{"id":151671,"date":"2018-04-14T13:50:11","date_gmt":"2018-04-14T13:50:11","guid":{"rendered":"http:\/\/www.esri.com\/arcgis-blog\/?post_type=blog&p=151671"},"modified":"2018-04-17T21:10:55","modified_gmt":"2018-04-17T21:10:55","slug":"the-science-of-where-discovering-alternate-climate-zones-through-machine-learning","status":"publish","type":"blog","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/the-science-of-where-discovering-alternate-climate-zones-through-machine-learning","title":{"rendered":"The Science of Where: Discovering Alternate Climate Zones through Machine Learning"},"author":5141,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","format":"standard","meta":{"_acf_changed":false,"_searchwp_excluded":""},"categories":[23341],"tags":[43091,35661,25581],"industry":[],"product":[36561],"class_list":["post-151671","blog","type-blog","status-publish","format-standard","hentry","category-analytics","tag-climatology","tag-machine-learning","tag-spatial-statistics","product-arcgis-pro"],"acf":{"short_description":"Combine the power of GIS, spatial machine learning and rich climate data to understand current and future climate patterns.","flexible_content":[{"acf_fc_layout":"content","content":"

Machine Learning (ML) refers to a set of data-driven algorithms and techniques that automate the prediction, classification, and clustering of data. Machine Learning is helping scientists understand past climates, better predict future climates and identify the large-scale weather patterns we experience daily.\u00a0 Modeling climate is a complex task where the circulation of Earth\u2019s atmosphere and oceans is simulated under a variety of scenarios using mathematical models on supercomputers.\u00a0 These models produce vast quantities of output ripe for analysis using machine learning techniques.\u00a0 Using the output of a continental scale climate model, we recently did an analysis to find regions that have similar amounts of precipitation and similar temperatures (climate zones).<\/p>\n

Why do we care about climate zones?<\/strong><\/p>\n

Your climate zone may have more of an impact on you than you know.\u00a0 Building codes<\/a> that dictate how much insulation is required in the floor and walls of your home to meet the U.S. Department of Energy\u2019s efficiency guidelines are based on a set eight climate zones.\u00a0 Epidemiologists have shown that climate zones can influence health outcomes<\/a> and hospital admissions among the elderly.\u00a0 Of particular concern in this time of rapid climate change is that climate conditions influence your exposure to infectious diseases<\/a>.\u00a0 On a more positive note, plant hardiness zones<\/a>, a special type of climate zone, can tell you if you can grow your own avocados!<\/p>\n"},{"acf_fc_layout":"content","content":"

Why do we need to create alternate climate zones?<\/strong><\/p>\n

The Koppen climate classification was available as early as 1884 and divides the planet into five main groups.\u00a0 The Koppen classification was refined in the 1960s to produce the Trewartha climate classification.\u00a0 As their names imply, both systems are classifications<\/em> of climate based on some prior rules.\u00a0 For example, in the Koppen system, any region where the average temperature in all 12 months was 64\u00b0 F or above is classified as a tropical climate.\u00a0 Machine Learning would take a different approach.\u00a0 Rather than relying on some prior set of rules, it would allow the data to \u2018speak for itself\u2019 and divide into a natural classification.\u00a0 In machine learning terminology this is called unsupervised<\/em> learning.\u00a0 This allows you to quickly create new, exploratory sets of climate zones.\u00a0 For example, the National Center for Atmospheric Research produces a climate model that projects temperature and precipitation in the year 2050 under a variety of scenarios that range from aggressive reductions in greenhouse gas emissions to business-as-usual scenarios where greenhouse gas emissions continue to increase throughout the 21st century.\u00a0 The data for these scenarios are available in the Living Atlas<\/a>.\u00a0 Using machine learning, you could see how the projected changes in temperature impact the climate zones.<\/p>\n"},{"acf_fc_layout":"image","image":{"ID":151681,"id":151681,"title":"Koppen","filename":"Koppen.png","filesize":494404,"url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/04\/Koppen.png","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/the-science-of-where-discovering-alternate-climate-zones-through-machine-learning\/koppen","alt":"","author":"5141","description":"","caption":"Koppen Climate Classification ","name":"koppen","status":"inherit","uploaded_to":151671,"date":"2018-04-14 20:19:52","modified":"2018-04-14 20:20:20","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":1430,"height":953,"sizes":{"thumbnail":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/04\/Koppen.png","thumbnail-width":213,"thumbnail-height":142,"medium":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/04\/Koppen.png","medium-width":392,"medium-height":261,"medium_large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/04\/Koppen.png","medium_large-width":768,"medium_large-height":512,"large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/04\/Koppen.png","large-width":1430,"large-height":953,"1536x1536":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/04\/Koppen.png","1536x1536-width":1430,"1536x1536-height":953,"2048x2048":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/04\/Koppen.png","2048x2048-width":1430,"2048x2048-height":953,"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/04\/Koppen.png","card_image-width":698,"card_image-height":465,"wide_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/04\/Koppen.png","wide_image-width":1430,"wide_image-height":953}},"image_position":"left","orientation":"horizontal","hyperlink":""},{"acf_fc_layout":"content","content":"

