{"id":346062,"date":"2019-01-02T08:03:27","date_gmt":"2019-01-02T16:03:27","guid":{"rendered":"http:\/\/www.esri.com\/arcgis-blog\/?post_type=blog&p=346062"},"modified":"2021-01-05T14:21:52","modified_gmt":"2021-01-05T22:21:52","slug":"spectral-profiles-classification","status":"publish","type":"blog","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/imagery\/spectral-profiles-classification","title":{"rendered":"Spectral Profiles: Improve Classification Before You Click Run"},"author":8222,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","format":"standard","meta":{"_acf_changed":false,"_searchwp_excluded":""},"categories":[22931],"tags":[28271,115262,25061,291812,291822],"industry":[],"product":[36561],"class_list":["post-346062","blog","type-blog","status-publish","format-standard","hentry","category-imagery","tag-image-classification","tag-imagery","tag-multispectral","tag-spectral-profile","tag-training-samples","product-arcgis-pro"],"acf":{"short_description":"Use ArcGIS Pro charting tools to evaluate the spectral profiles of your training sites to improve classification before you run the model. ","flexible_content":[{"acf_fc_layout":"content","content":"

One of the most important components in a supervised image classification is excellent training sites. Training an accurate classification model requires that your training samples represent distinct spectral responses recorded from the remote sensing platform<\/a> – a training sample for vegetation should not include pixels with snow or pavement, samples for water classification should not include pixels with bare earth. Using the spectral profiles chart, you can evaluate your training samples before you train your model.<\/p>\n

If you use the Training Samples Manager<\/strong><\/a>, it’s one simple step to create the chart. If you created your training samples separately, where each polygon or point is a different record in the feature class, it just takes a quick geoprocessing tool before creating the chart if you want to look at the average spectral profiles for each class all on one graph.<\/p>\n

The purpose of this blog is not to go through the entire image classification workflow from end-to-end, but simply to show you how to use spectral profiles to guide you in creating training samples.<\/p>\n"},{"acf_fc_layout":"image","image":{"ID":392442,"id":392442,"title":"profile","filename":"profile.png","filesize":51561,"url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/profile.png","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/imagery\/spectral-profiles-classification\/profile-6","alt":"Spectral profile example","author":"8222","description":"","caption":"This profile tells you that Water training sites are significantly distinct, but that Golf Course and Healthy Vegetation may be too similar to yield an accurate result","name":"profile-6","status":"inherit","uploaded_to":346062,"date":"2018-12-27 18:52:57","modified":"2018-12-27 18:54:16","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":559,"height":256,"sizes":{"thumbnail":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/profile-150x150.png","thumbnail-width":150,"thumbnail-height":150,"medium":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/profile-300x137.png","medium-width":300,"medium-height":137,"medium_large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/profile.png","medium_large-width":559,"medium_large-height":256,"large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/profile.png","large-width":559,"large-height":256,"1536x1536":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/profile.png","1536x1536-width":559,"1536x1536-height":256,"2048x2048":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/profile.png","2048x2048-width":559,"2048x2048-height":256,"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/profile.png","card_image-width":559,"card_image-height":256,"wide_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/profile.png","wide_image-width":559,"wide_image-height":256}},"image_position":"center","orientation":"horizontal","hyperlink":""},{"acf_fc_layout":"content","content":"

Of course, remotely sensed imagery with large-ish pixel sizes (e.g. Landsat with 30m resolution) is bound to have multiple land cover categories within a single pixel. Still, it’s important to create good training samples in regions where pixels are easily identifiable as a given land cover type, and these samples become even more important when working with lower resolution data or when trying to identify more land cover categories.<\/p>\n

