 18:55:34","menu_order":0,"mime_type":"image\/png","type":"image","subtype":"png","icon":"https:\/\/www.esri.com\/arcgis-blog\/wp-includes\/images\/media\/default.png","width":388,"height":120,"sizes":{"thumbnail":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-8-213x120.png","thumbnail-width":213,"thumbnail-height":120,"medium":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-8.png","medium-width":388,"medium-height":120,"medium_large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-8.png","medium_large-width":388,"medium_large-height":120,"large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-8.png","large-width":388,"large-height":120,"1536x1536":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-8.png","1536x1536-width":388,"1536x1536-height":120,"2048x2048":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-8.png","2048x2048-width":388,"2048x2048-height":120,"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-8.png","card_image-width":388,"card_image-height":120,"wide_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-8.png","wide_image-width":388,"wide_image-height":120}},"image_position":"center","orientation":"horizontal","hyperlink":""},{"acf_fc_layout":"content","content":"

    9. Click the Environments<\/strong> tab. Click the Select Coordinate System<\/strong> button (small globe) and select NAD 1983 Contiguous USA Albers<\/strong> (under Projected Coordinate System > Continental > North America) as the Output Coordinate System<\/strong>.<\/p>\n"},{"acf_fc_layout":"image","image":{"ID":1383632,"id":1383632,"title":"prepare data step 9","filename":"prepare-data-step-9.png","filesize":6257,"url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-9.png","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/looking-to-the-future-using-gis-to-model-and-predict-population\/prepare-data-step-9","alt":"","author":"55021","description":"","caption":"","name":"prepare-data-step-9","status":"inherit","uploaded_to":1383552,"date":"2021-10-27 18:55:34","modified":"2021-10-27 18:55:34","menu_order":0,"mime_type":"image\/png","type":"image","subtype":"png","icon":"https:\/\/www.esri.com\/arcgis-blog\/wp-includes\/images\/media\/default.png","width":402,"height":149,"sizes":{"thumbnail":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-9-213x149.png","thumbnail-width":213,"thumbnail-height":149,"medium":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-9.png","medium-width":402,"medium-height":149,"medium_large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-9.png","medium_large-width":402,"medium_large-height":149,"large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-9.png","large-width":402,"large-height":149,"1536x1536":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-9.png","1536x1536-width":402,"1536x1536-height":149,"2048x2048":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-9.png","2048x2048-width":402,"2048x2048-height":149,"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-9.png","card_image-width":402,"card_image-height":149,"wide_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-9.png","wide_image-width":402,"wide_image-height":149}},"image_position":"center","orientation":"horizontal","hyperlink":""},{"acf_fc_layout":"content","content":"

    10. In the Geoprocessing<\/strong> pane, in the search box, type Calculate Field<\/em>. In the search results, click Calculate Field to open the tool dialog.<\/p>\n"},{"acf_fc_layout":"image","image":{"ID":1383642,"id":1383642,"title":"prepare data step 10","filename":"prepare-data-step-10.png","filesize":8386,"url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-10.png","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/looking-to-the-future-using-gis-to-model-and-predict-population\/prepare-data-step-10","alt":"","author":"55021","description":"","caption":"","name":"prepare-data-step-10","status":"inherit","uploaded_to":1383552,"date":"2021-10-27 18:55:36","modified":"2021-10-27 18:55:36","menu_order":0,"mime_type":"image\/png","type":"image","subtype":"png","icon":"https:\/\/www.esri.com\/arcgis-blog\/wp-includes\/images\/media\/default.png","width":393,"height":238,"sizes":{"thumbnail":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-10-213x200.png","thumbnail-width":213,"thumbnail-height":200,"medium":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-10.png","medium-width":393,"medium-height":238,"medium_large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-10.png","medium_large-width":393,"medium_large-height":238,"large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-10.png","large-width":393,"large-height":238,"1536x1536":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-10.png","1536x1536-width":393,"1536x1536-height":238,"2048x2048":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-10.png","2048x2048-width":393,"2048x2048-height":238,"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-10.png","card_image-width":393,"card_image-height":238,"wide_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-10.png","wide_image-width":393,"wide_image-height":238}},"image_position":"center","orientation":"horizontal","hyperlink":""},{"acf_fc_layout":"content","content":"

    11. In the Calculate Field geoprocessing tool, change the following parameters:<\/p>\n

      \n
    • For Input Table<\/strong>, specify counties<\/strong>.<\/li>\n
    • For Field Name<\/strong> (Existing or New),<\/strong> type FIPS_NUM<\/em>.<\/li>\n
    • For Field Type<\/strong>, specify Long.<\/li>\n
    • For FIPS_NUM =<\/strong>, type !FIPS!<\/em>.<\/li>\n<\/ul>\n

      Click Run<\/strong>.<\/p>\n"},{"acf_fc_layout":"image","image":{"ID":1383652,"id":1383652,"title":"prepare data step 11","filename":"prepare-data-step-11.png","filesize":16912,"url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-11.png","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/looking-to-the-future-using-gis-to-model-and-predict-population\/prepare-data-step-11","alt":"","author":"55021","description":"","caption":"","name":"prepare-data-step-11","status":"inherit","uploaded_to":1383552,"date":"2021-10-27 18:55:37","modified":"2021-10-27 18:55:37","menu_order":0,"mime_type":"image\/png","type":"image","subtype":"png","icon":"https:\/\/www.esri.com\/arcgis-blog\/wp-includes\/images\/media\/default.png","width":394,"height":475,"sizes":{"thumbnail":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-11-213x200.png","thumbnail-width":213,"thumbnail-height":200,"medium":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-11.png","medium-width":216,"medium-height":261,"medium_large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-11.png","medium_large-width":394,"medium_large-height":475,"large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-11.png","large-width":394,"large-height":475,"1536x1536":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-11.png","1536x1536-width":394,"1536x1536-height":475,"2048x2048":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-11.png","2048x2048-width":394,"2048x2048-height":475,"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-11-386x465.png","card_image-width":386,"card_image-height":465,"wide_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/prepare-data-step-11.png","wide_image-width":394,"wide_image-height":475}},"image_position":"center","orientation":"horizontal","hyperlink":""},{"acf_fc_layout":"content","content":"

      This step prepares the data for the \u2018Create Space Time Cube From Defined Location\u2019 tool.<\/p>\n

      Creating Space-Time Cube and Visualize the population trend in 2D<\/h2>\n

      1. In the Geoprocessing<\/strong> pane, in the search box, type Create Space Time Cube From Defined Location<\/em>. In the search results, click Create Space Time Cube From Defined Location to open the tool dialog.<\/p>\n"},{"acf_fc_layout":"image","image":{"ID":1383662,"id":1383662,"title":"create cube step 1","filename":"create-cube-step-1.png","filesize":12594,"url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/create-cube-step-1.png","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/looking-to-the-future-using-gis-to-model-and-predict-population\/create-cube-step-1","alt":"","author":"55021","description":"","caption":"","name":"create-cube-step-1","status":"inherit","uploaded_to":1383552,"date":"2021-10-27 19:07:20","modified":"2021-10-27 19:07:20","menu_order":0,"mime_type":"image\/png","type":"image","subtype":"png","icon":"https:\/\/www.esri.com\/arcgis-blog\/wp-includes\/images\/media\/default.png","width":406,"height":251,"sizes":{"thumbnail":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/create-cube-step-1-213x200.png","thumbnail-width":213,"thumbnail-height":200,"medium":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/create-cube-step-1.png","medium-width":406,"medium-height":251,"medium_large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/create-cube-step-1.png","medium_large-width":406,"medium_large-height":251,"large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/create-cube-step-1.png","large-width":406,"large-height":251,"1536x1536":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/create-cube-step-1.png","1536x1536-width":406,"1536x1536-height":251,"2048x2048":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/create-cube-step-1.png","2048x2048-width":406,"2048x2048-height":251,"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/create-cube-step-1.png","card_image-width":406,"card_image-height":251,"wide_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/create-cube-step-1.png","wide_image-width":406,"wide_image-height":251}},"image_position":"center","orientation":"horizontal","hyperlink":""},{"acf_fc_layout":"content","content":"

      2. In the Create Space Time Cube From Defined Location geoprocessing tool, change the following parameters:<\/p>\n

        \n
      • For Input Features<\/strong>, specify counties<\/strong>.<\/li>\n
      • For Output Space Time Cube<\/strong>, type USA_County_Population_1969_2019.nc<\/em>.<\/li>\n
      • For Location ID<\/strong>, specify FIPS_NUM<\/strong>.<\/li>\n
      • For Related Table<\/strong>, specify Historical County Population by Race (White, Black, Other)<\/strong>.<\/li>\n
      • For Related Location ID, <\/strong>specify FIPS<\/strong>.<\/li>\n
      • Check Temporal Aggregation <\/strong><\/li>\n
      • For Time Field<\/strong>, specify Year<\/strong>.<\/li>\n
      • For Time Step Interval<\/strong>, type 1 and specify Year<\/strong> from the dropdown list.<\/li>\n
      • For Summary Fields<\/strong>,\n
          \n
        • Select Population <\/strong>for Field.<\/strong><\/li>\n
        • Select Sum <\/strong>for Statistics.<\/strong><\/li>\n
        • Select Zeros <\/strong>for Fill Empty Bins with<\/strong>.<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n

          Click Run<\/strong>.<\/p>\n"},{"acf_fc_layout":"image","image":{"ID":1383672,"id":1383672,"title":"create cube step 2","filename":"create-cube-step-2.png","filesize":15485,"url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/create-cube-step-2.png","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/looking-to-the-future-using-gis-to-model-and-predict-population\/create-cube-step-2","alt":"","author":"55021","description":"","caption":"","name":"create-cube-step-2","status":"inherit","uploaded_to":1383552,"date":"2021-10-27 19:07:21","modified":"2021-10-27 19:07:21","menu_order":0,"mime_type":"image\/png","type":"image","subtype":"png","icon":"https:\/\/www.esri.com\/arcgis-blog\/wp-includes\/images\/media\/default.png","width":403,"height":516,"sizes":{"thumbnail":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/create-cube-step-2-213x200.png","thumbnail-width":213,"thumbnail-height":200,"medium":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/create-cube-step-2.png","medium-width":204,"medium-height":261,"medium_large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/create-cube-step-2.png","medium_large-width":403,"medium_large-height":516,"large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/create-cube-step-2.png","large-width":403,"large-height":516,"1536x1536":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/create-cube-step-2.png","1536x1536-width":403,"1536x1536-height":516,"2048x2048":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/create-cube-step-2.png","2048x2048-width":403,"2048x2048-height":516,"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/create-cube-step-2-363x465.png","card_image-width":363,"card_image-height":465,"wide_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/create-cube-step-2.png","wide_image-width":403,"wide_image-height":516}},"image_position":"center","orientation":"horizontal","hyperlink":""},{"acf_fc_layout":"content","content":"

          Running this tool will produce a space-time cube containing the yearly total population data for each county in the US. Before we dive into the forecasting, let\u2019s get a quick visualization of the past trends of the population using the Visualize Space Time Cube in 2D tool.<\/p>\n

