{"id":84050,"date":"2023-08-14T07:28:24","date_gmt":"2023-08-14T12:28:24","guid":{"rendered":"https:\/\/gisgeography.com\/?p=84050"},"modified":"2025-05-31T21:48:09","modified_gmt":"2025-06-01T02:48:09","slug":"unsupervised-classification-remote-sensing","status":"publish","type":"post","link":"https:\/\/gisgeography.com\/unsupervised-classification-remote-sensing\/","title":{"rendered":"Unsupervised Classification in Remote Sensing"},"content":{"rendered":"<style>.kb-image84050_f32df6-aa .kb-image-has-overlay:after{opacity:0.3;}<\/style>\n<figure class=\"wp-block-kadence-image kb-image84050_f32df6-aa size-medium_large\"><img loading=\"lazy\" decoding=\"async\" width=\"768\" height=\"461\" src=\"https:\/\/gisgeography.com\/wp-content\/uploads\/2023\/08\/Unsupervised-Classification-Remote-Sensing-768x461.jpg\" alt=\"Unsupervised Classification Remote Sensing\" class=\"kb-img wp-image-84053\" srcset=\"https:\/\/gisgeography.com\/wp-content\/uploads\/2023\/08\/Unsupervised-Classification-Remote-Sensing-768x461.jpg 768w, https:\/\/gisgeography.com\/wp-content\/uploads\/2023\/08\/Unsupervised-Classification-Remote-Sensing-300x180.jpg 300w, https:\/\/gisgeography.com\/wp-content\/uploads\/2023\/08\/Unsupervised-Classification-Remote-Sensing-678x407.jpg 678w, https:\/\/gisgeography.com\/wp-content\/uploads\/2023\/08\/Unsupervised-Classification-Remote-Sensing-200x120.jpg 200w, https:\/\/gisgeography.com\/wp-content\/uploads\/2023\/08\/Unsupervised-Classification-Remote-Sensing-425x255.jpg 425w, https:\/\/gisgeography.com\/wp-content\/uploads\/2023\/08\/Unsupervised-Classification-Remote-Sensing-550x330.jpg 550w, https:\/\/gisgeography.com\/wp-content\/uploads\/2023\/08\/Unsupervised-Classification-Remote-Sensing-115x69.jpg 115w, https:\/\/gisgeography.com\/wp-content\/uploads\/2023\/08\/Unsupervised-Classification-Remote-Sensing-360x216.jpg 360w, https:\/\/gisgeography.com\/wp-content\/uploads\/2023\/08\/Unsupervised-Classification-Remote-Sensing.jpg 938w\" sizes=\"auto, (max-width: 768px) 100vw, 768px\" \/><\/figure>\n\n\n\n<div class=\"wp-block-group\" style=\"padding-top:var(--wp--preset--spacing--20);padding-bottom:var(--wp--preset--spacing--20)\"><div class=\"wp-block-group__inner-container is-layout-constrained wp-block-group-is-layout-constrained\"><style>.wp-block-kadence-advancedheading.kt-adv-heading84050_f18301-9f, .wp-block-kadence-advancedheading.kt-adv-heading84050_f18301-9f[data-kb-block=\"kb-adv-heading84050_f18301-9f\"]{font-style:normal;}.wp-block-kadence-advancedheading.kt-adv-heading84050_f18301-9f mark.kt-highlight, .wp-block-kadence-advancedheading.kt-adv-heading84050_f18301-9f[data-kb-block=\"kb-adv-heading84050_f18301-9f\"] mark.kt-highlight{font-style:normal;color:#f76a0c;-webkit-box-decoration-break:clone;box-decoration-break:clone;padding-top:0px;padding-right:0px;padding-bottom:0px;padding-left:0px;}.wp-block-kadence-advancedheading.kt-adv-heading84050_f18301-9f img.kb-inline-image, .wp-block-kadence-advancedheading.kt-adv-heading84050_f18301-9f[data-kb-block=\"kb-adv-heading84050_f18301-9f\"] img.kb-inline-image{width:150px;vertical-align:baseline;}<\/style>\n<h2 class=\"kt-adv-heading84050_f18301-9f wp-block-kadence-advancedheading\" data-kb-block=\"kb-adv-heading84050_f18301-9f\">What Is Unsupervised Classification in Remote Sensing?<\/h2>\n\n\n\n<p>Unsupervised classification in remote sensing <strong>categorizes pixels<\/strong> within an image into distinct classes.<\/p>\n\n\n\n<p>But the key difference between it and supervised classification is that it groups <strong>without prior training or labeled data<\/strong>.<\/p>\n\n\n\n<p>In this approach, clustering identifies similarities in pixel values with their spectral characteristics.