In this example, I\u00a0used image classification to get an understanding of the amount of land used for agriculture in the Imperial Valley in Southern California, a region situated in the Colorado Desert with high temperatures and very little rainfall.<\/p>\n"},{"acf_fc_layout":"image","image":{"ID":392852,"id":392852,"title":"Site","filename":"Site.png","filesize":416324,"url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/Site.png","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/imagery\/spectral-profiles-classification\/site","alt":"Imperial Valley study area","author":"8222","description":"","caption":"Imperial Valley is in Imperial County, California","name":"site","status":"inherit","uploaded_to":346062,"date":"2018-12-27 23:56:52","modified":"2019-03-26 18:47:00","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":1237,"height":702,"sizes":{"thumbnail":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/Site-150x150.png","thumbnail-width":150,"thumbnail-height":150,"medium":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/Site-300x170.png","medium-width":300,"medium-height":170,"medium_large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/Site-768x436.png","medium_large-width":768,"medium_large-height":436,"large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/Site-1024x581.png","large-width":1024,"large-height":581,"1536x1536":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/Site.png","1536x1536-width":1237,"1536x1536-height":702,"2048x2048":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/Site.png","2048x2048-width":1237,"2048x2048-height":702,"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/Site-819x465.png","card_image-width":819,"card_image-height":465,"wide_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/Site.png","wide_image-width":1237,"wide_image-height":702}},"image_position":"center","orientation":"horizontal","hyperlink":""},{"acf_fc_layout":"content","content":"

Scenario 1: With the Training Samples Manager<\/h2>\n

Using the Training Samples Manager<\/strong> in ArcGIS Pro to generate training samples allows you to create a feature class that’s already organized by class name and class ID according to a schema.<\/p>\n

In this analysis,\u00a0I’m using a schema made up of five land cover types: Barren, Planted\/Cultivated, Shrubland, Developed<\/em>, and Water<\/em>. Using the drawing tools, I’ve created several training samples for each category. Each time I draw a new training sample, a new record is added to the list in the Training Samples Manager<\/strong>. If I tried to use the Spectral Profile Chart<\/strong> with that many training samples, I’d have to select every record for each land cover class. Instead, I’ll use the Collapse<\/strong> tool to combine all the training samples for a given class into a single record. Then I’ll click the Save<\/strong> button to save my training samples as a feature class.<\/p>\n"},{"acf_fc_layout":"image","image":{"ID":392412,"id":392412,"title":"TrainingSamplesAll","filename":"TrainingSamplesAll.png","filesize":144617,"url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/TrainingSamplesAll.png","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/imagery\/spectral-profiles-classification\/trainingsamplesall","alt":"Collapse training samples for each category","author":"8222","description":"","caption":"","name":"trainingsamplesall","status":"inherit","uploaded_to":346062,"date":"2018-12-27 18:28:40","modified":"2018-12-27 18:30:33","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":1615,"height":900,"sizes":{"thumbnail":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/TrainingSamplesAll-150x150.png","thumbnail-width":150,"thumbnail-height":150,"medium":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/TrainingSamplesAll-300x167.png","medium-width":300,"medium-height":167,"medium_large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/TrainingSamplesAll-768x428.png","medium_large-width":768,"medium_large-height":428,"large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/TrainingSamplesAll-1024x571.png","large-width":1024,"large-height":571,"1536x1536":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/TrainingSamplesAll.png","1536x1536-width":1536,"1536x1536-height":856,"2048x2048":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/TrainingSamplesAll.png","2048x2048-width":1615,"2048x2048-height":900,"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/TrainingSamplesAll-826x460.png","card_image-width":826,"card_image-height":460,"wide_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/TrainingSamplesAll.png","wide_image-width":1615,"wide_image-height":900}},"image_position":"center","orientation":"horizontal","hyperlink":""},{"acf_fc_layout":"content","content":"

Scenario 2: Without the Training Samples Manager<\/h2>\n

If you have a feature class with training samples that you created outside of the Training Samples Manager<\/strong>, where each training site is a separate record in the feature class, you need to run the Dissolve<\/strong>\u00a0geoprocessing tool before creating a chart if you want to see the average spectral profiles for all your training samples at once. Use the class name or class value as the Dissolve field<\/strong>\u00a0to combine all records associated with a given land cover class into a single multi-part polygon.<\/p>\n