          3. In the Geoprocessing<\/strong> pane, in the search box, type Visualize Space Time Cube in 2D<\/em>. In the search results, click Visualize Space Time Cube in 2D to open the dialog.<\/p>\n"},{"acf_fc_layout":"image","image":{"ID":1383682,"id":1383682,"title":"create cube step 3","filename":"create-cube-step-3.png","filesize":12890,"url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/create-cube-step-3.png","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/looking-to-the-future-using-gis-to-model-and-predict-population\/create-cube-step-3","alt":"","author":"55021","description":"","caption":"","name":"create-cube-step-3","status":"inherit","uploaded_to":1383552,"date":"2021-10-27 19:07:23","modified":"2021-10-27 19:07:23","menu_order":0,"mime_type":"image\/png","type":"image","subtype":"png","icon":"https:\/\/www.esri.com\/arcgis-blog\/wp-includes\/images\/media\/default.png","width":405,"height":236,"sizes":{"thumbnail":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/create-cube-step-3-213x200.png","thumbnail-width":213,"thumbnail-height":200,"medium":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/create-cube-step-3.png","medium-width":405,"medium-height":236,"medium_large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/create-cube-step-3.png","medium_large-width":405,"medium_large-height":236,"large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/create-cube-step-3.png","large-width":405,"large-height":236,"1536x1536":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/create-cube-step-3.png","1536x1536-width":405,"1536x1536-height":236,"2048x2048":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/create-cube-step-3.png","2048x2048-width":405,"2048x2048-height":236,"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/create-cube-step-3.png","card_image-width":405,"card_image-height":236,"wide_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/create-cube-step-3.png","wide_image-width":405,"wide_image-height":236}},"image_position":"center","orientation":"horizontal","hyperlink":""},{"acf_fc_layout":"content","content":"

          4. In the Visualize Space Time Cube in 2D geoprocessing tool, change the following parameters:<\/p>\n

            \n
          • For Input Space Time Cube<\/strong>, specify USA_County_Population_1969_2019.nc<\/strong>.<\/strong><\/li>\n
          • For Cube Variable<\/strong>, select POPULATION_SUM_ZERO<\/strong>.<\/li>\n
          • For Display Theme<\/strong>, specify Trends<\/strong>.<\/li>\n
          • Check Enable Time Series Pop-ups<\/strong>.<\/li>\n<\/ul>\n

            Click Run<\/strong>.<\/p>\n"},{"acf_fc_layout":"image","image":{"ID":1383692,"id":1383692,"title":"create cube step 4","filename":"create-cube-step-4.png","filesize":8724,"url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/create-cube-step-4.png","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/looking-to-the-future-using-gis-to-model-and-predict-population\/create-cube-step-4","alt":"","author":"55021","description":"","caption":"","name":"create-cube-step-4","status":"inherit","uploaded_to":1383552,"date":"2021-10-27 19:07:24","modified":"2021-10-27 19:07:24","menu_order":0,"mime_type":"image\/png","type":"image","subtype":"png","icon":"https:\/\/www.esri.com\/arcgis-blog\/wp-includes\/images\/media\/default.png","width":404,"height":224,"sizes":{"thumbnail":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/create-cube-step-4-213x200.png","thumbnail-width":213,"thumbnail-height":200,"medium":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/create-cube-step-4.png","medium-width":404,"medium-height":224,"medium_large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/create-cube-step-4.png","medium_large-width":404,"medium_large-height":224,"large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/create-cube-step-4.png","large-width":404,"large-height":224,"1536x1536":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/create-cube-step-4.png","1536x1536-width":404,"1536x1536-height":224,"2048x2048":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/create-cube-step-4.png","2048x2048-width":404,"2048x2048-height":224,"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/create-cube-step-4.png","card_image-width":404,"card_image-height":224,"wide_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/create-cube-step-4.png","wide_image-width":404,"wide_image-height":224}},"image_position":"center","orientation":"horizontal","hyperlink":""},{"acf_fc_layout":"content","content":"

            Your map now contains overall trends of population change from 1969 to 2019. The purple counties have increasing trends, while those in green have decreasing trends over the 51 years. Counties in white have no significant trend in population growth. The darker colors indicate higher statistical significance in terms of the tested trends. You can also click each individual county feature to see how the population changes in that specific county in the pop-up window.<\/p>\n"},{"acf_fc_layout":"image","image":{"ID":1383702,"id":1383702,"title":"create cube step 5","filename":"create-cube-step-5.png","filesize":835763,"url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/create-cube-step-5.png","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/looking-to-the-future-using-gis-to-model-and-predict-population\/create-cube-step-5","alt":"","author":"55021","description":"","caption":"","name":"create-cube-step-5","status":"inherit","uploaded_to":1383552,"date":"2021-10-27 19:07:26","modified":"2021-10-27 19:07:26","menu_order":0,"mime_type":"image\/png","type":"image","subtype":"png","icon":"https:\/\/www.esri.com\/arcgis-blog\/wp-includes\/images\/media\/default.png","width":1431,"height":774,"sizes":{"thumbnail":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/create-cube-step-5-213x200.png","thumbnail-width":213,"thumbnail-height":200,"medium":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/create-cube-step-5.png","medium-width":464,"medium-height":251,"medium_large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/create-cube-step-5.png","medium_large-width":768,"medium_large-height":415,"large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/create-cube-step-5.png","large-width":1431,"large-height":774,"1536x1536":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/create-cube-step-5.png","1536x1536-width":1431,"1536x1536-height":774,"2048x2048":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/create-cube-step-5.png","2048x2048-width":1431,"2048x2048-height":774,"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/create-cube-step-5-826x447.png","card_image-width":826,"card_image-height":447,"wide_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/create-cube-step-5.png","wide_image-width":1431,"wide_image-height":774}},"image_position":"center","orientation":"horizontal","hyperlink":""},{"acf_fc_layout":"content","content":"

            Forecasting future population using Curve Fit Forecast<\/h2>\n

            We first use the Curve Fit Forecast tool in the Time Series Forecasting toolset to project the population from 2020 to 2030, using the following four types of parametric curves: linear, parabolic, exponential, and Gompertz (S-shaped).<\/p>\n

            1. In the Geoprocessing<\/strong> pane, in the search box, type Curve Fit<\/em>. In the search results, click Curve Fit Forecast to open the dialog.<\/p>\n"},{"acf_fc_layout":"image","image":{"ID":1383762,"id":1383762,"title":"curve fit step 1","filename":"curve-fit-step-1.png","filesize":9301,"url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/curve-fit-step-1.png","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/looking-to-the-future-using-gis-to-model-and-predict-population\/curve-fit-step-1","alt":"","author":"55021","description":"","caption":"","name":"curve-fit-step-1","status":"inherit","uploaded_to":1383552,"date":"2021-10-27 19:17:06","modified":"2021-10-27 19:17:06","menu_order":0,"mime_type":"image\/png","type":"image","subtype":"png","icon":"https:\/\/www.esri.com\/arcgis-blog\/wp-includes\/images\/media\/default.png","width":402,"height":232,"sizes":{"thumbnail":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/curve-fit-step-1-213x200.png","thumbnail-width":213,"thumbnail-height":200,"medium":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/curve-fit-step-1.png","medium-width":402,"medium-height":232,"medium_large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/curve-fit-step-1.png","medium_large-width":402,"medium_large-height":232,"large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/curve-fit-step-1.png","large-width":402,"large-height":232,"1536x1536":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/curve-fit-step-1.png","1536x1536-width":402,"1536x1536-height":232,"2048x2048":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/curve-fit-step-1.png","2048x2048-width":402,"2048x2048-height":232,"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/curve-fit-step-1.png","card_image-width":402,"card_image-height":232,"wide_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/curve-fit-step-1.png","wide_image-width":402,"wide_image-height":232}},"image_position":"center","orientation":"horizontal","hyperlink":""},{"acf_fc_layout":"content","content":"

            2. In the Curve Fit Forecast geoprocessing tool, change the following parameters:<\/p>\n

              \n
            • For Input Space Time Cube<\/strong>, specify USA_County_Population_1969_2019.nc<\/strong>.<\/li>\n
            • For Analysis Variable<\/strong>, select POPULATION_SUM_ZERO<\/strong>.<\/li>\n
            • For Number of Time Steps to Forecast<\/strong>, type 11<\/strong>. This means we will forecast 11 time steps out to the future, specifically, from 2020 to 2030.<\/li>\n
            • For Output Features<\/strong>, type USA_County_Population_2030_CF<\/em>.<\/li>\n
            • For Output Space Time Cube<\/strong>, type USA_County_Population_2030_CF.nc.<\/em><\/li>\n
            • For Curve Type<\/strong>, leave it as default, which is Auto-detect<\/strong>.<\/li>\n
            • For Number of Time Steps to Exclude for Validation<\/strong>, type 10<\/strong>. This means we will leave observed data of the last 10 time steps for validation, which is data of 2010 to 2019.<\/li>\n
            • For Outlier Option<\/strong>, leave it as default, which is None<\/strong>.<\/li>\n<\/ul>\n

              Click Run<\/strong>.<\/p>\n"},{"acf_fc_layout":"image","image":{"ID":1383782,"id":1383782,"title":"curve fit step 2","filename":"curve-fit-step-2.png","filesize":12728,"url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/curve-fit-step-2.png","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/looking-to-the-future-using-gis-to-model-and-predict-population\/curve-fit-step-2","alt":"","author":"55021","description":"","caption":"","name":"curve-fit-step-2","status":"inherit","uploaded_to":1383552,"date":"2021-10-27 19:17:08","modified":"2021-10-27 19:17:08","menu_order":0,"mime_type":"image\/png","type":"image","subtype":"png","icon":"https:\/\/www.esri.com\/arcgis-blog\/wp-includes\/images\/media\/default.png","width":404,"height":360,"sizes":{"thumbnail":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/curve-fit-step-2-213x200.png","thumbnail-width":213,"thumbnail-height":200,"medium":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/curve-fit-step-2.png","medium-width":293,"medium-height":261,"medium_large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/curve-fit-step-2.png","medium_large-width":404,"medium_large-height":360,"large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/curve-fit-step-2.png","large-width":404,"large-height":360,"1536x1536":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/curve-fit-step-2.png","1536x1536-width":404,"1536x1536-height":360,"2048x2048":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/curve-fit-step-2.png","2048x2048-width":404,"2048x2048-height":360,"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/curve-fit-step-2.png","card_image-width":404,"card_image-height":360,"wide_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/curve-fit-step-2.png","wide_image-width":404,"wide_image-height":360}},"image_position":"center","orientation":"horizontal","hyperlink":""},{"acf_fc_layout":"content","content":"

              This tool will fit a parametric curve to each location and forecast future time series by extrapolating the curve to future time steps. You could specify the curve type for all counties that you would like to use to forecast the data, or you can let the tool to automatically detect the optimal curve type for each location based on the overall fit or the validation result. You could also select the number of time steps to forecast (1 by default, 50% of total observed time steps as maximum), and you can also choose number of time steps excluded for validation (10% of total observed time steps by default, and 25% as maximum). For this blog, we will let the tool select the optimal curve type to use for each county and exclude the last 10 time steps as validation data. For each location, the curve type leading to the smallest validation Root Mean Squared Error (RMSE) at that location will be chosen as optimal curve and used for forecasting. In some cases, you will see \u201cmean\u201d chosen as the forecast method at some location, this indicates that the observed data will get the smallest validation RMSE using the mean value as fitted value for every single step, compared to using the other four types of curve. In this case, the forecasts will also the mean of observed data.<\/p>\n