Creating alternate climate zones with traditional Machine Learning<\/strong><\/p>\n

Recall that climate zones are regions that have similar amounts of precipitation and similar temperatures.\u00a0 This sounds like a perfect task for clustering.\u00a0 The goal is to create regions where all the locations within each region are as similar as possible, and all the regions themselves are as different as possible.\u00a0 Since climate varies throughout the year, we wouldn\u2019t want to use just the average temperature and precipitation at each location.\u00a0 We\u2019ve used the long-term monthly means for precipitation and temperature for each of the twelve months as input to this analysis \u2013 24 variables in all.\u00a0 Data for this blog are from NOAA\u2019s North American Regional Reanalysis Model (NARR).<\/p>\n

We used the Multivariate Clustering<\/a> tool available in the Spatial Statistics toolbox in ArcGIS Pro to find natural clusters of features based solely on feature attributes.\u00a0 This tool uses a very common machine learning algorithm called k-means and found three \u2018natural\u2019 clusters in the data.\u00a0 While this clustering is not completely unreasonable, it is strange to see the Pacific Northwest and the Southeast in the same cluster.\u00a0 Also, there are patches of Southwest climate in Western Idaho.\u00a0 We can do better by providing the machine learning algorithm with more information \u2013 spatial information \u2013 something that is very important in climate.<\/p>\n"},{"acf_fc_layout":"image","image":{"ID":151691,"id":151691,"title":"A","filename":"A.png","filesize":115695,"url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/04\/A.png","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/the-science-of-where-discovering-alternate-climate-zones-through-machine-learning\/a","alt":"","author":"5141","description":"","caption":"Climate zones of the contiguous U.S. derived from aspatial machine learning.","name":"a","status":"inherit","uploaded_to":151671,"date":"2018-04-14 20:21:57","modified":"2018-04-14 20:22:33","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":1270,"height":768,"sizes":{"thumbnail":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/04\/A.png","thumbnail-width":213,"thumbnail-height":129,"medium":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/04\/A.png","medium-width":432,"medium-height":261,"medium_large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/04\/A.png","medium_large-width":768,"medium_large-height":464,"large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/04\/A.png","large-width":1270,"large-height":768,"1536x1536":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/04\/A.png","1536x1536-width":1270,"1536x1536-height":768,"2048x2048":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/04\/A.png","2048x2048-width":1270,"2048x2048-height":768,"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/04\/A.png","card_image-width":769,"card_image-height":465,"wide_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/04\/A.png","wide_image-width":1270,"wide_image-height":768}},"image_position":"center","orientation":"horizontal","hyperlink":""},{"acf_fc_layout":"content","content":"