To view the spectral profile for one training sample at a time interactively (e.g. to view each individual training site for Developed<\/em>), skip this step entirely and start working with your chart.<\/p>\n"},{"acf_fc_layout":"image","image":{"ID":392462,"id":392462,"title":"Dissolve","filename":"Dissolve.png","filesize":1342514,"url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/Dissolve.png","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/imagery\/spectral-profiles-classification\/dissolve","alt":"Use Dissolve to \"collapse\" your records in your feature class","author":"8222","description":"","caption":"","name":"dissolve","status":"inherit","uploaded_to":346062,"date":"2018-12-27 19:18:50","modified":"2018-12-27 19:19:06","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":1342,"height":805,"sizes":{"thumbnail":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/Dissolve-150x150.png","thumbnail-width":150,"thumbnail-height":150,"medium":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/Dissolve-300x180.png","medium-width":300,"medium-height":180,"medium_large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/Dissolve-768x461.png","medium_large-width":768,"medium_large-height":461,"large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/Dissolve-1024x614.png","large-width":1024,"large-height":614,"1536x1536":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/Dissolve.png","1536x1536-width":1342,"1536x1536-height":805,"2048x2048":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/Dissolve.png","2048x2048-width":1342,"2048x2048-height":805,"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/Dissolve-775x465.png","card_image-width":775,"card_image-height":465,"wide_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/Dissolve.png","wide_image-width":1342,"wide_image-height":805}},"image_position":"center","orientation":"horizontal","hyperlink":""},{"acf_fc_layout":"content","content":"

Charting the Spectral Profiles<\/h2>\n

At this point, using your imagery and the training samples feature class, you can create your spectral profiles chart:<\/p>\n

    \n
  1. Right-click on the image to be classified in the Contents<\/strong> pane<\/li>\n
  2. Select Create Chart<\/strong> > Spectral Profile<\/strong><\/li>\n
  3. In the Chart Properties<\/strong> pane, choose Mean Line<\/strong> as the Plot Type<\/strong>.<\/li>\n
  4. Use the Feature Selector<\/strong> tool to select one of the polygons. Remember that because we used Collapse<\/strong>, selecting one polygon means you are selecting all the training sites for the land cover category represented by that polygon.<\/li>\n
  5. Symbolize the profile lines to match the color of the land cover type and change the label name so you can easily assess the chart.
    \n**\u00a0 Pro Tip: To change the label of the profile, type the name in the Label field on the Chart Properties pane and hit TAB\u00a0 **<\/em><\/em><\/li>\n
  6. Try out different chart types to see the types of information you can glean from them – do you see outliers? Consistent trends? Similar profiles? Distinct categories?<\/li>\n<\/ol>\n

    Below is the spectral profile chart I created using the imagery and training samples for the Imperial Valley study. I used the “Medium” (grey) theme in the chart to make it easier to view the profiles.<\/p>\n"},{"acf_fc_layout":"image","image":{"ID":392762,"id":392762,"title":"NewSpectProf","filename":"NewSpectProf-1.png","filesize":47658,"url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/NewSpectProf-1.png","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/imagery\/spectral-profiles-classification\/newspectprof-2","alt":"Spectral profiles of training samples","author":"8222","description":"","caption":"","name":"newspectprof-2","status":"inherit","uploaded_to":346062,"date":"2018-12-27 23:11:03","modified":"2018-12-27 23:11:17","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":1081,"height":394,"sizes":{"thumbnail":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/NewSpectProf-1-150x150.png","thumbnail-width":150,"thumbnail-height":150,"medium":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/NewSpectProf-1-300x109.png","medium-width":300,"medium-height":109,"medium_large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/NewSpectProf-1-768x280.png","medium_large-width":768,"medium_large-height":280,"large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/NewSpectProf-1-1024x373.png","large-width":1024,"large-height":373,"1536x1536":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/NewSpectProf-1.png","1536x1536-width":1081,"1536x1536-height":394,"2048x2048":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/NewSpectProf-1.png","2048x2048-width":1081,"2048x2048-height":394,"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/NewSpectProf-1-826x301.png","card_image-width":826,"card_image-height":301,"wide_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/NewSpectProf-1.png","wide_image-width":1081,"wide_image-height":394}},"image_position":"center","orientation":"horizontal","hyperlink":""},{"acf_fc_layout":"content","content":"