              You could save the forecast results as an Output Features<\/strong> and an optional Output Space Time Cube<\/strong>, which can be consumed in the Evaluate Forecasts By Location<\/strong> tool to evaluate forecast results from various forecast methods. The Output Features contain the population forecasts for 11 years and the formulas of parametric curves in the attribute table. The Output Features are symbolized with the forecasted value of the final forecast time step, the population forecast of the year 2030 in this case.<\/p>\n"},{"acf_fc_layout":"image","image":{"ID":1383772,"id":1383772,"title":"curve fit step 2 map","filename":"curve-fit-step-2-map.png","filesize":217730,"url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/curve-fit-step-2-map.png","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/looking-to-the-future-using-gis-to-model-and-predict-population\/curve-fit-step-2-map","alt":"","author":"55021","description":"","caption":"","name":"curve-fit-step-2-map","status":"inherit","uploaded_to":1383552,"date":"2021-10-27 19:17:07","modified":"2021-10-27 19:17:07","menu_order":0,"mime_type":"image\/png","type":"image","subtype":"png","icon":"https:\/\/www.esri.com\/arcgis-blog\/wp-includes\/images\/media\/default.png","width":742,"height":449,"sizes":{"thumbnail":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/curve-fit-step-2-map-213x200.png","thumbnail-width":213,"thumbnail-height":200,"medium":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/curve-fit-step-2-map.png","medium-width":431,"medium-height":261,"medium_large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/curve-fit-step-2-map.png","medium_large-width":742,"medium_large-height":449,"large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/curve-fit-step-2-map.png","large-width":742,"large-height":449,"1536x1536":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/curve-fit-step-2-map.png","1536x1536-width":742,"1536x1536-height":449,"2048x2048":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/curve-fit-step-2-map.png","2048x2048-width":742,"2048x2048-height":449,"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/curve-fit-step-2-map.png","card_image-width":742,"card_image-height":449,"wide_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/curve-fit-step-2-map.png","wide_image-width":742,"wide_image-height":449}},"image_position":"center","orientation":"horizontal","hyperlink":""},{"acf_fc_layout":"content","content":"

              3. Click on a few of the counties on the map and explore the information in the pop-up window. It shows detailed information about the forecast and an interactive line chart. In this chart, a blue line visualizes the historic population from 1969 to 2019 for each individual county and an orange line shows the fitting and prediction using a specific curve type. The black vertical dotted line shows where the forecast starts. You can also hover over the chart to read the observed value and forecasted value at each time step. Above the chart are some statistics related to the fitted curve at the location, including forecast Root Mean Squared Error (showing the overall fit of the forecast model), the validation Root Mean Squared Error (showing the forecasting power of the validation model), chosen forecast method and its formula.<\/p>\n"},{"acf_fc_layout":"image","image":{"ID":1383792,"id":1383792,"title":"curve fit step 3","filename":"curve-fit-step-3.png","filesize":34790,"url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/curve-fit-step-3.png","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/looking-to-the-future-using-gis-to-model-and-predict-population\/curve-fit-step-3","alt":"","author":"55021","description":"","caption":"","name":"curve-fit-step-3","status":"inherit","uploaded_to":1383552,"date":"2021-10-27 19:17:10","modified":"2021-10-27 19:17:10","menu_order":0,"mime_type":"image\/png","type":"image","subtype":"png","icon":"https:\/\/www.esri.com\/arcgis-blog\/wp-includes\/images\/media\/default.png","width":609,"height":578,"sizes":{"thumbnail":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/curve-fit-step-3-213x200.png","thumbnail-width":213,"thumbnail-height":200,"medium":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/curve-fit-step-3.png","medium-width":275,"medium-height":261,"medium_large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/curve-fit-step-3.png","medium_large-width":609,"medium_large-height":578,"large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/curve-fit-step-3.png","large-width":609,"large-height":578,"1536x1536":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/curve-fit-step-3.png","1536x1536-width":609,"1536x1536-height":578,"2048x2048":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/curve-fit-step-3.png","2048x2048-width":609,"2048x2048-height":578,"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/curve-fit-step-3-490x465.png","card_image-width":490,"card_image-height":465,"wide_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/curve-fit-step-3.png","wide_image-width":609,"wide_image-height":578}},"image_position":"center","orientation":"horizontal","hyperlink":""},{"acf_fc_layout":"content","content":"

              Creating an interactive bar chart counting number of locations using different forecast methods will be very helpful to understand the different patterns. Let\u2019s do it using the following steps.<\/p>\n

              4. In the Contents<\/strong> pane, right-click USA_County_Population_2030_CF<\/strong>, point to Create Chart<\/strong>, and choose Bar Chart<\/strong>.<\/p>\n"},{"acf_fc_layout":"image","image":{"ID":1383812,"id":1383812,"title":"curve fit step 4","filename":"curve-fit-step-4.png","filesize":24650,"url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/curve-fit-step-4.png","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/looking-to-the-future-using-gis-to-model-and-predict-population\/curve-fit-step-4","alt":"","author":"55021","description":"","caption":"","name":"curve-fit-step-4","status":"inherit","uploaded_to":1383552,"date":"2021-10-27 19:17:11","modified":"2021-10-27 19:17:11","menu_order":0,"mime_type":"image\/png","type":"image","subtype":"png","icon":"https:\/\/www.esri.com\/arcgis-blog\/wp-includes\/images\/media\/default.png","width":558,"height":306,"sizes":{"thumbnail":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/curve-fit-step-4-213x200.png","thumbnail-width":213,"thumbnail-height":200,"medium":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/curve-fit-step-4.png","medium-width":464,"medium-height":254,"medium_large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/curve-fit-step-4.png","medium_large-width":558,"medium_large-height":306,"large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/curve-fit-step-4.png","large-width":558,"large-height":306,"1536x1536":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/curve-fit-step-4.png","1536x1536-width":558,"1536x1536-height":306,"2048x2048":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/curve-fit-step-4.png","2048x2048-width":558,"2048x2048-height":306,"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/curve-fit-step-4.png","card_image-width":558,"card_image-height":306,"wide_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/curve-fit-step-4.png","wide_image-width":558,"wide_image-height":306}},"image_position":"center","orientation":"horizontal","hyperlink":""},{"acf_fc_layout":"content","content":"

              The Chart Properties<\/strong> panes and a chart view appear. Initially, the chart view is empty.<\/p>\n

              5. In the Chart Properties pane, change the following parameters:<\/p>\n

                \n
              • For Category or Date<\/strong>, specify Forecast Method<\/strong>.<\/li>\n
              • For Sort<\/strong>, select Y-axis Descending<\/strong>.<\/li>\n<\/ul>\n"},{"acf_fc_layout":"image","image":{"ID":1383822,"id":1383822,"title":"curve fit step 5","filename":"curve-fit-step-5.png","filesize":11021,"url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/curve-fit-step-5.png","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/looking-to-the-future-using-gis-to-model-and-predict-population\/curve-fit-step-5","alt":"","author":"55021","description":"","caption":"","name":"curve-fit-step-5","status":"inherit","uploaded_to":1383552,"date":"2021-10-27 19:17:12","modified":"2021-10-27 19:17:12","menu_order":0,"mime_type":"image\/png","type":"image","subtype":"png","icon":"https:\/\/www.esri.com\/arcgis-blog\/wp-includes\/images\/media\/default.png","width":404,"height":485,"sizes":{"thumbnail":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/curve-fit-step-5-213x200.png","thumbnail-width":213,"thumbnail-height":200,"medium":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/curve-fit-step-5.png","medium-width":217,"medium-height":261,"medium_large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/curve-fit-step-5.png","medium_large-width":404,"medium_large-height":485,"large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/curve-fit-step-5.png","large-width":404,"large-height":485,"1536x1536":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/curve-fit-step-5.png","1536x1536-width":404,"1536x1536-height":485,"2048x2048":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/curve-fit-step-5.png","2048x2048-width":404,"2048x2048-height":485,"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/curve-fit-step-5-387x465.png","card_image-width":387,"card_image-height":465,"wide_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/curve-fit-step-5.png","wide_image-width":404,"wide_image-height":485}},"image_position":"center","orientation":"horizontal","hyperlink":""},{"acf_fc_layout":"content","content":"

                6. Click on a specific type of curve in the bar chart, all the places where the specific curve fit forecast was applied to will be highlighted on the map. This interaction makes it extremely easy for you to understand the different trends and characteristics of population growths among the US counties. You can also go one step further and symbolize the map using the Forecast Methods field.<\/p>\n"},{"acf_fc_layout":"image","image":{"ID":1383832,"id":1383832,"title":"curve fit step 6","filename":"curve-fit-step-6.png","filesize":209073,"url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/curve-fit-step-6.png","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/looking-to-the-future-using-gis-to-model-and-predict-population\/curve-fit-step-6","alt":"","author":"55021","description":"","caption":"","name":"curve-fit-step-6","status":"inherit","uploaded_to":1383552,"date":"2021-10-27 19:17:14","modified":"2021-10-27 19:17:14","menu_order":0,"mime_type":"image\/png","type":"image","subtype":"png","icon":"https:\/\/www.esri.com\/arcgis-blog\/wp-includes\/images\/media\/default.png","width":850,"height":863,"sizes":{"thumbnail":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/curve-fit-step-6-213x200.png","thumbnail-width":213,"thumbnail-height":200,"medium":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/curve-fit-step-6.png","medium-width":257,"medium-height":261,"medium_large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/curve-fit-step-6.png","medium_large-width":768,"medium_large-height":780,"large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/curve-fit-step-6.png","large-width":850,"large-height":863,"1536x1536":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/curve-fit-step-6.png","1536x1536-width":850,"1536x1536-height":863,"2048x2048":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/curve-fit-step-6.png","2048x2048-width":850,"2048x2048-height":863,"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/curve-fit-step-6-458x465.png","card_image-width":458,"card_image-height":465,"wide_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/curve-fit-step-6.png","wide_image-width":850,"wide_image-height":863}},"image_position":"center","orientation":"horizontal","hyperlink":""},{"acf_fc_layout":"content","content":"

                Forecasting future population using Exponential Smoothing Forecast<\/h2>\n

                Next, we would use the Exponential Smoothing Forecast to project the population in the future 11 years (2020 \u2013 2030). The Exponential Smoothing Forecast works by decomposing the population time series at each county into seasonal and trend components. Therefore, this tool works best on population data that has moderate trends and strong seasonal behavior.<\/p>\n

                1. In the Geoprocessing<\/strong> pane, in the search box, type Exponential Smoothing<\/em>. In the search results, click Exponential Smoothing Forecast to open the dialog.<\/p>\n"},{"acf_fc_layout":"image","image":{"ID":1383862,"id":1383862,"title":"exponential smoothing step 1","filename":"exponential-smoothing-step-1.png","filesize":9882,"url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/exponential-smoothing-step-1.png","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/looking-to-the-future-using-gis-to-model-and-predict-population\/exponential-smoothing-step-1","alt":"","author":"55021","description":"","caption":"","name":"exponential-smoothing-step-1","status":"inherit","uploaded_to":1383552,"date":"2021-10-27 19:27:10","modified":"2021-10-27 19:27:10","menu_order":0,"mime_type":"image\/png","type":"image","subtype":"png","icon":"https:\/\/www.esri.com\/arcgis-blog\/wp-includes\/images\/media\/default.png","width":402,"height":236,"sizes":{"thumbnail":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/exponential-smoothing-step-1-213x200.png","thumbnail-width":213,"thumbnail-height":200,"medium":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/exponential-smoothing-step-1.png","medium-width":402,"medium-height":236,"medium_large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/exponential-smoothing-step-1.png","medium_large-width":402,"medium_large-height":236,"large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/exponential-smoothing-step-1.png","large-width":402,"large-height":236,"1536x1536":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/exponential-smoothing-step-1.png","1536x1536-width":402,"1536x1536-height":236,"2048x2048":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/exponential-smoothing-step-1.png","2048x2048-width":402,"2048x2048-height":236,"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/exponential-smoothing-step-1.png","card_image-width":402,"card_image-height":236,"wide_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/exponential-smoothing-step-1.png","wide_image-width":402,"wide_image-height":236}},"image_position":"center","orientation":"horizontal","hyperlink":""},{"acf_fc_layout":"content","content":"