Adding a spatial component<\/strong><\/p>\n

When we think of climate zones we often think about contiguous regions.\u00a0 We can still use the power of machine learning to build climate zones but we can force the algorithm to build contiguous regions by adding spatial constraints.\u00a0 We used the Spatially Constrained Multivariate Clustering<\/a> tool in ArcGIS Pro to build an alternate set of climate zones.\u00a0 This tool is an implementation of the SKATER algorithm and works by growing and pruning a minimum spanning tree to create similar clusters.\u00a0 This time the tool found six natural clusters in the data and these seem more intuitive when compared to the non-spatial clustering.\u00a0 In fact, these six clusters separate warmer, drier Southern California from the more temperate and moist Northern California and Pacific Northwest.\u00a0 This alternate set of climate zones also separates semi-arid West Texas from the more humid eastern portion of the state.<\/p>\n"},{"acf_fc_layout":"image","image":{"ID":151701,"id":151701,"title":"B","filename":"B.png","filesize":99800,"url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/04\/B.png","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/the-science-of-where-discovering-alternate-climate-zones-through-machine-learning\/b","alt":"","author":"5141","description":"","caption":"Climate zones of the contiguous U.S. derived from spatial machine learning. The algorithm found six natural zones (clusters). ","name":"b","status":"inherit","uploaded_to":151671,"date":"2018-04-14 20:23:45","modified":"2018-04-14 20:24:03","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":1026,"height":768,"sizes":{"thumbnail":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/04\/B.png","thumbnail-width":213,"thumbnail-height":159,"medium":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/04\/B.png","medium-width":349,"medium-height":261,"medium_large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/04\/B.png","medium_large-width":768,"medium_large-height":575,"large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/04\/B.png","large-width":1026,"large-height":768,"1536x1536":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/04\/B.png","1536x1536-width":1026,"1536x1536-height":768,"2048x2048":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/04\/B.png","2048x2048-width":1026,"2048x2048-height":768,"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/04\/B.png","card_image-width":621,"card_image-height":465,"wide_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/04\/B.png","wide_image-width":1026,"wide_image-height":768}},"image_position":"center","orientation":"horizontal","hyperlink":""},{"acf_fc_layout":"content","content":"

To compare our spatial machine learning climate zones to an existing set of climate zones, we reran the spatially constrained clustering asking for nine climate regions. \u00a0This allows us to compare our climate regions to a set of nine climate regions developed by NOAA\u2019s National Center for Environmental Information. \u00a0Even though NOAA\u2019s approach was to aggregate their data up to the state level, there are remarkable similarities between the two maps below.<\/p>\n"},{"acf_fc_layout":"image","image":{"ID":151711,"id":151711,"title":"D","filename":"D.png","filesize":80235,"url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/04\/D.png","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/the-science-of-where-discovering-alternate-climate-zones-through-machine-learning\/d","alt":"","author":"5141","description":"","caption":"Nine climate regions identified by the National Centers for Environmental Information. https:\/\/www.ncdc.noaa.gov\/monitoring-references\/maps\/us-climate-regions.php ","name":"d","status":"inherit","uploaded_to":151671,"date":"2018-04-14 20:25:10","modified":"2018-04-14 20:25:33","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":1034,"height":674,"sizes":{"thumbnail":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/04\/D.png","thumbnail-width":213,"thumbnail-height":139,"medium":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/04\/D.png","medium-width":400,"medium-height":261,"medium_large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/04\/D.png","medium_large-width":768,"medium_large-height":501,"large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/04\/D.png","large-width":1034,"large-height":674,"1536x1536":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/04\/D.png","1536x1536-width":1034,"1536x1536-height":674,"2048x2048":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/04\/D.png","2048x2048-width":1034,"2048x2048-height":674,"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/04\/D.png","card_image-width":713,"card_image-height":465,"wide_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/04\/D.png","wide_image-width":1034,"wide_image-height":674}},"image_position":"center","orientation":"horizontal","hyperlink":""},{"acf_fc_layout":"image","image":{"ID":151721,"id":151721,"title":"E","filename":"E.png","filesize":111914,"url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/04\/E.png","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/the-science-of-where-discovering-alternate-climate-zones-through-machine-learning\/e","alt":"","author":"5141","description":"","caption":"Nine climate regions identified by spatial machine learning.","name":"e","status":"inherit","uploaded_to":151671,"date":"2018-04-14 20:27:04","modified":"2018-04-14 20:27:35","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":1270,"height":765,"sizes":{"thumbnail":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/04\/E.png","thumbnail-width":213,"thumbnail-height":128,"medium":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/04\/E.png","medium-width":433,"medium-height":261,"medium_large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/04\/E.png","medium_large-width":768,"medium_large-height":463,"large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/04\/E.png","large-width":1270,"large-height":765,"1536x1536":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/04\/E.png","1536x1536-width":1270,"1536x1536-height":765,"2048x2048":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/04\/E.png","2048x2048-width":1270,"2048x2048-height":765,"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/04\/E.png","card_image-width":772,"card_image-height":465,"wide_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/04\/E.png","wide_image-width":1270,"wide_image-height":765}},"image_position":"center","orientation":"horizontal","hyperlink":""},{"acf_fc_layout":"content","content":"