    Assessment of Spectral Profiles<\/h2>\n

    At first glance, I can tell that the Planted\/Cultivated<\/em>, Water<\/em>, and Barren<\/em> land cover classes have profiles that are distinct enough that I can expect good initial results for classification of these classes. However, the Developed<\/em> and Shrubland<\/em> profiles are a little too close for comfort: they have the same general shape and the average reflectance values are similar at each wavelength. From this, I can choose whether I want to re-create my training samples or simply combine the two categories into a single class. Theoretically, combining the Shrubland<\/em> and Developed<\/em> into one class shouldn’t impact my analysis because my main focus is an accurate estimate of Planted\/Cultivated<\/em> land cover.<\/p>\n

    Before making my decision, I’ll take a deeper look at the data. The chart below is the same data in a Boxes plot, and I can hover my mouse over the boxes to get the statistics for each land cover class at each wavelength band.<\/p>\n"},{"acf_fc_layout":"image","image":{"ID":393472,"id":393472,"title":"HoverTool","filename":"HoverTool.png","filesize":275892,"url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/HoverTool.png","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/imagery\/spectral-profiles-classification\/hovertool","alt":"Boxes plot with spectral response distribution","author":"8222","description":"","caption":"","name":"hovertool","status":"inherit","uploaded_to":346062,"date":"2018-12-28 16:43:36","modified":"2018-12-28 16:43:54","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":1687,"height":859,"sizes":{"thumbnail":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/HoverTool-150x150.png","thumbnail-width":150,"thumbnail-height":150,"medium":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/HoverTool-300x153.png","medium-width":300,"medium-height":153,"medium_large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/HoverTool-768x391.png","medium_large-width":768,"medium_large-height":391,"large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/HoverTool-1024x521.png","large-width":1024,"large-height":521,"1536x1536":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/HoverTool.png","1536x1536-width":1536,"1536x1536-height":782,"2048x2048":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/HoverTool.png","2048x2048-width":1687,"2048x2048-height":859,"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/HoverTool-826x421.png","card_image-width":826,"card_image-height":421,"wide_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/HoverTool.png","wide_image-width":1687,"wide_image-height":859}},"image_position":"center","orientation":"horizontal","hyperlink":""},{"acf_fc_layout":"content","content":"

    From the Boxes chart, I can see that the Developed<\/em> and Shrubland<\/em> land cover classes have similar average values and similar distribution. However, the Developed<\/em> land cover type has much higher maximum reflectance values across all wavelengths, and Shrubland<\/em>\u00a0has lower minimum values. This makes sense – I would expect developed areas (buildings, roads, parking lots, etc.) to be brighter in general than shrubby areas.<\/p>\n

    Since the Boxes chart tells me that the minimum and maximum values vary so much between the classes, combining these two classes into a single class could potentially confuse my classification model and impact the overall accuracy. Instead, I’m going to re-create the training samples for the Developed<\/em> class to capture those higher reflectance values.<\/p>\n

    The charts below include the spectral profiles for my modified training samples.<\/p>\n"},{"acf_fc_layout":"image","image":{"ID":392742,"id":392742,"title":"NewAllProfs","filename":"NewAllProfs.png","filesize":192178,"url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/NewAllProfs.png","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/imagery\/spectral-profiles-classification\/newallprofs","alt":"Spectral profiles of modified samples","author":"8222","description":"","caption":"","name":"newallprofs","status":"inherit","uploaded_to":346062,"date":"2018-12-27 23:01:08","modified":"2018-12-27 23:01:19","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":1024,"height":725,"sizes":{"thumbnail":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/NewAllProfs-150x150.png","thumbnail-width":150,"thumbnail-height":150,"medium":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/NewAllProfs-300x212.png","medium-width":300,"medium-height":212,"medium_large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/NewAllProfs-768x544.png","medium_large-width":768,"medium_large-height":544,"large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/NewAllProfs-1024x725.png","large-width":1024,"large-height":725,"1536x1536":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/NewAllProfs.png","1536x1536-width":1024,"1536x1536-height":725,"2048x2048":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/NewAllProfs.png","2048x2048-width":1024,"2048x2048-height":725,"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/NewAllProfs-657x465.png","card_image-width":657,"card_image-height":465,"wide_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/NewAllProfs.png","wide_image-width":1024,"wide_image-height":725}},"image_position":"center","orientation":"horizontal","hyperlink":""},{"acf_fc_layout":"content","content":"