                2. In the Exponential Smoothing Forecast geoprocessing tool, change the following parameters:<\/p>\n

                  \n
                • For Input Space Time Cube<\/strong>, specify USA_County_Population_1969_2019.nc<\/strong>.<\/li>\n
                • For Analysis Variable<\/strong>, select POPULATION_SUM_ZERO<\/strong>.<\/li>\n
                • For Number of Time Steps to Forecast<\/strong>, type 11<\/strong>. This means we will forecast 11 time steps out to the future, specifically, from 2020 to 2030.<\/li>\n
                • For Output Features<\/strong>, type USA_County_Population_2030_ES<\/em>.<\/li>\n
                • For Output Space Time Cube<\/strong>, type USA_County_Population_2030_ES.nc<\/em>.<\/li>\n
                • For Season Length<\/strong>, leave it as default, which is empty<\/strong>.<\/li>\n
                • For Number of Time Steps to Exclude for Validation<\/strong>, type 10<\/strong>.<\/li>\n
                • For Outlier Option<\/strong>, leave it as default, which is None<\/strong>.<\/li>\n<\/ul>\n

                  Click Run<\/strong>.<\/p>\n"},{"acf_fc_layout":"image","image":{"ID":1383872,"id":1383872,"title":"exponential smoothing step 2","filename":"exponential-smoothing-step-2.png","filesize":14233,"url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/exponential-smoothing-step-2.png","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/looking-to-the-future-using-gis-to-model-and-predict-population\/exponential-smoothing-step-2","alt":"","author":"55021","description":"","caption":"","name":"exponential-smoothing-step-2","status":"inherit","uploaded_to":1383552,"date":"2021-10-27 19:27:11","modified":"2021-10-27 19:27:11","menu_order":0,"mime_type":"image\/png","type":"image","subtype":"png","icon":"https:\/\/www.esri.com\/arcgis-blog\/wp-includes\/images\/media\/default.png","width":400,"height":376,"sizes":{"thumbnail":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/exponential-smoothing-step-2-213x200.png","thumbnail-width":213,"thumbnail-height":200,"medium":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/exponential-smoothing-step-2.png","medium-width":278,"medium-height":261,"medium_large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/exponential-smoothing-step-2.png","medium_large-width":400,"medium_large-height":376,"large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/exponential-smoothing-step-2.png","large-width":400,"large-height":376,"1536x1536":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/exponential-smoothing-step-2.png","1536x1536-width":400,"1536x1536-height":376,"2048x2048":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/exponential-smoothing-step-2.png","2048x2048-width":400,"2048x2048-height":376,"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/exponential-smoothing-step-2.png","card_image-width":400,"card_image-height":376,"wide_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/exponential-smoothing-step-2.png","wide_image-width":400,"wide_image-height":376}},"image_position":"center","orientation":"horizontal","hyperlink":""},{"acf_fc_layout":"content","content":"

                  3. Click a few counties on the output features to see the detailed statistical results and informative pop-ups. Notice that the method also provides a 90% confidence interval of the forecasts, shown as the transparent orange cone around the forecasted line.<\/p>\n"},{"acf_fc_layout":"image","image":{"ID":1383882,"id":1383882,"title":"exponential smoothing step 3","filename":"exponential-smoothing-step-3.png","filesize":40438,"url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/exponential-smoothing-step-3.png","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/looking-to-the-future-using-gis-to-model-and-predict-population\/exponential-smoothing-step-3","alt":"","author":"55021","description":"","caption":"","name":"exponential-smoothing-step-3","status":"inherit","uploaded_to":1383552,"date":"2021-10-27 19:27:12","modified":"2021-10-27 19:27:12","menu_order":0,"mime_type":"image\/png","type":"image","subtype":"png","icon":"https:\/\/www.esri.com\/arcgis-blog\/wp-includes\/images\/media\/default.png","width":599,"height":572,"sizes":{"thumbnail":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/exponential-smoothing-step-3-213x200.png","thumbnail-width":213,"thumbnail-height":200,"medium":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/exponential-smoothing-step-3.png","medium-width":273,"medium-height":261,"medium_large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/exponential-smoothing-step-3.png","medium_large-width":599,"medium_large-height":572,"large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/exponential-smoothing-step-3.png","large-width":599,"large-height":572,"1536x1536":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/exponential-smoothing-step-3.png","1536x1536-width":599,"1536x1536-height":572,"2048x2048":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/exponential-smoothing-step-3.png","2048x2048-width":599,"2048x2048-height":572,"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/exponential-smoothing-step-3-487x465.png","card_image-width":487,"card_image-height":465,"wide_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/exponential-smoothing-step-3.png","wide_image-width":599,"wide_image-height":572}},"image_position":"center","orientation":"horizontal","hyperlink":""},{"acf_fc_layout":"content","content":"

                  Given that the population data in most counties do not have a clear seasonal pattern, we can guess most of the counties should get a detected season length of 1, which means no periodic patterns detected by the method. Let\u2019s create a histogram to check if it is the case.<\/p>\n

                  4. In the Contents<\/strong> pane, right-click USA_County_Population_2030_ES<\/strong>, point to Create Chart<\/strong>, and choose Histogram<\/strong>.<\/p>\n"},{"acf_fc_layout":"image","image":{"ID":1383892,"id":1383892,"title":"exponential smoothing step 4","filename":"exponential-smoothing-step-4.png","filesize":21691,"url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/exponential-smoothing-step-4.png","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/looking-to-the-future-using-gis-to-model-and-predict-population\/exponential-smoothing-step-4","alt":"","author":"55021","description":"","caption":"","name":"exponential-smoothing-step-4","status":"inherit","uploaded_to":1383552,"date":"2021-10-27 19:27:14","modified":"2021-10-27 19:27:14","menu_order":0,"mime_type":"image\/png","type":"image","subtype":"png","icon":"https:\/\/www.esri.com\/arcgis-blog\/wp-includes\/images\/media\/default.png","width":584,"height":256,"sizes":{"thumbnail":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/exponential-smoothing-step-4-213x200.png","thumbnail-width":213,"thumbnail-height":200,"medium":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/exponential-smoothing-step-4.png","medium-width":464,"medium-height":203,"medium_large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/exponential-smoothing-step-4.png","medium_large-width":584,"medium_large-height":256,"large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/exponential-smoothing-step-4.png","large-width":584,"large-height":256,"1536x1536":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/exponential-smoothing-step-4.png","1536x1536-width":584,"1536x1536-height":256,"2048x2048":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/exponential-smoothing-step-4.png","2048x2048-width":584,"2048x2048-height":256,"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/exponential-smoothing-step-4.png","card_image-width":584,"card_image-height":256,"wide_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/exponential-smoothing-step-4.png","wide_image-width":584,"wide_image-height":256}},"image_position":"center","orientation":"horizontal","hyperlink":""},{"acf_fc_layout":"content","content":"

                  The Chart Properties<\/strong> panes and a chart view appear. Initially, the chart view is empty.<\/p>\n

                  5. In the Chart Properties<\/strong> pane, on the Data<\/strong> tab:<\/p>\n

                    \n
                  • Under Variable<\/strong>, for Number<\/strong>, choose Season Length<\/strong>.<\/li>\n
                  • Under Bins<\/strong>, specify 16<\/strong>.<\/li>\n<\/ul>\n

                    The chart updates to show a histogram of temperature measurements and the chart title Distribution of Season Length<\/strong> appears. Additionally, the Statistics<\/strong> group in Chart Properties<\/strong> updates, showing various statistics for the Season Length<\/strong> histogram field.<\/p>\n

                    6. In the Statistics <\/strong>group, leave Mean<\/strong> checked, and check Median<\/strong> and Std. Dev.<\/strong><\/p>\n"},{"acf_fc_layout":"image","image":{"ID":1383902,"id":1383902,"title":"exponential smoothing step 5","filename":"exponential-smoothing-step-5.png","filesize":13551,"url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/exponential-smoothing-step-5.png","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/looking-to-the-future-using-gis-to-model-and-predict-population\/exponential-smoothing-step-5","alt":"","author":"55021","description":"","caption":"","name":"exponential-smoothing-step-5","status":"inherit","uploaded_to":1383552,"date":"2021-10-27 19:27:15","modified":"2021-10-27 19:27:15","menu_order":0,"mime_type":"image\/png","type":"image","subtype":"png","icon":"https:\/\/www.esri.com\/arcgis-blog\/wp-includes\/images\/media\/default.png","width":401,"height":624,"sizes":{"thumbnail":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/exponential-smoothing-step-5-213x200.png","thumbnail-width":213,"thumbnail-height":200,"medium":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/exponential-smoothing-step-5.png","medium-width":168,"medium-height":261,"medium_large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/exponential-smoothing-step-5.png","medium_large-width":401,"medium_large-height":624,"large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/exponential-smoothing-step-5.png","large-width":401,"large-height":624,"1536x1536":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/exponential-smoothing-step-5.png","1536x1536-width":401,"1536x1536-height":624,"2048x2048":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/exponential-smoothing-step-5.png","2048x2048-width":401,"2048x2048-height":624,"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/exponential-smoothing-step-5-299x465.png","card_image-width":299,"card_image-height":465,"wide_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/exponential-smoothing-step-5.png","wide_image-width":401,"wide_image-height":624}},"image_position":"center","orientation":"horizontal","hyperlink":""},{"acf_fc_layout":"content","content":"

                    In the Distribution of Season Length histogram, a blue vertical line is displayed at the Mean season length (1.5). The Median temperature (1) is displayed in purple and the Mean plus 1 Standard Deviation (1.5 + 2.45 = 3.95) is in grey. Season length values are right-skewed, as we have guessed, most of the counties have detected season length to be 1.<\/p>\n

                    7. You might be curious about the counties that have some kinds of seasonality. Drag a box over the bins large than 1 to highlight locations with season lengths greater than 1 from the histogram chart and show them on the map. You can also click to see their pop-ups to get more details.<\/p>\n"},{"acf_fc_layout":"image","image":{"ID":1383912,"id":1383912,"title":"exponential smoothing step 6","filename":"exponential-smoothing-step-6.png","filesize":208112,"url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/exponential-smoothing-step-6.png","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/looking-to-the-future-using-gis-to-model-and-predict-population\/exponential-smoothing-step-6","alt":"","author":"55021","description":"","caption":"","name":"exponential-smoothing-step-6","status":"inherit","uploaded_to":1383552,"date":"2021-10-27 19:27:16","modified":"2021-10-27 19:27:16","menu_order":0,"mime_type":"image\/png","type":"image","subtype":"png","icon":"https:\/\/www.esri.com\/arcgis-blog\/wp-includes\/images\/media\/default.png","width":843,"height":863,"sizes":{"thumbnail":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/exponential-smoothing-step-6-213x200.png","thumbnail-width":213,"thumbnail-height":200,"medium":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/exponential-smoothing-step-6.png","medium-width":255,"medium-height":261,"medium_large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/exponential-smoothing-step-6.png","medium_large-width":768,"medium_large-height":786,"large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/exponential-smoothing-step-6.png","large-width":843,"large-height":863,"1536x1536":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/exponential-smoothing-step-6.png","1536x1536-width":843,"1536x1536-height":863,"2048x2048":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/exponential-smoothing-step-6.png","2048x2048-width":843,"2048x2048-height":863,"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/exponential-smoothing-step-6-454x465.png","card_image-width":454,"card_image-height":465,"wide_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/exponential-smoothing-step-6.png","wide_image-width":843,"wide_image-height":863}},"image_position":"center","orientation":"horizontal","hyperlink":""},{"acf_fc_layout":"content","content":"

                    Forecasting future population using Forest-based Forecast<\/h2>\n

                    We could also use the Forest-based Forecast tool to predict future population for each county. Forest-based Forecast will use an adapted random forest algorithm to train space-time data based on time windows and forecast future time slices for each location.<\/p>\n