The intersection of GIS, machine learning and climate science<\/strong><\/p>\n

This workflow illustrates the power of bringing together, GIS, spatial machine learning and valuable data from the climate sciences.\u00a0 The huge volumes of data coming from climate models and climate change research is overwhelming.\u00a0 You can use machine learning techniques to summarize and glean patterns from these vast amounts of data and turn them into understandable, actionable information products.\u00a0 We\u2019re actively working to build the tools that help you build these information products, as well as pushing the limits of what it means to make machine learning truly spatial.<\/p>\n

What are you going to do?<\/strong><\/p>\n

Here are three ideas for how you can explore machine learning and climate science in ArcGIS.<\/p>\n

    \n
  1. Will climate zones change in the future? The National Center for Atmospheric Research produces a climate model that projects temperature and precipitation in the year 2050 under a variety of scenarios that range from aggressive reductions in greenhouse gas emissions to business-as-usual scenarios where greenhouse gas emissions continue to increase throughout the 21st century.\u00a0 The data for these scenarios are available in the Living Atlas<\/a>.<\/li>\n
  2. What would global climate zones look like? While the data used in this blog was from a regional model for North America, the NOAA\u2019s Earth System Research Laboratory provides data<\/a> for global climate models.<\/li>\n
  3. Are temperature and precipitation sufficient to construct climate zones? This blog used only two variables, temperature and precipitation, to delineate climate zones.\u00a0 The NARR model contains other climate variables such as snow cover, cloud cover and wind.<\/li>\n<\/ol>\n"},{"acf_fc_layout":"content","content":"

    NCEP Reanalysis data (NARR) provided by the NOAA\/OAR\/ESRL PSD, Boulder, Colorado, USA, from their Web site at https:\/\/www.esrl.noaa.gov\/psd\/<\/p>\n