    Now, in the visible and near infrared bands especially, you can see distinctly higher reflectance values for the Developed land cover training sample data compared to the Shrubland spectral response. With these results, I would be comfortable moving forward with my classification workflow by training my model with all my training samples.<\/p>\n

    Extra Credit<\/h2>\n

    For bonus points, I used the Multispectral Landsat image service<\/a> from the Living Atlas to quickly visualize NDVI in the Imperial Valley area. Then I used a spectral profile chart to compare NDVI averages in different areas of interest for vegetation health assessment. Use the steps below to try it yourself:<\/p>\n

      \n
    1. In ArcGIS Pro,\u00a0 open the Map<\/strong> tab and select Add Data<\/strong>.<\/li>\n
    2. From the menu on the left, expand the Portal<\/strong> option and select Living Atlas<\/strong>. Use the Search<\/strong> box to search for “Multispectral Landsat.”<\/li>\n
    3. Select the Multispectral Landsat image service and click OK<\/strong>.<\/li>\n
    4. Zoom to Imperial Valley or your area of interest.<\/li>\n
    5. Make sure the Multispectral Landsat service is highlighted in the Contents<\/strong> pane. In the Image Service<\/strong> contextual tab set, select the Data<\/strong> tab.<\/li>\n
    6. In the Processing<\/strong> group, click the Processing Templates<\/strong> drop-down.<\/li>\n
    7. Scroll down to NDVI Colorized<\/em>. Select this template to display the colormap for NDVI.<\/li>\n
    8. Right-click on the Multispectral Landsat image service in Contents<\/strong> and select Create Chart<\/strong> > Spectral Profile<\/strong>.<\/li>\n
    9. Use the drawing tools to select multiple small areas of interest to compare NDVI distribution throughout the region.<\/li>\n<\/ol>\n

       <\/p>\n"},{"acf_fc_layout":"image","image":{"ID":393892,"id":393892,"title":"NDVIChartVertical","filename":"NDVIChartVertical.png","filesize":589729,"url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/NDVIChartVertical.png","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/imagery\/spectral-profiles-classification\/ndvichartvertical","alt":"NDVI distribution charted for three sites in Imperial Valley","author":"8222","description":"","caption":"","name":"ndvichartvertical","status":"inherit","uploaded_to":346062,"date":"2018-12-28 19:27:33","modified":"2018-12-28 19:27:58","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":1160,"height":1079,"sizes":{"thumbnail":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/NDVIChartVertical-150x150.png","thumbnail-width":150,"thumbnail-height":150,"medium":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/NDVIChartVertical-300x279.png","medium-width":281,"medium-height":261,"medium_large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/NDVIChartVertical-768x714.png","medium_large-width":768,"medium_large-height":714,"large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/NDVIChartVertical-1024x952.png","large-width":1024,"large-height":952,"1536x1536":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/NDVIChartVertical.png","1536x1536-width":1160,"1536x1536-height":1079,"2048x2048":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/NDVIChartVertical.png","2048x2048-width":1160,"2048x2048-height":1079,"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/NDVIChartVertical-500x465.png","card_image-width":500,"card_image-height":465,"wide_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/NDVIChartVertical.png","wide_image-width":1160,"wide_image-height":1079}},"image_position":"center","orientation":"horizontal","hyperlink":""},{"acf_fc_layout":"content","content":"