<\/p>\n\n\n\n<p>In this article, we&#8217;re going to go through the steps of unsupervised classification.<\/p>\n<\/div><\/div>\n\n\n\n<div class=\"wp-block-group\" style=\"padding-top:var(--wp--preset--spacing--40);padding-bottom:var(--wp--preset--spacing--40)\"><div class=\"wp-block-group__inner-container is-layout-constrained wp-block-group-is-layout-constrained\"><style>.wp-block-kadence-advancedheading.kt-adv-heading84050_f3107b-29, .wp-block-kadence-advancedheading.kt-adv-heading84050_f3107b-29[data-kb-block=\"kb-adv-heading84050_f3107b-29\"]{font-style:normal;}.wp-block-kadence-advancedheading.kt-adv-heading84050_f3107b-29 mark.kt-highlight, .wp-block-kadence-advancedheading.kt-adv-heading84050_f3107b-29[data-kb-block=\"kb-adv-heading84050_f3107b-29\"] mark.kt-highlight{font-style:normal;color:#f76a0c;-webkit-box-decoration-break:clone;box-decoration-break:clone;padding-top:0px;padding-right:0px;padding-bottom:0px;padding-left:0px;}.wp-block-kadence-advancedheading.kt-adv-heading84050_f3107b-29 img.kb-inline-image, .wp-block-kadence-advancedheading.kt-adv-heading84050_f3107b-29[data-kb-block=\"kb-adv-heading84050_f3107b-29\"] img.kb-inline-image{width:150px;vertical-align:baseline;}<\/style>\n<h2 class=\"kt-adv-heading84050_f3107b-29 wp-block-kadence-advancedheading\" data-kb-block=\"kb-adv-heading84050_f3107b-29\">Unsupervised Image Classification Steps<\/h2>\n\n\n\n<p>The process of unsupervised classification involves the following two basic steps:<\/p>\n\n\n<div class=\"wp-block-image\">\n<figure class=\"alignright\"><img loading=\"lazy\" decoding=\"async\" width=\"213\" height=\"215\" src=\"https:\/\/gisgeography.com\/wp-content\/uploads\/2014\/06\/unsupervised-diagram.png\" alt=\"Unsupervised Classification Diagram\" class=\"wp-image-834\" srcset=\"https:\/\/gisgeography.com\/wp-content\/uploads\/2014\/06\/unsupervised-diagram.png 213w, https:\/\/gisgeography.com\/wp-content\/uploads\/2014\/06\/unsupervised-diagram-150x150.png 150w, https:\/\/gisgeography.com\/wp-content\/uploads\/2014\/06\/unsupervised-diagram-50x50.png 50w, https:\/\/gisgeography.com\/wp-content\/uploads\/2014\/06\/unsupervised-diagram-198x200.png 198w, https:\/\/gisgeography.com\/wp-content\/uploads\/2014\/06\/unsupervised-diagram-115x116.png 115w, https:\/\/gisgeography.com\/wp-content\/uploads\/2014\/06\/unsupervised-diagram-154x155.png 154w\" sizes=\"auto, (max-width: 213px) 100vw, 213px\" \/><\/figure>\n<\/div>\n\n\n<ol class=\"wp-block-list\">\n<li><strong>Generate Clusters<\/strong>: Generating clusters involves autonomously grouping pixels with similar spectral characteristics.<\/li>\n\n\n\n<li><strong>Manual Classification<\/strong>: Classifying clusters means assigning each group of pixels a land cover category.<\/li>\n<\/ol>\n\n\n\n<p><strong>READ MORE:<\/strong> <a href=\"https:\/\/gisgeography.com\/supervised-unsupervised-classification-arcgis\/\">Supervised and Unsupervised Classification in Remote Sensing<\/a><\/p>\n<\/div><\/div>\n\n\n\n<div class=\"wp-block-group\" style=\"padding-top:var(--wp--preset--spacing--40);padding-bottom:var(--wp--preset--spacing--40)\"><div class=\"wp-block-group__inner-container is-layout-constrained wp-block-group-is-layout-constrained\"><style>.wp-block-kadence-advancedheading.kt-adv-heading84050_1b136f-54, .wp-block-kadence-advancedheading.kt-adv-heading84050_1b136f-54[data-kb-block=\"kb-adv-heading84050_1b136f-54\"]{font-style:normal;}.wp-block-kadence-advancedheading.kt-adv-heading84050_1b136f-54 mark.kt-highlight, .wp-block-kadence-advancedheading.kt-adv-heading84050_1b136f-54[data-kb-block=\"kb-adv-heading84050_1b136f-54\"] mark.kt-highlight{font-style:normal;color:#f76a0c;-webkit-box-decoration-break:clone;box-decoration-break:clone;padding-top:0px;padding-right:0px;padding-bottom:0px;padding-left:0px;}.wp-block-kadence-advancedheading.kt-adv-heading84050_1b136f-54 