                    1. In the Geoprocessing<\/strong> pane, in the search box, type forest-based<\/em>. In the search results, click Forest-based Forecast to open the dialog.<\/p>\n"},{"acf_fc_layout":"image","image":{"ID":1384032,"id":1384032,"title":"forest based forecast step 1","filename":"forest-based-forecast-step-1.png","filesize":15577,"url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/forest-based-forecast-step-1.png","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/looking-to-the-future-using-gis-to-model-and-predict-population\/forest-based-forecast-step-1","alt":"","author":"55021","description":"","caption":"","name":"forest-based-forecast-step-1","status":"inherit","uploaded_to":1383552,"date":"2021-10-27 19:47:29","modified":"2021-10-27 19:47:29","menu_order":0,"mime_type":"image\/png","type":"image","subtype":"png","icon":"https:\/\/www.esri.com\/arcgis-blog\/wp-includes\/images\/media\/default.png","width":402,"height":330,"sizes":{"thumbnail":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/forest-based-forecast-step-1-213x200.png","thumbnail-width":213,"thumbnail-height":200,"medium":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/forest-based-forecast-step-1.png","medium-width":318,"medium-height":261,"medium_large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/forest-based-forecast-step-1.png","medium_large-width":402,"medium_large-height":330,"large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/forest-based-forecast-step-1.png","large-width":402,"large-height":330,"1536x1536":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/forest-based-forecast-step-1.png","1536x1536-width":402,"1536x1536-height":330,"2048x2048":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/forest-based-forecast-step-1.png","2048x2048-width":402,"2048x2048-height":330,"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/forest-based-forecast-step-1.png","card_image-width":402,"card_image-height":330,"wide_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/forest-based-forecast-step-1.png","wide_image-width":402,"wide_image-height":330}},"image_position":"center","orientation":"horizontal","hyperlink":""},{"acf_fc_layout":"content","content":"

                    2. In the Forest-based Forecast geoprocessing tool, change the following parameters:<\/p>\n

                      \n
                    • For Input Space Time Cube<\/strong>, specify USA_County_Population_1969_2019.nc<\/strong>.<\/li>\n
                    • For Analysis Variable<\/strong>, select POPULATION_SUM_ZERO<\/strong>.<\/li>\n
                    • For Number of Time Steps to Forecast<\/strong>, type 11<\/strong>. This means we will forecast 11 time steps out to the future, specifically, from 2020 to 2030.<\/li>\n
                    • For Output Features<\/strong>, type USA_County_Population_2030_FB<\/em>.<\/li>\n
                    • For Output Space Time Cube<\/strong>, type USA_County_Population_2030_FB.nc<\/em>.<\/li>\n
                    • For Time Step Window<\/strong>, leave it as default, which is empty<\/strong>.<\/li>\n
                    • For Number of Time Steps to Exclude for Validation<\/strong>, type 10<\/strong>.<\/li>\n
                    • For Forecast Approach<\/strong>, leave it as default, which is Build Model by value after detrending<\/strong>.<\/li>\n
                    • For Outlier Option<\/strong>, leave it as default, which is None<\/strong>.<\/li>\n<\/ul>\n

                      Click Run<\/strong>.<\/p>\n"},{"acf_fc_layout":"image","image":{"ID":1384052,"id":1384052,"title":"forest based forecast step 2","filename":"forest-based-forecast-step-2.png","filesize":15788,"url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/forest-based-forecast-step-2.png","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/looking-to-the-future-using-gis-to-model-and-predict-population\/forest-based-forecast-step-2","alt":"","author":"55021","description":"","caption":"","name":"forest-based-forecast-step-2","status":"inherit","uploaded_to":1383552,"date":"2021-10-27 19:47:31","modified":"2021-10-27 19:47:31","menu_order":0,"mime_type":"image\/png","type":"image","subtype":"png","icon":"https:\/\/www.esri.com\/arcgis-blog\/wp-includes\/images\/media\/default.png","width":402,"height":429,"sizes":{"thumbnail":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/forest-based-forecast-step-2-213x200.png","thumbnail-width":213,"thumbnail-height":200,"medium":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/forest-based-forecast-step-2.png","medium-width":245,"medium-height":261,"medium_large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/forest-based-forecast-step-2.png","medium_large-width":402,"medium_large-height":429,"large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/forest-based-forecast-step-2.png","large-width":402,"large-height":429,"1536x1536":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/forest-based-forecast-step-2.png","1536x1536-width":402,"1536x1536-height":429,"2048x2048":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/forest-based-forecast-step-2.png","2048x2048-width":402,"2048x2048-height":429,"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/forest-based-forecast-step-2.png","card_image-width":402,"card_image-height":429,"wide_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/forest-based-forecast-step-2.png","wide_image-width":402,"wide_image-height":429}},"image_position":"center","orientation":"horizontal","hyperlink":""},{"acf_fc_layout":"content","content":"

                      While you specify exactly the same values for the parameters including Input Space Time Cube<\/strong>, Analysis Variable<\/strong>, Number of Time Steps to Forecast<\/strong>, And Number of Time Steps to Exclude for Validation<\/strong> as the previous two tools, you will also notice there are some parameters specific to this tool. One important new optional parameter is Time Step Window<\/strong>. It indicates the number of the previous time steps which would be used for model training. If not specified, the tool will automatically detect if there are any cyclic patterns or seasons in the data, using the same algorithm as in Exponential Smoothing Forecast. For locations detected with seasons, the season length will be used as the time step window those each location. For locations detected with no seasonality, 25% of total observed time steps (T), that is 25% * T, will be used as Time Step Window. So, by leaving this parameter blank, you\u2019re expecting to see Time Step Window varies from location to location and you can find the window size in the Forecast Method field in the Attribute Table of Output Forecast Features. If you want to set a uniform Time Step Window for all locations based on your expertise, just set a specific number in this parameter. Ideally, you should provide the number of time steps corresponding to one season. In this analysis, we will leave it blank and let the tool do the work. You can also create a histogram chart to exam the distribution of the Time Step Window across all US counties, as we did for Season Length in Exponential Smoothing Forecast.<\/p>\n

                      Here is a map of the forecasting results in 2030 produced by the Forest-based Forecast tool.<\/p>\n

                       <\/p>\n"},{"acf_fc_layout":"image","image":{"ID":1384042,"id":1384042,"title":"forest based forecast step 2 map","filename":"forest-based-forecast-step-2-map.png","filesize":270085,"url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/forest-based-forecast-step-2-map.png","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/looking-to-the-future-using-gis-to-model-and-predict-population\/forest-based-forecast-step-2-map","alt":"","author":"55021","description":"","caption":"","name":"forest-based-forecast-step-2-map","status":"inherit","uploaded_to":1383552,"date":"2021-10-27 19:47:30","modified":"2021-10-27 19:47:30","menu_order":0,"mime_type":"image\/png","type":"image","subtype":"png","icon":"https:\/\/www.esri.com\/arcgis-blog\/wp-includes\/images\/media\/default.png","width":990,"height":525,"sizes":{"thumbnail":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/forest-based-forecast-step-2-map-213x200.png","thumbnail-width":213,"thumbnail-height":200,"medium":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/forest-based-forecast-step-2-map.png","medium-width":464,"medium-height":246,"medium_large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/forest-based-forecast-step-2-map.png","medium_large-width":768,"medium_large-height":407,"large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/forest-based-forecast-step-2-map.png","large-width":990,"large-height":525,"1536x1536":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/forest-based-forecast-step-2-map.png","1536x1536-width":990,"1536x1536-height":525,"2048x2048":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/forest-based-forecast-step-2-map.png","2048x2048-width":990,"2048x2048-height":525,"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/forest-based-forecast-step-2-map-826x438.png","card_image-width":826,"card_image-height":438,"wide_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/forest-based-forecast-step-2-map.png","wide_image-width":990,"wide_image-height":525}},"image_position":"center","orientation":"horizontal","hyperlink":""},{"acf_fc_layout":"content","content":"

                      3. If you click on some of the counties and look at the pop-up charts, the line chart of the observed value and fitted values will indicate how well the model forecasted the yearly population in the county. You can also see the Time Window used in that location and if any seasonality is detected at that location. In the following case, no seasonality is detected at San Francisco County, CA therefore 25% of total time steps, which is rounded down (25% * 51) to 12 steps and used as the time window.<\/p>\n"},{"acf_fc_layout":"image","image":{"ID":1384062,"id":1384062,"title":"forest based forecast step 3","filename":"forest-based-forecast-step-3.png","filesize":40817,"url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/forest-based-forecast-step-3.png","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/looking-to-the-future-using-gis-to-model-and-predict-population\/forest-based-forecast-step-3","alt":"","author":"55021","description":"","caption":"","name":"forest-based-forecast-step-3","status":"inherit","uploaded_to":1383552,"date":"2021-10-27 19:47:32","modified":"2021-10-27 19:47:32","menu_order":0,"mime_type":"image\/png","type":"image","subtype":"png","icon":"https:\/\/www.esri.com\/arcgis-blog\/wp-includes\/images\/media\/default.png","width":598,"height":571,"sizes":{"thumbnail":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/forest-based-forecast-step-3-213x200.png","thumbnail-width":213,"thumbnail-height":200,"medium":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/forest-based-forecast-step-3.png","medium-width":273,"medium-height":261,"medium_large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/forest-based-forecast-step-3.png","medium_large-width":598,"medium_large-height":571,"large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/forest-based-forecast-step-3.png","large-width":598,"large-height":571,"1536x1536":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/forest-based-forecast-step-3.png","1536x1536-width":598,"1536x1536-height":571,"2048x2048":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/forest-based-forecast-step-3.png","2048x2048-width":598,"2048x2048-height":571,"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/forest-based-forecast-step-3-487x465.png","card_image-width":487,"card_image-height":465,"wide_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/forest-based-forecast-step-3.png","wide_image-width":598,"wide_image-height":571}},"image_position":"center","orientation":"horizontal","hyperlink":""},{"acf_fc_layout":"content","content":"

                      Selecting best prediction using Evaluating Forecasts By Location<\/h2>\n

                      Finally, we will explore model comparison and evaluation. We will compare the forecasting results for each time step from the Curve Fit Forecast, the Exponential Smoothing Forecast, and the Forest-based Forecast and select the best forecast for each location. As mentioned earlier, you need to save forecasts as Output Space Time Cubes<\/strong> when you run the three tools on the same Input Space Time Cube. We will refer to these cubes as Forecast Cubes<\/em> in this blog, and these forecast cubes will be the inputs in the Evaluation Forecasts by Location tool, and the output will be a hybrid forecast cube where each location is forecasted using the best forecast method.<\/p>\n

                      1. In the Geoprocessing<\/strong> pane, in the search box, type evaluate forecast<\/em>. In the search results, click Evaluate Forecasts by Location to open the dialog.<\/p>\n"},{"acf_fc_layout":"image","image":{"ID":1384072,"id":1384072,"title":"evaluate step 1","filename":"evaluate-step-1.png","filesize":10153,"url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/evaluate-step-1.png","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/looking-to-the-future-using-gis-to-model-and-predict-population\/evaluate-step-1","alt":"","author":"55021","description":"","caption":"","name":"evaluate-step-1","status":"inherit","uploaded_to":1383552,"date":"2021-10-27 19:58:30","modified":"2021-10-27 19:58:30","menu_order":0,"mime_type":"image\/png","type":"image","subtype":"png","icon":"https:\/\/www.esri.com\/arcgis-blog\/wp-includes\/images\/media\/default.png","width":398,"height":235,"sizes":{"thumbnail":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/evaluate-step-1-213x200.png","thumbnail-width":213,"thumbnail-height":200,"medium":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/evaluate-step-1.png","medium-width":398,"medium-height":235,"medium_large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/evaluate-step-1.png","medium_large-width":398,"medium_large-height":235,"large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/evaluate-step-1.png","large-width":398,"large-height":235,"1536x1536":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/evaluate-step-1.png","1536x1536-width":398,"1536x1536-height":235,"2048x2048":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/evaluate-step-1.png","2048x2048-width":398,"2048x2048-height":235,"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/evaluate-step-1.png","card_image-width":398,"card_image-height":235,"wide_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/evaluate-step-1.png","wide_image-width":398,"wide_image-height":235}},"image_position":"center","orientation":"horizontal","hyperlink":""},{"acf_fc_layout":"content","content":"