      Want to know more?<\/h2>\n

      Try the Image Classification Wizard tutorial<\/a><\/p>\n

      Learn more about the Training Samples Manager<\/a><\/p>\n

      Learn more about image classification<\/a><\/p>\n

      Learn more about charting tools<\/a><\/p>\n"}],"authors":[{"ID":8222,"user_firstname":"Julia","user_lastname":"Lenhardt","nickname":"Julia L","user_nicename":"jlenhardt","display_name":"Julia Lenhardt","user_email":"JLenhardt@esri.com","user_url":"","user_registered":"2018-08-03 17:12:51","user_description":"Julia is a product engineer on the Raster team. She has been with Esri since 2014 and has a background in remote sensing and GIS for environmental research. In addition to image analysis, she has a passion for music, running, good food and animal welfare.","user_avatar":""}],"related_articles":[{"ID":73211,"post_author":"6731","post_date":"2016-08-11 14:33:48","post_date_gmt":"2016-08-11 14:33:48","post_content":"","post_title":"Hands-on experience with the Image Classification Wizard (ArcGIS Pro 1.3)","post_excerpt":"","post_status":"publish","comment_status":"closed","ping_status":"closed","post_password":"","post_name":"hands-on-experience-with-the-image-classification-wizard-arcgis-pro-1-3","to_ping":"","pinged":"","post_modified":"2019-02-13 11:53:38","post_modified_gmt":"2019-02-13 19:53:38","post_content_filtered":"","post_parent":0,"guid":"http:\/\/www.esri.com\/arcgis-blog\/products\/product\/uncategorized\/hands-on-experience-with-the-image-classification-wizard-arcgis-pro-1-3\/","menu_order":0,"post_type":"blog","post_mime_type":"","comment_count":"0","filter":"raw"},{"ID":76721,"post_author":"5991","post_date":"2017-04-27 14:29:43","post_date_gmt":"2017-04-27 14:29:43","post_content":"","post_title":"Impervious Surface Mapping Using ArcGIS Pro \u2013 Part 2: Classification","post_excerpt":"","post_status":"publish","comment_status":"closed","ping_status":"closed","post_password":"","post_name":"impervious-surface-mapping-using-pro-1-4-part-2-classification","to_ping":"","pinged":"","post_modified":"2022-08-25 13:02:27","post_modified_gmt":"2022-08-25 20:02:27","post_content_filtered":"","post_parent":0,"guid":"http:\/\/www.esri.com\/arcgis-blog\/products\/product\/uncategorized\/impervious-surface-mapping-using-pro-1-4-part-2-classification\/","menu_order":0,"post_type":"blog","post_mime_type":"","comment_count":"0","filter":"raw"},{"ID":174131,"post_author":"5041","post_date":"2011-01-10 18:33:51","post_date_gmt":"2011-01-10 18:33:51","post_content":"","post_title":"Raster Image Processing Tips and Tricks \u2014 Part 4: Image Classification","post_excerpt":"","post_status":"publish","comment_status":"closed","ping_status":"closed","post_password":"","post_name":"raster-image-processing-tips-and-tricks-part-4-image-classification","to_ping":"","pinged":"","post_modified":"2018-12-18 11:05:49","post_modified_gmt":"2018-12-18 19:05:49","post_content_filtered":"","post_parent":0,"guid":"http:\/\/www.esri.com\/arcgis-blog\/?post_type=blog&p=174131","menu_order":0,"post_type":"blog","post_mime_type":"","comment_count":"0","filter":"raw"}],"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/ImperialValleyBanner.png","wide_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/ImperialValleyBan3.jpg"},"yoast_head":"\nSpectral Profiles: Improve Classification Before You Click Run<\/title>\n<meta name=\"description\" content=\"Evaluate spectral profiles of training samples using charting tools in ArcGIS Pro before image classification. A case study in Imperial Valley.\" \/>\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\/imagery\/spectral-profiles-classification\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Spectral Profiles: Improve Classification Before You Click Run\" \/>\n<meta property=\"og:description\" content=\"Evaluate spectral profiles of training samples using charting tools in ArcGIS Pro before image classification. A case study in Imperial Valley.