img.kb-inline-image, .wp-block-kadence-advancedheading.kt-adv-heading84050_1b136f-54[data-kb-block=\"kb-adv-heading84050_1b136f-54\"] img.kb-inline-image{width:150px;vertical-align:baseline;}<\/style>\n<h2 class=\"kt-adv-heading84050_1b136f-54 wp-block-kadence-advancedheading\" data-kb-block=\"kb-adv-heading84050_1b136f-54\">Step 1. Generating Clusters<\/h2>\n\n\n\n<p>As mentioned already, generating clusters involves grouping pixels <strong>based on similar spectral characteristics<\/strong>. This allows you to identify distinct land cover classes in any type of imagery.<\/p>\n\n\n\n<p>Here are some of the options that you have to consider when you&#8217;re generating clusters:<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>NUMBER OF CLASSES<\/strong>: The number of clusters that you want to generate during the unsupervised classification. ArcGIS recommends that this number should be 10 times larger than the number of bands in your image. So if you are working with red, green, and blue bands, then this value should be 30. But keep in mind that you can always combine clusters together into a single class.<\/li>\n\n\n\n<li><strong>MINIMUM CLASS SIZE<\/strong>: This value can ensure that you have a minimum number of pixels to make a unique class.<\/li>\n<\/ul>\n\n\n\n<p>Overall, we recommend trial and error with these inputs as they can make a world of difference to the quality of your classification.<\/p>\n\n\n\n<p>Here&#8217;s an example of a raw <a href=\"https:\/\/gisgeography.com\/landsat\/\">Landsat image<\/a>. If you&#8217;re looking to download an image for your own personal use, check out our guide on <a href=\"https:\/\/gisgeography.com\/usgs-earth-explorer-download-free-landsat-imagery\/\">downloading Landsat imagery from the USGS Earth Explorer<\/a>.<\/p>\n\n\n<style>.kb-image84050_be6920-34.kb-image-is-ratio-size, .kb-image84050_be6920-34 .kb-image-is-ratio-size{max-width:650px;width:100%;}.wp-block-kadence-column > .kt-inside-inner-col > .kb-image84050_be6920-34.kb-image-is-ratio-size, .wp-block-kadence-column > .kt-inside-inner-col > .kb-image84050_be6920-34 .kb-image-is-ratio-size{align-self:unset;}.kb-image84050_be6920-34{max-width:650px;}.image-is-svg.kb-image84050_be6920-34{-webkit-flex:0 1 100%;flex:0 1 100%;}.image-is-svg.kb-image84050_be6920-34 img{width:100%;}.kb-image84050_be6920-34 .kb-image-has-overlay:after{opacity:0.3;}<\/style>\n<figure class=\"wp-block-kadence-image kb-image84050_be6920-34 size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"678\" height=\"404\" src=\"https:\/\/gisgeography.com\/wp-content\/uploads\/2023\/08\/Raw-Image-Unsupervised-Classification-678x404.jpg\" alt=\"Raw Image Unsupervised Classification\" class=\"kb-img wp-image-84057\" srcset=\"https:\/\/gisgeography.com\/wp-content\/uploads\/2023\/08\/Raw-Image-Unsupervised-Classification-678x404.jpg 678w, https:\/\/gisgeography.com\/wp-content\/uploads\/2023\/08\/Raw-Image-Unsupervised-Classification-300x179.jpg 300w, https:\/\/gisgeography.com\/wp-content\/uploads\/2023\/08\/Raw-Image-Unsupervised-Classification-768x458.jpg 768w, https:\/\/gisgeography.com\/wp-content\/uploads\/2023\/08\/Raw-Image-Unsupervised-Classification-200x119.jpg 200w, https:\/\/gisgeography.com\/wp-content\/uploads\/2023\/08\/Raw-Image-Unsupervised-Classification-425x254.jpg 425w, https:\/\/gisgeography.com\/wp-content\/uploads\/2023\/08\/Raw-Image-Unsupervised-Classification-550x328.jpg 550w, https:\/\/gisgeography.com\/wp-content\/uploads\/2023\/08\/Raw-Image-Unsupervised-Classification-115x69.jpg 115w, https:\/\/gisgeography.com\/wp-content\/uploads\/2023\/08\/Raw-Image-Unsupervised-Classification-360x215.jpg 360w, https:\/\/gisgeography.com\/wp-content\/uploads\/2023\/08\/Raw-Image-Unsupervised-Classification.jpg 855w\" sizes=\"auto, (max-width: 678px) 100vw, 678px\" \/><\/figure>\n\n\n\n<p>After clustering your image, it will look like the following. As you can see, it&#8217;s done a fairly good job of grouping pixels based on the spectral properties of the image.