                      2. In the Evaluate Forecasts by Location geoprocessing tool, change the following parameters:<\/p>\n

                        \n
                      • For Input Forecast Space Time Cube<\/strong>, add USA_County_Population_2030_CF.nc<\/strong>, USA_County_Population_2030_ES.nc<\/strong>, USA_County_Population_2030_FB.nc<\/strong>.<\/li>\n
                      • For Output Features<\/strong>, type USA_County_Population_2030_EFBL<\/strong>.<\/li>\n
                      • For Output Space Time Cube<\/strong>, type USA_County_Population_2030_EFBL.nc<\/strong>.<\/li>\n
                      • Check Evaluate Using Validation Results<\/strong>.<\/li>\n<\/ul>\n

                        Click Run<\/strong>.<\/p>\n"},{"acf_fc_layout":"image","image":{"ID":1384082,"id":1384082,"title":"evaluate step 2","filename":"evaluate-step-2.png","filesize":11302,"url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/evaluate-step-2.png","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/looking-to-the-future-using-gis-to-model-and-predict-population\/evaluate-step-2","alt":"","author":"55021","description":"","caption":"","name":"evaluate-step-2","status":"inherit","uploaded_to":1383552,"date":"2021-10-27 19:58:31","modified":"2021-10-27 19:58:31","menu_order":0,"mime_type":"image\/png","type":"image","subtype":"png","icon":"https:\/\/www.esri.com\/arcgis-blog\/wp-includes\/images\/media\/default.png","width":401,"height":256,"sizes":{"thumbnail":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/evaluate-step-2-213x200.png","thumbnail-width":213,"thumbnail-height":200,"medium":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/evaluate-step-2.png","medium-width":401,"medium-height":256,"medium_large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/evaluate-step-2.png","medium_large-width":401,"medium_large-height":256,"large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/evaluate-step-2.png","large-width":401,"large-height":256,"1536x1536":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/evaluate-step-2.png","1536x1536-width":401,"1536x1536-height":256,"2048x2048":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/evaluate-step-2.png","2048x2048-width":401,"2048x2048-height":256,"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/evaluate-step-2.png","card_image-width":401,"card_image-height":256,"wide_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/evaluate-step-2.png","wide_image-width":401,"wide_image-height":256}},"image_position":"center","orientation":"horizontal","hyperlink":""},{"acf_fc_layout":"content","content":"

                        This tool could evaluate the forecasting models by validation or overall fitness of observed values. If the Evaluate Using Validation Results<\/strong> box is checked, the tool will determine the best forecast method for each location based on the smallest Root Mean Square Error for the validation set, the Validation RMSE. Remember that we have excluded the last few time steps as validation set before training the model \u2013 therefore the validation RMSE reveals the model\u2019s performance in predicting unseen data. One reminder here is to set the same number for Number of Time Steps to Exclude for Validation<\/strong> when running the forecast tools.\u00a0 This ensures that the Validation RMSE of forecast cubes are comparable. On the other hand, if we uncheck the Evaluate Using Validation Results<\/strong> box, the tool will use the forecasting RMSE to evaluate model performance, which generally represent the overall fitting between the line of original values and the line of the forecasted values. In this analysis, we use Validation RMSE as the criteria for choosing the best method.<\/p>\n

                        3. Click View Details<\/strong> in the geoprocessing progress bar, click Messages<\/strong> tab to check diagnostics.<\/p>\n"},{"acf_fc_layout":"image","image":{"ID":1384102,"id":1384102,"title":"evaluate step 3","filename":"evaluate-step-3.png","filesize":32503,"url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/evaluate-step-3.png","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/looking-to-the-future-using-gis-to-model-and-predict-population\/evaluate-step-3","alt":"","author":"55021","description":"","caption":"","name":"evaluate-step-3","status":"inherit","uploaded_to":1383552,"date":"2021-10-27 19:58:34","modified":"2021-10-27 19:58:34","menu_order":0,"mime_type":"image\/png","type":"image","subtype":"png","icon":"https:\/\/www.esri.com\/arcgis-blog\/wp-includes\/images\/media\/default.png","width":847,"height":508,"sizes":{"thumbnail":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/evaluate-step-3-213x200.png","thumbnail-width":213,"thumbnail-height":200,"medium":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/evaluate-step-3.png","medium-width":435,"medium-height":261,"medium_large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/evaluate-step-3.png","medium_large-width":768,"medium_large-height":461,"large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/evaluate-step-3.png","large-width":847,"large-height":508,"1536x1536":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/evaluate-step-3.png","1536x1536-width":847,"1536x1536-height":508,"2048x2048":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/evaluate-step-3.png","2048x2048-width":847,"2048x2048-height":508,"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/evaluate-step-3-775x465.png","card_image-width":775,"card_image-height":465,"wide_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/evaluate-step-3.png","wide_image-width":847,"wide_image-height":508}},"image_position":"center","orientation":"horizontal","hyperlink":""},{"acf_fc_layout":"content","content":"

                        This tool creates geoprocessing messages to help you understand the results. The messages contain information about the structure of the forecast cubes, summary statistics of the RMSE across forest cubes, and summaries of each forecast method is chosen by how many locations as the best method.<\/p>\n"},{"acf_fc_layout":"image","image":{"ID":1384092,"id":1384092,"title":"evaluate step 3 messages","filename":"evaluate-step-3-messages.png","filesize":48157,"url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/evaluate-step-3-messages.png","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/looking-to-the-future-using-gis-to-model-and-predict-population\/evaluate-step-3-messages","alt":"","author":"55021","description":"","caption":"","name":"evaluate-step-3-messages","status":"inherit","uploaded_to":1383552,"date":"2021-10-27 19:58:32","modified":"2021-10-27 19:58:32","menu_order":0,"mime_type":"image\/png","type":"image","subtype":"png","icon":"https:\/\/www.esri.com\/arcgis-blog\/wp-includes\/images\/media\/default.png","width":604,"height":1118,"sizes":{"thumbnail":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/evaluate-step-3-messages-213x200.png","thumbnail-width":213,"thumbnail-height":200,"medium":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/evaluate-step-3-messages.png","medium-width":141,"medium-height":261,"medium_large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/evaluate-step-3-messages.png","medium_large-width":604,"medium_large-height":1118,"large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/evaluate-step-3-messages.png","large-width":583,"large-height":1080,"1536x1536":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/evaluate-step-3-messages.png","1536x1536-width":604,"1536x1536-height":1118,"2048x2048":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/evaluate-step-3-messages.png","2048x2048-width":604,"2048x2048-height":1118,"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/evaluate-step-3-messages-251x465.png","card_image-width":251,"card_image-height":465,"wide_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/evaluate-step-3-messages-583x1080.png","wide_image-width":583,"wide_image-height":1080}},"image_position":"center","orientation":"horizontal","hyperlink":""},{"acf_fc_layout":"content","content":"

                        4. Click a couple of counties of interest and explore the pop-up chart. The best forecast method at that location will be highlighted in the legend to the right of the chart. You could also click on other methods in the legend to visualize the forecasted values of a specific method, or hover over the chart to check the details of each time step.<\/p>\n"},{"acf_fc_layout":"image","image":{"ID":1384112,"id":1384112,"title":"evaluate step 4","filename":"evaluate-step-4.png","filesize":41045,"url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/evaluate-step-4.png","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/looking-to-the-future-using-gis-to-model-and-predict-population\/evaluate-step-4","alt":"","author":"55021","description":"","caption":"","name":"evaluate-step-4","status":"inherit","uploaded_to":1383552,"date":"2021-10-27 19:58:35","modified":"2021-10-27 19:58:35","menu_order":0,"mime_type":"image\/png","type":"image","subtype":"png","icon":"https:\/\/www.esri.com\/arcgis-blog\/wp-includes\/images\/media\/default.png","width":806,"height":567,"sizes":{"thumbnail":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/evaluate-step-4-213x200.png","thumbnail-width":213,"thumbnail-height":200,"medium":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/evaluate-step-4.png","medium-width":371,"medium-height":261,"medium_large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/evaluate-step-4.png","medium_large-width":768,"medium_large-height":540,"large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/evaluate-step-4.png","large-width":806,"large-height":567,"1536x1536":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/evaluate-step-4.png","1536x1536-width":806,"1536x1536-height":567,"2048x2048":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/evaluate-step-4.png","2048x2048-width":806,"2048x2048-height":567,"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/evaluate-step-4-661x465.png","card_image-width":661,"card_image-height":465,"wide_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/evaluate-step-4.png","wide_image-width":806,"wide_image-height":567}},"image_position":"center","orientation":"horizontal","hyperlink":""},{"acf_fc_layout":"content","content":"

                        The\u00a0Output Features\u00a0will be added to the\u00a0map and symbolized based on the value of final forecasted time step of the selected method at each location. An alternative way to visualize the result is to symbolize the map using the Forecast Method chosen at each location. Let\u2019s quickly adjust the symbology.<\/p>\n

                        5. In the Contents<\/strong> pane, right-click USA_County_Population_2030_EFBL<\/strong>, choose Symbology<\/strong>.<\/p>\n"},{"acf_fc_layout":"image","image":{"ID":1384122,"id":1384122,"title":"evaluate step 5","filename":"evaluate-step-5.png","filesize":27713,"url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/evaluate-step-5.png","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/looking-to-the-future-using-gis-to-model-and-predict-population\/evaluate-step-5","alt":"","author":"55021","description":"","caption":"","name":"evaluate-step-5","status":"inherit","uploaded_to":1383552,"date":"2021-10-27 19:58:37","modified":"2021-10-27 19:58:37","menu_order":0,"mime_type":"image\/png","type":"image","subtype":"png","icon":"https:\/\/www.esri.com\/arcgis-blog\/wp-includes\/images\/media\/default.png","width":424,"height":482,"sizes":{"thumbnail":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/evaluate-step-5-213x200.png","thumbnail-width":213,"thumbnail-height":200,"medium":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/evaluate-step-5.png","medium-width":230,"medium-height":261,"medium_large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/evaluate-step-5.png","medium_large-width":424,"medium_large-height":482,"large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/evaluate-step-5.png","large-width":424,"large-height":482,"1536x1536":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/evaluate-step-5.png","1536x1536-width":424,"1536x1536-height":482,"2048x2048":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/evaluate-step-5.png","2048x2048-width":424,"2048x2048-height":482,"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/evaluate-step-5-409x465.png","card_image-width":409,"card_image-height":465,"wide_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/evaluate-step-5.png","wide_image-width":424,"wide_image-height":482}},"image_position":"center","orientation":"horizontal","hyperlink":""},{"acf_fc_layout":"content","content":"