    The blog post is provided by Kevin Butler. Kevin is a product engineer on the Spatial Statistics team.\u00a0 Comments about this blog, the data sources and workflows used are welcomed and can be submitted by leaving a reply on the blog.\u00a0 You must be logged in to post a comment.<\/p>\n"}],"authors":[{"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":82841,"post_author":"6581","post_date":"2018-02-21 10:14:24","post_date_gmt":"2018-02-21 10:14:24","post_content":"","post_title":"Predict Seagrass Habitats with Machine Learning","post_excerpt":"","post_status":"publish","comment_status":"open","ping_status":"closed","post_password":"","post_name":"predict-seagrass-habitats-with-machine-learning","to_ping":"","pinged":"","post_modified":"2018-03-26 21:17:09","post_modified_gmt":"2018-03-26 21:17:09","post_content_filtered":"","post_parent":0,"guid":"http:\/\/www.esri.com\/arcgis-blog\/products\/product\/uncategorized\/predict-seagrass-habitats-with-machine-learning\/","menu_order":0,"post_type":"blog","post_mime_type":"","comment_count":"0","filter":"raw"},{"ID":82111,"post_author":"7021","post_date":"2018-01-22 06:00:00","post_date_gmt":"2018-01-22 06:00:00","post_content":"","post_title":"New Clustering Tools in ArcGIS Pro 2.1: More Machine Learning at your Fingertips","post_excerpt":"","post_status":"publish","comment_status":"open","ping_status":"closed","post_password":"","post_name":"new-clustering-tools-in-arcgis-pro-2-1-more-machine-learning-at-your-fingertips","to_ping":"","pinged":"","post_modified":"2018-03-26 21:16:34","post_modified_gmt":"2018-03-26 21:16:34","post_content_filtered":"","post_parent":0,"guid":"http:\/\/www.esri.com\/arcgis-blog\/products\/product\/uncategorized\/new-clustering-tools-in-arcgis-pro-2-1-more-machine-learning-at-your-fingertips\/","menu_order":0,"post_type":"blog","post_mime_type":"","comment_count":"0","filter":"raw"}],"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2015\/06\/MultidimensionalCard.png","wide_image":false},"yoast_head":"\nThe Science of Where: Discovering Alternate Climate Zones through Machine Learning<\/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\/the-science-of-where-discovering-alternate-climate-zones-through-machine-learning\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"The Science of Where: Discovering Alternate Climate Zones through Machine Learning\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/the-science-of-where-discovering-alternate-climate-zones-through-machine-learning\" \/>\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=\"2018-04-17T21:10:55+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\/the-science-of-where-discovering-alternate-climate-zones-through-machine-learning#article\",\"isPartOf\":{\"@id\":\"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/the-science-of-where-discovering-alternate-climate-zones-through-machine-learning\"},\"author\":{\"name\":\"Kevin Butler\",\"@id\":\"https:\/\/www.esri.com\/arcgis-blog\/#\/schema\/person\/8691ab3666684108f926d34bbb97f082\"},\"headline\":\"The Science of Where: Discovering Alternate Climate Zones through Machine Learning\",\"datePublished\":\"2018-04-14T13:50:11+00:00\",\"dateModified\":\"2018-04-17T21:10:55+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/the-science-of-where-discovering-alternate-climate-zones-through-machine-learning\"},\"wordCount\":11,\"publisher\":{\"@id\":\"https:\/\/www.esri.com\/arcgis-blog\/#organization\"},\"keywords\":[\"climatology\",\"machine learning\",\"spatial statistics\"],\"articleSection\":[\"Analytics\"],\"inLanguage\":\"en-US\"},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/the-science-of-where-discovering-alternate-climate-zones-through-machine-learning\",\"url\":\"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/the-science-of-where-discovering-alternate-climate-zones-through-machine-learning\",\"name\":\"The Science of Where: Discovering Alternate Climate Zones through Machine Learning\",\"isPartOf\":{\"@id\":\"https:\/\/www.esri.com\/arcgis-blog\/#website\"},\"datePublished\":\"2018-04-14T13:50:11+00:00\",\"dateModified\":\"2018-04-17T21:10:55+00:00\",\"breadcrumb\":{\"@id\":\"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/the-science-of-where-discovering-alternate-climate-zones-through-machine-learning#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/the-science-of-where-discovering-alternate-climate-zones-through-machine-learning\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/the-science-of-where-discovering-alternate-climate-zones-through-machine-learning#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/www.esri.com\/arcgis-blog\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"The Science of Where: Discovering Alternate Climate Zones through Machine Learning\"}]},{\"@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\/8691ab3666684108f926d34bbb97f082\",\"name\":\"Kevin Butler\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/www.esri.com\/arcgis-blog\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/871537530afdee476917a9da0f9e9ac26665a4226ea71bee234efba5d2441ab2?s=96&d=blank&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/871537530afdee476917a9da0f9e9ac26665a4226ea71bee234efba5d2441ab2?s=96&d=blank&r=g\",\"caption\":\"Kevin Butler\"},\"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.\",\"url\":\"https:\/\/www.esri.com\/arcgis-blog\/author\/kevi6890\"}]}<\/script>\n<!