<\/p>\n\n\n<style>.kb-image84050_fbc03d-92.kb-image-is-ratio-size, .kb-image84050_fbc03d-92 .kb-image-is-ratio-size{max-width:650px;width:100%;}.wp-block-kadence-column > .kt-inside-inner-col > .kb-image84050_fbc03d-92.kb-image-is-ratio-size, .wp-block-kadence-column > .kt-inside-inner-col > .kb-image84050_fbc03d-92 .kb-image-is-ratio-size{align-self:unset;}.kb-image84050_fbc03d-92{max-width:650px;}.image-is-svg.kb-image84050_fbc03d-92{-webkit-flex:0 1 100%;flex:0 1 100%;}.image-is-svg.kb-image84050_fbc03d-92 img{width:100%;}.kb-image84050_fbc03d-92 .kb-image-has-overlay:after{opacity:0.3;}<\/style>\n<figure class=\"wp-block-kadence-image kb-image84050_fbc03d-92 size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"678\" height=\"406\" src=\"https:\/\/gisgeography.com\/wp-content\/uploads\/2023\/08\/Image-Clusters-Unsupervised-Classification-678x406.jpg\" alt=\"Image Clusters Unsupervised Classification\" class=\"kb-img wp-image-84058\" srcset=\"https:\/\/gisgeography.com\/wp-content\/uploads\/2023\/08\/Image-Clusters-Unsupervised-Classification-678x406.jpg 678w, https:\/\/gisgeography.com\/wp-content\/uploads\/2023\/08\/Image-Clusters-Unsupervised-Classification-300x180.jpg 300w, https:\/\/gisgeography.com\/wp-content\/uploads\/2023\/08\/Image-Clusters-Unsupervised-Classification-768x460.jpg 768w, https:\/\/gisgeography.com\/wp-content\/uploads\/2023\/08\/Image-Clusters-Unsupervised-Classification-200x120.jpg 200w, https:\/\/gisgeography.com\/wp-content\/uploads\/2023\/08\/Image-Clusters-Unsupervised-Classification-425x254.jpg 425w, https:\/\/gisgeography.com\/wp-content\/uploads\/2023\/08\/Image-Clusters-Unsupervised-Classification-550x329.jpg 550w, https:\/\/gisgeography.com\/wp-content\/uploads\/2023\/08\/Image-Clusters-Unsupervised-Classification-115x69.jpg 115w, https:\/\/gisgeography.com\/wp-content\/uploads\/2023\/08\/Image-Clusters-Unsupervised-Classification-360x216.jpg 360w, https:\/\/gisgeography.com\/wp-content\/uploads\/2023\/08\/Image-Clusters-Unsupervised-Classification.jpg 800w\" sizes=\"auto, (max-width: 678px) 100vw, 678px\" \/><\/figure>\n\n\n\n<p>But the only problem is that it&#8217;s hard to tell which class is which. We&#8217;ll address this issue in the next step through manual classification.<\/p>\n<\/div><\/div>\n\n\n\n<div class=\"wp-block-group\" style=\"padding-top:var(--wp--preset--spacing--40);padding-bottom:var(--wp--preset--spacing--40)\"><div class=\"wp-block-group__inner-container is-layout-constrained wp-block-group-is-layout-constrained\"><style>.wp-block-kadence-advancedheading.kt-adv-heading84050_5e275c-31, .wp-block-kadence-advancedheading.kt-adv-heading84050_5e275c-31[data-kb-block=\"kb-adv-heading84050_5e275c-31\"]{font-style:normal;}.wp-block-kadence-advancedheading.kt-adv-heading84050_5e275c-31 mark.kt-highlight, .wp-block-kadence-advancedheading.kt-adv-heading84050_5e275c-31[data-kb-block=\"kb-adv-heading84050_5e275c-31\"] mark.kt-highlight{font-style:normal;color:#f76a0c;-webkit-box-decoration-break:clone;box-decoration-break:clone;padding-top:0px;padding-right:0px;padding-bottom:0px;padding-left:0px;}.wp-block-kadence-advancedheading.kt-adv-heading84050_5e275c-31 img.kb-inline-image, .wp-block-kadence-advancedheading.kt-adv-heading84050_5e275c-31[data-kb-block=\"kb-adv-heading84050_5e275c-31\"] img.kb-inline-image{width:150px;vertical-align:baseline;}<\/style>\n<h2 class=\"kt-adv-heading84050_5e275c-31 wp-block-kadence-advancedheading\" data-kb-block=\"kb-adv-heading84050_5e275c-31\">Step 2. Manual Classification<\/h2>\n\n\n\n<p>Manual classification involves visually inspecting the clusters generated. Then, you <strong>assign them to specific land cover classes<\/strong> based on their spectral characteristics and context within the image.