                        6. In the Symbology pane, change the following settings:<\/p>\n

                          \n
                        • For Primary Symbology<\/strong>, specify Unique Values<\/strong>.<\/li>\n
                        • For Field 1<\/strong>, specify Forecast Method<\/strong>.<\/li>\n
                        • For Symbol<\/strong>, manually adjust the order, colors, and labels as you prefer. Here is an example of how we generated the following map:
                          \n\n\n\n\n\n\n\n\n\n\n
                          Symbol color (RGB)<\/strong><\/td>\nLabel<\/strong><\/td>\n<\/tr>\n
                          [255, 199, 0]<\/td>\nlinear<\/td>\n<\/tr>\n
                          [250, 165, 19]<\/td>\nexponential<\/td>\n<\/tr>\n
                          [244, 147, 104]<\/td>\nparabolic<\/td>\n<\/tr>\n
                          [242, 103, 69]<\/td>\ngompertz<\/td>\n<\/tr>\n
                          [49, 162, 189]<\/td>\nexponential smoothing<\/td>\n<\/tr>\n
                          [126, 87, 194]<\/td>\nforest-based<\/td>\n<\/tr>\n
                          [204, 204, 204]<\/td>\nmean<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/li>\n<\/ul>\n"},{"acf_fc_layout":"image","image":{"ID":1384142,"id":1384142,"title":"evaluate step 6","filename":"evaluate-step-6.png","filesize":13022,"url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/evaluate-step-6.png","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/looking-to-the-future-using-gis-to-model-and-predict-population\/evaluate-step-6","alt":"","author":"55021","description":"","caption":"","name":"evaluate-step-6","status":"inherit","uploaded_to":1383552,"date":"2021-10-27 19:58:40","modified":"2021-10-27 19:58:40","menu_order":0,"mime_type":"image\/png","type":"image","subtype":"png","icon":"https:\/\/www.esri.com\/arcgis-blog\/wp-includes\/images\/media\/default.png","width":481,"height":467,"sizes":{"thumbnail":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/evaluate-step-6-213x200.png","thumbnail-width":213,"thumbnail-height":200,"medium":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/evaluate-step-6.png","medium-width":269,"medium-height":261,"medium_large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/evaluate-step-6.png","medium_large-width":481,"medium_large-height":467,"large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/evaluate-step-6.png","large-width":481,"large-height":467,"1536x1536":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/evaluate-step-6.png","1536x1536-width":481,"1536x1536-height":467,"2048x2048":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/evaluate-step-6.png","2048x2048-width":481,"2048x2048-height":467,"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/evaluate-step-6-479x465.png","card_image-width":479,"card_image-height":465,"wide_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/evaluate-step-6.png","wide_image-width":481,"wide_image-height":467}},"image_position":"center","orientation":"horizontal","hyperlink":""},{"acf_fc_layout":"image","image":{"ID":1384132,"id":1384132,"title":"evaluate step 6 map","filename":"evaluate-step-6-map.png","filesize":318834,"url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/evaluate-step-6-map.png","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/looking-to-the-future-using-gis-to-model-and-predict-population\/evaluate-step-6-map","alt":"","author":"55021","description":"","caption":"","name":"evaluate-step-6-map","status":"inherit","uploaded_to":1383552,"date":"2021-10-27 19:58:38","modified":"2021-10-27 19:58:38","menu_order":0,"mime_type":"image\/png","type":"image","subtype":"png","icon":"https:\/\/www.esri.com\/arcgis-blog\/wp-includes\/images\/media\/default.png","width":889,"height":520,"sizes":{"thumbnail":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/evaluate-step-6-map-213x200.png","thumbnail-width":213,"thumbnail-height":200,"medium":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/evaluate-step-6-map.png","medium-width":446,"medium-height":261,"medium_large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/evaluate-step-6-map.png","medium_large-width":768,"medium_large-height":449,"large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/evaluate-step-6-map.png","large-width":889,"large-height":520,"1536x1536":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/evaluate-step-6-map.png","1536x1536-width":889,"1536x1536-height":520,"2048x2048":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/evaluate-step-6-map.png","2048x2048-width":889,"2048x2048-height":520,"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/evaluate-step-6-map-795x465.png","card_image-width":795,"card_image-height":465,"wide_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/evaluate-step-6-map.png","wide_image-width":889,"wide_image-height":520}},"image_position":"center","orientation":"horizontal","hyperlink":""},{"acf_fc_layout":"content","content":"