-- \/ Yoast SEO Premium plugin. -->","yoast_head_json":{"title":"The Science of Where: Discovering Alternate Climate Zones through Machine Learning","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\/the-science-of-where-discovering-alternate-climate-zones-through-machine-learning","og_locale":"en_US","og_type":"article","og_title":"The Science of Where: Discovering Alternate Climate Zones through Machine Learning","og_url":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/the-science-of-where-discovering-alternate-climate-zones-through-machine-learning","og_site_name":"ArcGIS Blog","article_publisher":"https:\/\/www.facebook.com\/esrigis\/","article_modified_time":"2018-04-17T21:10:55+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\/the-science-of-where-discovering-alternate-climate-zones-through-machine-learning#article","isPartOf":{"@id":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/the-science-of-where-discovering-alternate-climate-zones-through-machine-learning"},"author":{"name":"Kevin Butler","@id":"https:\/\/www.esri.com\/arcgis-blog\/#\/schema\/person\/8691ab3666684108f926d34bbb97f082"},"headline":"The Science of Where: Discovering Alternate Climate Zones through Machine Learning","datePublished":"2018-04-14T13:50:11+00:00","dateModified":"2018-04-17T21:10:55+00:00","mainEntityOfPage":{"@id":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/the-science-of-where-discovering-alternate-climate-zones-through-machine-learning"},"wordCount":11,"publisher":{"@id":"https:\/\/www.esri.com\/arcgis-blog\/#organization"},"keywords":["climatology","machine learning","spatial statistics"],"articleSection":["Analytics"],"inLanguage":"en-US"},{"@type":"WebPage","@id":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/the-science-of-where-discovering-alternate-climate-zones-through-machine-learning","url":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/the-science-of-where-discovering-alternate-climate-zones-through-machine-learning","name":"The Science of Where: Discovering Alternate Climate Zones through Machine Learning","isPartOf":{"@id":"https:\/\/www.esri.com\/arcgis-blog\/#website"},"datePublished":"2018-04-14T13:50:11+00:00","dateModified":"2018-04-17T21:10:55+00:00","breadcrumb":{"@id":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/the-science-of-where-discovering-alternate-climate-zones-through-machine-learning#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/the-science-of-where-discovering-alternate-climate-zones-through-machine-learning"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/analytics\/the-science-of-where-discovering-alternate-climate-zones-through-machine-learning#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.esri.com\/arcgis-blog\/"},{"@type":"ListItem","position":2,"name":"The Science of Where: Discovering Alternate Climate Zones through Machine Learning"}]},{"@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\/8691ab3666684108f926d34bbb97f082","name":"Kevin Butler","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.esri.com\/arcgis-blog\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/871537530afdee476917a9da0f9e9ac26665a4226ea71bee234efba5d2441ab2?s=96&d=blank&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/871537530afdee476917a9da0f9e9ac26665a4226ea71bee234efba5d2441ab2?s=96&d=blank&r=g","caption":"Kevin Butler"},"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.","url":"https:\/\/www.esri.com\/arcgis-blog\/author\/kevi6890"}]}},"text_date":"April 14, 2018","author_name":"Kevin Butler","author_page":"https:\/\/www.esri.com\/arcgis-blog\/author\/kevi6890","custom_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2025\/08\/Newsroom-Keyart-Wide-1920-x-1080.jpg","primary_product":"ArcGIS Pro","tag_data":[{"term_id":43091,"name":"climatology","slug":"climatology","term_group":0,"term_taxonomy_id":43091,"taxonomy":"post_tag","description":"","parent":0,"count":1,"filter":"raw"},{"term_id":35661,"name":"machine learning","slug":"machine-learning","term_group":0,"term_taxonomy_id":35661,"taxonomy":"post_tag","description":"","parent":0,"count":41,"filter":"raw"},{"term_id":25581,"name":"spatial statistics","slug":"spatial-statistics","term_group":0,"term_taxonomy_id":25581,"taxonomy":"post_tag","description":"","parent":0,"count":128,"filter":"raw"}],"category_data":[{"term_id":23341,"name":"Analytics","slug":"analytics","term_group":0,"term_taxonomy_id":23341,"taxonomy":"category","description":"","parent":0,"count":1325,"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":2035,"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\/151671","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\/5141"}],"replies":[{"embeddable":true,"href":"https:\/\/www.esri.com\/arcgis-blog\/wp-json\/wp\/v2\/comments?post=151671"}],"version-history":[{"count":0,"href":"https:\/\/www.esri.com\/arcgis-blog\/wp-json\/wp\/v2\/blog\/151671\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.esri.com\/arcgis-blog\/wp-json\/wp\/v2\/media?parent=151671"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.esri.com\/arcgis-blog\/wp-json\/wp\/v2\/categories?post=151671"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.esri.com\/arcgis-blog\/wp-json\/wp\/v2\/tags?post=151671"},{"taxonomy":"industry","embeddable":true,"href":"https:\/\/www.esri.com\/arcgis-blog\/wp-json\/wp\/v2\/industry?post=151671"},{"taxonomy":"product","embeddable":true,"href":"https:\/\/www.esri.com\/arcgis-blog\/wp-json\/wp\/v2\/product?post=151671"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}