<\/p>\n\n\n\n<p>While this method allows for greater interpretive control, it can be subjective. It can also be more time-consuming compared to automated approaches.<\/p>\n\n\n\n<p>Below is a screenshot of <strong>setting each class color<\/strong> to a specific land cover class. For example, you may want to change water classes to blue and urban classes to red.<\/p>\n\n\n<style>.kb-image84050_58a58e-a5 .kb-image-has-overlay:after{opacity:0.3;}.kb-image84050_58a58e-a5 img.kb-img, .kb-image84050_58a58e-a5 .kb-img img{border-top:1px solid #cccccc;border-right:1px solid #cccccc;border-bottom:1px solid #cccccc;border-left:1px solid #cccccc;}@media all and (max-width: 1024px){.kb-image84050_58a58e-a5 img.kb-img, .kb-image84050_58a58e-a5 .kb-img img{border-top:1px solid #cccccc;border-right:1px solid #cccccc;border-bottom:1px solid #cccccc;border-left:1px solid #cccccc;}}@media all and (max-width: 767px){.kb-image84050_58a58e-a5 img.kb-img, .kb-image84050_58a58e-a5 .kb-img img{border-top:1px solid #cccccc;border-right:1px solid #cccccc;border-bottom:1px solid #cccccc;border-left:1px solid #cccccc;}}<\/style>\n<figure class=\"wp-block-kadence-image kb-image84050_58a58e-a5 size-medium_large\"><img loading=\"lazy\" decoding=\"async\" width=\"768\" height=\"413\" src=\"https:\/\/gisgeography.com\/wp-content\/uploads\/2023\/08\/Color-Coded-Manual-Unsupervised-Classification-768x413.jpg\" alt=\"Color Coded Manual Unsupervised Classification\" class=\"kb-img wp-image-84060\" srcset=\"https:\/\/gisgeography.com\/wp-content\/uploads\/2023\/08\/Color-Coded-Manual-Unsupervised-Classification-768x413.jpg 768w, https:\/\/gisgeography.com\/wp-content\/uploads\/2023\/08\/Color-Coded-Manual-Unsupervised-Classification-300x161.jpg 300w, https:\/\/gisgeography.com\/wp-content\/uploads\/2023\/08\/Color-Coded-Manual-Unsupervised-Classification-678x365.jpg 678w, https:\/\/gisgeography.com\/wp-content\/uploads\/2023\/08\/Color-Coded-Manual-Unsupervised-Classification-1536x827.jpg 1536w, https:\/\/gisgeography.com\/wp-content\/uploads\/2023\/08\/Color-Coded-Manual-Unsupervised-Classification-200x108.jpg 200w, https:\/\/gisgeography.com\/wp-content\/uploads\/2023\/08\/Color-Coded-Manual-Unsupervised-Classification-425x229.jpg 425w, https:\/\/gisgeography.com\/wp-content\/uploads\/2023\/08\/Color-Coded-Manual-Unsupervised-Classification-550x296.jpg 550w, https:\/\/gisgeography.com\/wp-content\/uploads\/2023\/08\/Color-Coded-Manual-Unsupervised-Classification-115x62.jpg 115w, https:\/\/gisgeography.com\/wp-content\/uploads\/2023\/08\/Color-Coded-Manual-Unsupervised-Classification-1000x538.jpg 1000w, https:\/\/gisgeography.com\/wp-content\/uploads\/2023\/08\/Color-Coded-Manual-Unsupervised-Classification-360x194.jpg 360w, https:\/\/gisgeography.com\/wp-content\/uploads\/2023\/08\/Color-Coded-Manual-Unsupervised-Classification.jpg 1635w\" sizes=\"auto, (max-width: 768px) 100vw, 768px\" \/><\/figure>\n\n\n\n<p>Needless to say, this can be a very tedious process. Specifically, you may never find the perfect class for a cluster. If this is the case, you may want to repeat step 1 and regenerate clusters. Another good option is to try out <a href=\"https:\/\/gisgeography.com\/obia-object-based-image-analysis-geobia\/\">object-based image classification<\/a> as it can be more accurate.