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/imagery\/spectral-profiles-classification\" \/>\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=\"2021-01-05T22:21:52+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\/imagery\/spectral-profiles-classification#article\",\"isPartOf\":{\"@id\":\"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/imagery\/spectral-profiles-classification\"},\"author\":{\"name\":\"Julia Lenhardt\",\"@id\":\"https:\/\/www.esri.com\/arcgis-blog\/#\/schema\/person\/dd72385e82420c28c64ee1e347f8e26b\"},\"headline\":\"Spectral Profiles: Improve Classification Before You Click Run\",\"datePublished\":\"2019-01-02T16:03:27+00:00\",\"dateModified\":\"2021-01-05T22:21:52+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/imagery\/spectral-profiles-classification\"},\"wordCount\":8,\"publisher\":{\"@id\":\"https:\/\/www.esri.com\/arcgis-blog\/#organization\"},\"keywords\":[\"Image Classification\",\"Imagery\",\"Multispectral\",\"spectral profile\",\"training samples\"],\"articleSection\":[\"Imagery & Remote Sensing\"],\"inLanguage\":\"en-US\"},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/imagery\/spectral-profiles-classification\",\"url\":\"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/imagery\/spectral-profiles-classification\",\"name\":\"Spectral Profiles: Improve Classification Before You Click Run\",\"isPartOf\":{\"@id\":\"https:\/\/www.esri.com\/arcgis-blog\/#website\"},\"datePublished\":\"2019-01-02T16:03:27+00:00\",\"dateModified\":\"2021-01-05T22:21:52+00:00\",\"description\":\"Evaluate spectral profiles of training samples using charting tools in ArcGIS Pro before image classification. A case study in Imperial Valley.\",\"breadcrumb\":{\"@id\":\"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/imagery\/spectral-profiles-classification#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/imagery\/spectral-profiles-classification\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/imagery\/spectral-profiles-classification#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/www.esri.com\/arcgis-blog\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Spectral Profiles: Improve Classification Before You Click Run\"}]},{\"@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\/dd72385e82420c28c64ee1e347f8e26b\",\"name\":\"Julia Lenhardt\",\"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\/2018\/10\/Me.jpg\",\"contentUrl\":\"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/10\/Me.jpg\",\"caption\":\"Julia Lenhardt\"},\"description\":\"Julia is a product engineer on the Raster team. She has been with Esri since 2014 and has a background in remote sensing and GIS for environmental research. In addition to image analysis, she has a passion for music, running, good food and animal welfare.\",\"url\":\"https:\/\/www.esri.com\/arcgis-blog\/author\/jlenhardt\"}]}<\/script>\n<!-- \/ Yoast SEO Premium plugin. -->","yoast_head_json":{"title":"Spectral Profiles: Improve Classification Before You Click Run","description":"Evaluate spectral profiles of training samples using charting tools in ArcGIS Pro before image classification. A case study in Imperial Valley.","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\/imagery\/spectral-profiles-classification","og_locale":"en_US","og_type":"article","og_title":"Spectral Profiles: Improve Classification Before You Click Run","og_description":"Evaluate spectral profiles of training samples using charting tools in ArcGIS Pro before image classification. A case study in Imperial Valley.","og_url":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/imagery\/spectral-profiles-classification","og_site_name":"ArcGIS Blog","article_publisher":"https:\/\/www.facebook.com\/esrigis\/","article_modified_time":"2021-01-05T22:21:52+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\/imagery\/spectral-profiles-classification#article","isPartOf":{"@id":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/imagery\/spectral-profiles-classification"},"author":{"name":"Julia Lenhardt","@id":"https:\/\/www.esri.com\/arcgis-blog\/#\/schema\/person\/dd72385e82420c28c64ee1e347f8e26b"},"headline":"Spectral Profiles: Improve Classification Before You Click Run","datePublished":"2019-01-02T16:03:27+00:00","dateModified":"2021-01-05T22:21:52+00:00","mainEntityOfPage":{"@id":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/imagery\/spectral-profiles-classification"},"wordCount":8,"publisher":{"@id":"https:\/\/www.esri.com\/arcgis-blog\/#organization"},"keywords":["Image