                          Conclusions<\/h2>\n

                          By using ArcGIS Pro as your spatial data science workstation, urban planners can get their population projection work done easily with the new Time Series Forecasting toolset, explore different scenarios of population growth, and plan for the future.<\/p>\n"}],"authors":[{"ID":245352,"user_firstname":"Stella","user_lastname":"Li","nickname":"Stella Li","user_nicename":"stellali","display_name":"Stella(Xintian) Li","user_email":"stellali@esri.com","user_url":"","user_registered":"2021-06-30 17:08:59","user_description":"Stella(Xintian) Li is a Product Engineer on Esri's Spatial Statistics team. As an urban enthusiast who has a strong passion for spatial statistics and data science, Stella enjoys finding solutions to urban, social, and environmental problems with data-driven methods. Her role at Esri includes doing research, building and maintaining spatial data science tools and capabilities, and creating learning resources to help users better understand and utilize the tools.","user_avatar":""},{"ID":55021,"user_firstname":"Jie","user_lastname":"Liu","nickname":"Jie","user_nicename":"j-liu","display_name":"Jie Liu","user_email":"j.liu@esri.com","user_url":"","user_registered":"2020-06-24 22:18:34","user_description":"Jie Liu is a senior product engineer on the Spatial Statistics team. Jie earned her bachelor\u2019s degree in Urban Planning and minored in Economics at Peking University, and earned dual degrees in Master of City Planning and Master of Urban and Spatial Analytics in School of Design, University of Pennsylvania. She dives deep into spatial statistics algorithms but is also design- and user-focused. She loves applying spatial data science to solve transportation planning and socio-economic problems. In her free time, Jie enjoys snowboarding, hiking, backpacking, cooking, and playing the ukulele.","user_avatar":""},{"ID":5141,"user_firstname":"Kevin","user_lastname":"Butler","nickname":"Kevin Butler","user_nicename":"kevi6890","display_name":"Kevin Butler","user_email":"KButler@esri.com","user_url":"","user_registered":"2018-03-02 00:16:49","user_description":"Kevin Butler is a Product Engineer on Esri\u2019s Analysis and Geoprocessing Team working as a liaison to the science community. He holds a Ph.D. in Geography from Kent State University. Over the past decade he has worked on strategic projects, partnering with customers and other members of the science community to assist in the development of large ecological information products such as the ecological land units, ecological marine units and ecological coastal units. His research interests include a thematic focus on spatial statistical analytical workflows, a methodological focus on spatial clustering techniques and a geographic focus on Puerto Rico and midwestern cities.","user_avatar":""}],"related_articles":[{"ID":1161192,"post_author":"55021","post_date":"2021-04-07 10:30:35","post_date_gmt":"2021-04-07 17:30:35","post_content":"","post_title":"Integrate a spatial approach and time series forecasting","post_excerpt":"","post_status":"publish","comment_status":"open","ping_status":"closed","post_password":"","post_name":"dev-summit-2021-integrate-spatial-approach-and-time-series-analysis","to_ping":"","pinged":"","post_modified":"2021-06-08 15:22:51","post_modified_gmt":"2021-06-08 22:22:51","post_content_filtered":"","post_parent":0,"guid":"https:\/\/www.esri.com\/arcgis-blog\/?post_type=blog&p=1161192","menu_order":0,"post_type":"blog","post_mime_type":"","comment_count":"0","filter":"raw"},{"ID":949901,"post_author":"55021","post_date":"2020-07-28 14:21:32","post_date_gmt":"2020-07-28 21:21:32","post_content":"","post_title":"Time Series Forecasting 101 \u2013 Part 1. COVID-19 data preparation with ArcGIS Notebooks in ArcGIS Pro","post_excerpt":"","post_status":"publish","comment_status":"open","ping_status":"closed","post_password":"","post_name":"time-series-forecasting-101-part-1-covid-19-data-preparation","to_ping":"","pinged":"","post_modified":"2020-07-30 20:53:06","post_modified_gmt":"2020-07-31 03:53:06","post_content_filtered":"","post_parent":0,"guid":"https:\/\/www.esri.com\/arcgis-blog\/?post_type=blog&p=949901","menu_order":0,"post_type":"blog","post_mime_type":"","comment_count":"0","filter":"raw"},{"ID":950761,"post_author":"55021","post_date":"2020-07-28 14:22:51","post_date_gmt":"2020-07-28 21:22:51","post_content":"","post_title":"Time Series Forecasting 101 \u2013 Part 2. Forecast COVID-19 daily new confirmed cases with Exponential Smoothing Forecast and Forest-based Forecast","post_excerpt":"","post_status":"publish","comment_status":"open","ping_status":"closed","post_password":"","post_name":"time-series-forecasting-101-part-2-forecast-covid-19-daily-new-confirmed-cases-with-exponential-smoothing-forecast-and-forest-based-forecast","to_ping":"","pinged":"","post_modified":"2020-07-31 13:56:46","post_modified_gmt":"2020-07-31 20:56:46","post_content_filtered":"","post_parent":0,"guid":"https:\/\/www.esri.com\/arcgis-blog\/?post_type=blog&p=950761","menu_order":0,"post_type":"blog","post_mime_type":"","comment_count":"0","filter":"raw"},{"ID":951201,"post_author":"55021","post_date":"2020-07-28 14:23:05","post_date_gmt":"2020-07-28 21:23:05","post_content":"","post_title":"Time Series Forecasting 101 \u2013 Part 3. Forecast COVID-19 cumulative confirmed cases with Curve Fit Forecast and Evaluate Forecasts by Location","post_excerpt":"","post_status":"publish","comment_status":"open","ping_status":"closed","post_password":"","post_name":"time-series-forecasting-101-part-3-forecast-covid-19-cumulative-confirmed-cases-with-curve-fit-forecast-and-evaluate-forecasts-by-location","to_ping":"","pinged":"","post_modified":"2020-07-31 13:54:24","post_modified_gmt":"2020-07-31 20:54:24","post_content_filtered":"","post_parent":0,"guid":"https:\/\/www.esri.com\/arcgis-blog\/?post_type=blog&p=951201","menu_order":0,"post_type":"blog","post_mime_type":"","comment_count":"0","filter":"raw"},{"ID":945871,"post_author":"58381","post_date":"2020-07-28 14:24:22","post_date_gmt":"2020-07-28 21:24:22","post_content":"","post_title":"Time Series Forecasting 101 - Part 4. Forecast and visualize with Exponential Smoothing","post_excerpt":"","post_status":"publish","comment_status":"open","ping_status":"closed","post_password":"","post_name":"time-series-forecasting-101-part-4-forecast-and-visualize-with-exponential-smoothing","to_ping":"","pinged":"","post_modified":"2020-07-31 09:52:31","post_modified_gmt":"2020-07-31 16:52:31","post_content_filtered":"","post_parent":0,"guid":"https:\/\/www.esri.com\/arcgis-blog\/?post_type=blog&p=945871","menu_order":0,"post_type":"blog","post_mime_type":"","comment_count":"0","filter":"raw"}],"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/card-new.jpg","wide_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/banner-3.jpg"},"yoast_head":"\nLooking to the future: Using GIS to model and predict population<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/looking-to-the-future-using-gis-to-model-and-predict-population\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Looking to the future: Using GIS to model and predict population\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/looking-to-the-future-using-gis-to-model-and-predict-population\" \/>\n<meta property=\"og:site_name\" content=\"ArcGIS Blog\" \/>\n<meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/esrigis\/\" \/>\n<meta property=\"article:modified_time\" content=\"2021-11-04T22:37:58+00:00\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:site\" content=\"@ESRI\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":[\"Article\",\"BlogPosting\"],\"@id\":\"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/looking-to-the-future-using-gis-to-model-and-predict-population#article\",\"isPartOf\":{\"@id\":\"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/looking-to-the-future-using-gis-to-model-and-predict-population\"},\"author\":{\"name\":\"Jie Liu\",\"@id\":\"https:\/\/www.esri.com\/arcgis-blog\/#\/schema\/person\/93673f70c14871835adf04d096f40925\"},\"headline\":\"Looking to the future: Using GIS to model and predict population\",\"datePublished\":\"2021-10-28T19:45:50+00:00\",\"dateModified\":\"2021-11-04T22:37:58+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/looking-to-the-future-using-gis-to-model-and-predict-population\"},\"wordCount\":11,\"commentCount\":0,\"publisher\":{\"@id\":\"https:\/\/www.esri.com\/arcgis-blog\/#organization\"},\"keywords\":[\"city planning\",\"population\",\"population forecast\",\"time series forecasting\",\"Urban Planning\"],\"articleSection\":[\"Analytics\"],\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"CommentAction\",\"name\":\"Comment\",\"target\":[\"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/looking-to-the-future-using-gis-to-model-and-predict-population#respond\"]}]},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/looking-to-the-future-using-gis-to-model-and-predict-population\",\"url\":\"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/looking-to-the-future-using-gis-to-model-and-predict-population\",\"name\":\"Looking to the future: Using GIS to model and predict population\",\"isPartOf\":{\"@id\":\"https:\/\/www.esri.com\/arcgis-blog\/#website\"},\"datePublished\":\"2021-10-28T19:45:50+00:00\",\"dateModified\":\"2021-11-04T22:37:58+00:00\",\"breadcrumb\":{\"@id\":\"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/looking-to-the-future-using-gis-to-model-and-predict-population#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/looking-to-the-future-using-gis-to-model-and-predict-population\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/looking-to-the-future-using-gis-to-model-and-predict-population#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/www.esri.com\/arcgis-blog\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Looking to the future: Using GIS to model and predict population\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.esri.com\/arcgis-blog\/#website\",\"url\":\"https:\/\/www.esri.com\/arcgis-blog\/\",\"name\":\"ArcGIS Blog\",\"description\":\"Get insider info from Esri product teams\",\"publisher\":{\"@id\":\"https:\/\/www.esri.com\/arcgis-blog\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/www.esri.com\/arcgis-blog\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\/\/www.esri.com\/arcgis-blog\/#organization\",\"name\":\"Esri\",\"url\":\"https:\/\/www.esri.com\/arcgis-blog\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/www.esri.com\/arcgis-blog\/#\/schema\/logo\/image\/\",\"url\":\"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/04\/Esri.png\",\"contentUrl\":\"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/04\/Esri.png\",\"width\":400,\"height\":400,\"caption\":\"Esri\"},\"image\":{\"@id\":\"https:\/\/www.esri.com\/arcgis-blog\/#\/schema\/logo\/image\/\"},\"sameAs\":[\"https:\/\/www.facebook.com\/esrigis\/\",\"https:\/\/x.com\/ESRI\",\"https:\/\/www.linkedin.com\/company\/5311\/\"]},{\"@type\":\"Person\",\"@id\":\"https:\/\/www.esri.com\/arcgis-blog\/#\/schema\/person\/93673f70c14871835adf04d096f40925\",\"name\":\"Jie Liu\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/www.esri.com\/arcgis-blog\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2020\/07\/jie-liu-1536x1536.jpg\",\"contentUrl\":\"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2020\/07\/jie-liu-1536x1536.jpg\",\"caption\":\"Jie Liu\"},\"description\":\"Jie Liu is a senior product engineer on the Spatial Statistics team. Jie earned her bachelor\u2019s degree in Urban Planning and minored in Economics at Peking University, and earned dual degrees in Master of City Planning and Master of Urban and Spatial Analytics in School of Design, University of Pennsylvania. She dives deep into spatial statistics algorithms but is also design- and user-focused. She loves applying spatial data science to solve transportation planning and socio-economic problems. In her free time, Jie enjoys snowboarding, hiking, backpacking, cooking, and playing the ukulele.\",\"sameAs\":[\"https:\/\/www.linkedin.com\/in\/amyjieliu\/\"],\"url\":\"https:\/\/www.esri.com\/arcgis-blog\/author\/j-liu\"}]}<\/script>\n<!-- \/ Yoast SEO Premium plugin. -->","yoast_head_json":{"title":"Looking to the future: Using GIS to model and predict population","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/looking-to-the-future-using-gis-to-model-and-predict-population","og_locale":"en_US","og_type":"article","og_title":"Looking to the future: Using GIS to model and predict population","og_url":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/looking-to-the-future-using-gis-to-model-and-predict-population","og_site_name":"ArcGIS Blog","article_publisher":"https:\/\/www.facebook.com\/esrigis\/","article_modified_time":"2021-11-04T22:37:58+00:00","twitter_card":"summary_large_image","twitter_site":"@ESRI","schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":["Article","BlogPosting"],"@id":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/looking-to-the-future-using-gis-to-model-and-predict-population#article","isPartOf":{"@id":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/looking-to-the-future-using-gis-to-model-and-predict-population"},"author":{"name":"Jie Liu","@id":"https:\/\/www.esri.com\/arcgis-blog\/#\/schema\/person\/93673f70c14871835adf04d096f40925"},"headline":"Looking to the future: Using GIS to model and predict population","datePublished":"2021-10-28T19:45:50+00:00","dateModified":"2021-11-04T22:37:58+00:00","mainEntityOfPage":{"@id":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/looking-to-the-future-using-gis-to-model-and-predict-population"},"wordCount":11,"commentCount":0,"publisher":{"@id":"https:\/\/www.esri.com\/arcgis-blog\/#organization"},"keywords":["city planning","population","population forecast","time series forecasting","Urban Planning"],"articleSection":["Analytics"],"inLanguage":"en-US","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/looking-to-the-future-using-gis-to-model-and-predict-population#respond"]}]},{"@type":"WebPage","@id":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/looking-to-the-future-using-gis-to-model-and-predict-population","url":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/looking-to-the-future-using-gis-to-model-and-predict-population","name":"Looking to the future: Using GIS to model and predict population","isPartOf":{"@id":"https:\/\/www.esri.com\/arcgis-blog\/#website"},"datePublished":"2021-10-28T19:45:50+00:00","dateModified":"2021-11-04T22:37:58+00:00","breadcrumb":{"@id":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/looking-to-the-future-using-gis-to-model-and-predict-population#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/looking-to-the-future-using-gis-to-model-and-predict-population"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/looking-to-the-future-using-gis-to-model-and-predict-population#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.esri.com\/arcgis-blog\/"},{"@type":"ListItem","position":2,"name":"Looking to the future: Using GIS to model and predict population"}]},{"@type":"WebSite","@id":"https:\/\/www.esri.com\/arcgis-blog\/#website","url":"https:\/\/www.esri.com\/arcgis-blog\/","name":"ArcGIS Blog","description":"Get insider info from Esri product teams","publisher":{"@id":"https:\/\/www.esri.com\/arcgis-blog\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.esri.com\/arcgis-blog\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/www.esri.com\/arcgis-blog\/#organization","name":"Esri","url":"https:\/\/www.esri.com\/arcgis-blog\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.esri.com\/arcgis-blog\/#\/schema\/logo\/image\/","url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/04\/Esri.png","contentUrl":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/04\/Esri.png","width":400,"height":400,"caption":"Esri"},"image":{"@id":"https:\/\/www.esri.com\/arcgis-blog\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/www.facebook.com\/esrigis\/","https:\/\/x.com\/ESRI","https:\/\/www.linkedin.com\/company\/5311\/"]},{"@type":"Person","@id":"https:\/\/www.esri.com\/arcgis-blog\/#\/schema\/person\/93673f70c14871835adf04d096f40925","name":"Jie Liu","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.esri.com\/arcgis-blog\/#\/schema\/person\/image\/","url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2020\/07\/jie-liu-1536x1536.jpg","contentUrl":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2020\/07\/jie-liu-1536x1536.jpg","caption":"Jie Liu"},"description":"Jie Liu is a senior product engineer on the Spatial Statistics team. Jie earned her bachelor\u2019s degree in Urban Planning and minored in Economics at Peking University, and earned dual degrees in Master of City Planning and Master of Urban and Spatial Analytics in School of Design, University of Pennsylvania. She dives deep into spatial statistics algorithms but is also design- and user-focused. She loves applying spatial data science to solve transportation planning and socio-economic problems. In her free time, Jie enjoys snowboarding, hiking, backpacking, cooking, and playing the ukulele.","sameAs":["https:\/\/www.linkedin.com\/in\/amyjieliu\/"],"url":"https:\/\/www.esri.com\/arcgis-blog\/author\/j-liu"}]}},"text_date":"October 28, 2021","author_name":"Multiple Authors","author_page":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/looking-to-the-future-using-gis-to-model-and-predict-population","custom_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2021\/10\/banner-3.jpg","primary_product":"ArcGIS Pro","tag_data":[{"term_id":431062,"name":"city planning","slug":"city-planning","term_group":0,"term_taxonomy_id":431062,"taxonomy":"post_tag","description":"","parent":0,"count":4,"filter":"raw"},{"term_id":25491,"name":"population","slug":"population","term_group":0,"term_taxonomy_id":25491,"taxonomy":"post_tag","description":"","parent":0,"count":16,"filter":"raw"},{"term_id":762462,"name":"population forecast","slug":"population-forecast","term_group":0,"term_taxonomy_id":762462,"taxonomy":"post_tag","description":"","parent":0,"count":1,"filter":"raw"},{"term_id":725501,"name":"time series forecasting","slug":"time-series-forecasting","term_group":0,"term_taxonomy_id":725501,"taxonomy":"post_tag","description":"","parent":0,"count":7,"filter":"raw"},{"term_id":26171,"name":"Urban Planning","slug":"urban-planning","term_group":0,"term_taxonomy_id":26171,"taxonomy":"post_tag","description":"","parent":0,"count":87,"filter":"raw"}],"category_data":[{"term_id":23341,"name":"Analytics","slug":"analytics","term_group":0,"term_taxonomy_id":23341,"taxonomy":"category","description":"","parent":0,"count":1345,"filter":"raw"}],"product_data":[{"term_id":36561,"name":"ArcGIS Pro","slug":"arcgis-pro","term_group":0,"term_taxonomy_id":36561,"taxonomy":"product","description":"","parent":0,"count":2091,"filter":"raw"}],"primary_product_link":"https:\/\/www.esri.com\/arcgis-blog\/?s=#&products=arcgis-pro","_links":{"self":[{"href":"https:\/\/www.esri.com\/arcgis-blog\/wp-json\/wp\/v2\/blog\/1383552","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.esri.com\/arcgis-blog\/wp-json\/wp\/v2\/blog"}],"about":[{"href":"https:\/\/www.esri.com\/arcgis-blog\/wp-json\/wp\/v2\/types\/blog"}],"author":[{"embeddable":true,"href":"https:\/\/www.esri.com\/arcgis-blog\/wp-json\/wp\/v2\/users\/55021"}],"replies":[{"embeddable":true,"href":"https:\/\/www.esri.com\/arcgis-blog\/wp-json\/wp\/v2\/comments?post=1383552"}],"version-history":[{"count":0,"href":"https:\/\/www.esri.com\/arcgis-blog\/wp-json\/wp\/v2\/blog\/1383552\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.esri.com\/arcgis-blog\/wp-json\/wp\/v2\/media?parent=1383552"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.esri.com\/arcgis-blog\/wp-json\/wp\/v2\/categories?post=1383552"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.esri.com\/arcgis-blog\/wp-json\/wp\/v2\/tags?post=1383552"},{"taxonomy":"industry","embeddable":true,"href":"https:\/\/www.esri.com\/arcgis-blog\/wp-json\/wp\/v2\/industry?post=1383552"},{"taxonomy":"product","embeddable":true,"href":"https:\/\/www.esri.com\/arcgis-blog\/wp-json\/wp\/v2\/product?post=1383552"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}