<\/p>\n\n\n\n<p>After completing this manual process of assigning each cluster to a land cover class, here is what the final product looks like with water, wetlands, urban, and different forested areas:<\/p>\n\n\n<style>.kb-image84050_d65528-23 .kb-image-has-overlay:after{opacity:0.3;}<\/style>\n<figure class=\"wp-block-kadence-image kb-image84050_d65528-23 size-medium_large\"><img loading=\"lazy\" decoding=\"async\" width=\"768\" height=\"461\" src=\"https:\/\/gisgeography.com\/wp-content\/uploads\/2023\/08\/Final-Land-Cover-Product-768x461.jpg\" alt=\"Final Land Cover Product\" class=\"kb-img wp-image-84061\" srcset=\"https:\/\/gisgeography.com\/wp-content\/uploads\/2023\/08\/Final-Land-Cover-Product-768x461.jpg 768w, https:\/\/gisgeography.com\/wp-content\/uploads\/2023\/08\/Final-Land-Cover-Product-300x180.jpg 300w, https:\/\/gisgeography.com\/wp-content\/uploads\/2023\/08\/Final-Land-Cover-Product-678x407.jpg 678w, https:\/\/gisgeography.com\/wp-content\/uploads\/2023\/08\/Final-Land-Cover-Product-200x120.jpg 200w, https:\/\/gisgeography.com\/wp-content\/uploads\/2023\/08\/Final-Land-Cover-Product-425x255.jpg 425w, https:\/\/gisgeography.com\/wp-content\/uploads\/2023\/08\/Final-Land-Cover-Product-550x330.jpg 550w, https:\/\/gisgeography.com\/wp-content\/uploads\/2023\/08\/Final-Land-Cover-Product-115x69.jpg 115w, https:\/\/gisgeography.com\/wp-content\/uploads\/2023\/08\/Final-Land-Cover-Product-360x216.jpg 360w, https:\/\/gisgeography.com\/wp-content\/uploads\/2023\/08\/Final-Land-Cover-Product.jpg 938w\" sizes=\"auto, (max-width: 768px) 100vw, 768px\" \/><\/figure>\n\n\n\n<p>Keep in mind that you&#8217;ll have to export your final land cover product. You may also have to reclassify each class and merge each cluster into its own unique land cover ID.<\/p>\n<\/div><\/div>\n\n\n\n<div class=\"wp-block-group\" style=\"padding-top:var(--wp--preset--spacing--40);padding-bottom:var(--wp--preset--spacing--40)\"><div class=\"wp-block-group__inner-container is-layout-constrained wp-block-group-is-layout-constrained\"><style>.wp-block-kadence-advancedheading.kt-adv-heading84050_6411fe-c3, .wp-block-kadence-advancedheading.kt-adv-heading84050_6411fe-c3[data-kb-block=\"kb-adv-heading84050_6411fe-c3\"]{font-style:normal;}.wp-block-kadence-advancedheading.kt-adv-heading84050_6411fe-c3 mark.kt-highlight, .wp-block-kadence-advancedheading.kt-adv-heading84050_6411fe-c3[data-kb-block=\"kb-adv-heading84050_6411fe-c3\"] mark.kt-highlight{font-style:normal;color:#f76a0c;-webkit-box-decoration-break:clone;box-decoration-break:clone;padding-top:0px;padding-right:0px;padding-bottom:0px;padding-left:0px;}.wp-block-kadence-advancedheading.kt-adv-heading84050_6411fe-c3 img.kb-inline-image, .wp-block-kadence-advancedheading.kt-adv-heading84050_6411fe-c3[data-kb-block=\"kb-adv-heading84050_6411fe-c3\"] img.kb-inline-image{width:150px;vertical-align:baseline;}<\/style>\n<h2 class=\"kt-adv-heading84050_6411fe-c3 wp-block-kadence-advancedheading\" data-kb-block=\"kb-adv-heading84050_6411fe-c3\">Summary: Unsupervised Classification<\/h2>\n\n\n\n<p>You&#8217;ve learned today that the two steps for performing an unsupervised classification are (1) generating clusters and (2) manual classification.<\/p>\n\n\n\n<p>Although you may not ever be able to generate perfect clusters, this technique allows you to perform land cover classification <strong>without predefined training data<\/strong> and <strong>minimal user intervention<\/strong> prior to classification.<\/p>\n\n\n\n<p>In our example, we classified a Landsat image into water, wetlands, urban, and forested land cover classes.<\/p>\n\n\n\n<p>Do you have any questions? We&#8217;d love to hear from you. Please send us your feedback in the comment section below.<\/p>\n<\/div><\/div>\n","protected":false},"excerpt":{"rendered":"<p>Unsupervised classification is a technique in remote sensing that clusters pixels within a satellite or aerial image into distinct classes.