Classification","Imagery","Multispectral","spectral profile","training samples"],"articleSection":["Imagery & Remote Sensing"],"inLanguage":"en-US"},{"@type":"WebPage","@id":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/imagery\/spectral-profiles-classification","url":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/imagery\/spectral-profiles-classification","name":"Spectral Profiles: Improve Classification Before You Click Run","isPartOf":{"@id":"https:\/\/www.esri.com\/arcgis-blog\/#website"},"datePublished":"2019-01-02T16:03:27+00:00","dateModified":"2021-01-05T22:21:52+00:00","description":"Evaluate spectral profiles of training samples using charting tools in ArcGIS Pro before image classification. A case study in Imperial Valley.","breadcrumb":{"@id":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/imagery\/spectral-profiles-classification#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/imagery\/spectral-profiles-classification"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/imagery\/spectral-profiles-classification#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.esri.com\/arcgis-blog\/"},{"@type":"ListItem","position":2,"name":"Spectral Profiles: Improve Classification Before You Click Run"}]},{"@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\/dd72385e82420c28c64ee1e347f8e26b","name":"Julia Lenhardt","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\/2018\/10\/Me.jpg","contentUrl":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/10\/Me.jpg","caption":"Julia Lenhardt"},"description":"Julia is a product engineer on the Raster team. She has been with Esri since 2014 and has a background in remote sensing and GIS for environmental research. In addition to image analysis, she has a passion for music, running, good food and animal welfare.","url":"https:\/\/www.esri.com\/arcgis-blog\/author\/jlenhardt"}]}},"text_date":"January 2, 2019","author_name":"Julia Lenhardt","author_page":"https:\/\/www.esri.com\/arcgis-blog\/author\/jlenhardt","custom_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2018\/12\/ImperialValleyBan3.jpg","primary_product":"ArcGIS Pro","tag_data":[{"term_id":28271,"name":"Image Classification","slug":"image-classification","term_group":0,"term_taxonomy_id":28271,"taxonomy":"post_tag","description":"","parent":0,"count":13,"filter":"raw"},{"term_id":115262,"name":"Imagery","slug":"imagery","term_group":0,"term_taxonomy_id":115262,"taxonomy":"post_tag","description":"","parent":0,"count":152,"filter":"raw"},{"term_id":25061,"name":"Multispectral","slug":"multispectral","term_group":0,"term_taxonomy_id":25061,"taxonomy":"post_tag","description":"","parent":0,"count":8,"filter":"raw"},{"term_id":291812,"name":"spectral profile","slug":"spectral-profile","term_group":0,"term_taxonomy_id":291812,"taxonomy":"post_tag","description":"","parent":0,"count":2,"filter":"raw"},{"term_id":291822,"name":"training samples","slug":"training-samples","term_group":0,"term_taxonomy_id":291822,"taxonomy":"post_tag","description":"","parent":0,"count":3,"filter":"raw"}],"category_data":[{"term_id":22931,"name":"Imagery & Remote Sensing","slug":"imagery","term_group":0,"term_taxonomy_id":22931,"taxonomy":"category","description":"","parent":0,"count":765,"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\/346062","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\/8222"}],"replies":[{"embeddable":true,"href":"https:\/\/www.esri.com\/arcgis-blog\/wp-json\/wp\/v2\/comments?post=346062"}],"version-history":[{"count":0,"href":"https:\/\/www.esri.com\/arcgis-blog\/wp-json\/wp\/v2\/blog\/346062\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.esri.com\/arcgis-blog\/wp-json\/wp\/v2\/media?parent=346062"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.esri.com\/arcgis-blog\/wp-json\/wp\/v2\/categories?post=346062"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.esri.com\/arcgis-blog\/wp-json\/wp\/v2\/tags?post=346062"},{"taxonomy":"industry","embeddable":true,"href":"https:\/\/www.esri.com\/arcgis-blog\/wp-json\/wp\/v2\/industry?post=346062"},{"taxonomy":"product","embeddable":true,"href":"https:\/\/www.esri.com\/arcgis-blog\/wp-json\/wp\/v2\/product?post=346062"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}