<\/p>\n","protected":false},"author":2,"featured_media":84053,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_kad_blocks_custom_css":"","_kad_blocks_head_custom_js":"","_kad_blocks_body_custom_js":"","_kad_blocks_footer_custom_js":"","_kad_post_transparent":"","_kad_post_title":"","_kad_post_layout":"","_kad_post_sidebar_id":"","_kad_post_content_style":"","_kad_post_vertical_padding":"","_kad_post_feature":"","_kad_post_feature_position":"","_kad_post_header":false,"_kad_post_footer":false,"_kad_post_classname":"","footnotes":""},"categories":[90],"tags":[67],"class_list":["post-84050","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-gis-analysis","tag-image-classification"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v27.6 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>Unsupervised Classification in Remote Sensing - GIS Geography<\/title>\n<meta name=\"description\" content=\"Unsupervised classification is a technique in remote sensing that clusters pixels within a satellite or aerial image into distinct classes.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/gisgeography.com\/unsupervised-classification-remote-sensing\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Unsupervised Classification in Remote Sensing - GIS Geography\" \/>\n<meta property=\"og:description\" content=\"Unsupervised classification is a technique in remote sensing that clusters pixels within a satellite or aerial image into distinct classes.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/gisgeography.com\/unsupervised-classification-remote-sensing\/\" \/>\n<meta property=\"og:site_name\" content=\"GIS Geography\" \/>\n<meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/gisgeography\" \/>\n<meta property=\"article:author\" content=\"https:\/\/www.facebook.com\/gisgeography\" \/>\n<meta property=\"article:published_time\" content=\"2023-08-14T12:28:24+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2025-06-01T02:48:09+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/gisgeography.com\/wp-content\/uploads\/2023\/08\/Unsupervised-Classification-Remote-Sensing.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"938\" \/>\n\t<meta property=\"og:image:height\" content=\"563\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"author\" content=\"GISGeography\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@https:\/\/twitter.com\/GisGeography\" \/>\n<meta name=\"twitter:site\" content=\"@GisGeography\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"GISGeography\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"5 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\\\/\\\/gisgeography.com\\\/unsupervised-classification-remote-sensing\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/gisgeography.com\\\/unsupervised-classification-remote-sensing\\\/\"},\"author\":{\"name\":\"GISGeography\",\"@id\":\"https:\\\/\\\/gisgeography.com\\\/#\\\/schema\\\/person\\\/9e7385da3acea92bc45d45be5dfe191e\"},\"headline\":\"Unsupervised Classification in Remote Sensing\",\"datePublished\":\"2023-08-14T12:28:24+00:00\",\"dateModified\":\"2025-06-01T02:48:09+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/gisgeography.com\\\/unsupervised-classification-remote-sensing\\\/\"},\"wordCount\":647,\"commentCount\":0,\"publisher\":{\"@id\":\"https:\\\/\\\/gisgeography.com\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/gisgeography.com\\\/unsupervised-classification-remote-sensing\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/gisgeography.com\\\/wp-content\\\/uploads\\\/2023\\\/08\\\/Unsupervised-Classification-Remote-Sensing.jpg\",\"keywords\":[\"Image Classification\"],\"articleSection\":[\"GIS Analysis\"],\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"CommentAction\",\"name\":\"Comment\",\"target\":[\"https:\\\/\\\/gisgeography.com\\\/unsupervised-classification-remote-sensing\\\/#respond\"]}]},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/gisgeography.com\\\/unsupervised-classification-remote-sensing\\\/\",\"url\":\"https:\\\/\\\/gisgeography.com\\\/unsupervised-classification-remote-sensing\\\/\",\"name\":\"Unsupervised Classification in Remote Sensing - GIS Geography\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/gisgeography.com\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/gisgeography.com\\\/unsupervised-classification-remote-sensing\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/gisgeography.com\\\/unsupervised-classification-remote-sensing\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/gisgeography.com\\\/wp-content\\\/uploads\\\/2023\\\/08\\\/Unsupervised-Classification-Remote-Sensing.jpg\",\"datePublished\":\"2023-08-14T12:28:24+00:00\",\"dateModified\":\"2025-06-01T02:48:09+00:00\",\"description\":\"Unsupervised classification is a technique in remote sensing that clusters pixels within a satellite or aerial image into distinct classes.\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/gisgeography.com\\\/unsupervised-classification-remote-sensing\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/gisgeography.com\\\/unsupervised-classification-remote-sensing\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/gisgeography.com\\\/unsupervised-classification-remote-sensing\\\/#primaryimage\",\"url\":\"https:\\\/\\\/gisgeography.com\\\/wp-content\\\/uploads\\\/2023\\\/08\\\/Unsupervised-Classification-Remote-Sensing.jpg\",\"contentUrl\":\"https:\\\/\\\/gisgeography.com\\\/wp-content\\\/uploads\\\/2023\\\/08\\\/Unsupervised-Classification-Remote-Sensing.jpg\",\"width\":938,\"height\":563,\"caption\":\"Unsupervised Classification Remote Sensing\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/gisgeography.com\\\/unsupervised-classification-remote-sensing\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/gisgeography.com\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"GIS Analysis\",\"item\":\"https:\\\/\\\/gisgeography.com\\\/category\\\/gis-analysis\\\/\"},{\"@type\":\"ListItem\",\"position\":3,\"name\":\"Unsupervised Classification in Remote Sensing\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/gisgeography.com\\\/#website\",\"url\":\"https:\\\/\\\/gisgeography.com\\\/\",\"name\":\"GIS Geography\",\"description\":\"Geographic Information Systems\",\"publisher\":{\"@id\":\"https:\\\/\\\/gisgeography.com\\\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/gisgeography.com\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/gisgeography.com\\\/#organization\",\"name\":\"GIS Geography\",\"url\":\"https:\\\/\\\/gisgeography.com\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/gisgeography.com\\\/#\\\/schema\\\/logo\\\/image\\\/\",\"url\":\"https:\\\/\\\/gisgeography.com\\\/wp-content\\\/uploads\\\/2015\\\/11\\\/cropped-GIS-Geography-Logo0.png\",\"contentUrl\":\"https:\\\/\\\/gisgeography.com\\\/wp-content\\\/uploads\\\/2015\\\/11\\\/cropped-GIS-Geography-Logo0.png\",\"width\":500,\"height\":100,\"caption\":\"GIS Geography\"},\"image\":{\"@id\":\"https:\\\/\\\/gisgeography.com\\\/#\\\/schema\\\/logo\\\/image\\\/\"},\"sameAs\":[\"https:\\\/\\\/www.facebook.com\\\/gisgeography\",\"https:\\\/\\\/x.com\\\/GisGeography\"]},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/gisgeography.com\\\/#\\\/schema\\\/person\\\/9e7385da3acea92bc45d45be5dfe191e\",\"name\":\"GISGeography\",\"description\":\"We help you learn Geographic Information Systems and remote sensing\",\"sameAs\":[\"https:\\\/\\\/www.facebook.com\\\/gisgeography\",\"https:\\\/\\\/x.com\\\/https:\\\/\\\/twitter.com\\\/GisGeography\"],\"url\":\"https:\\\/\\\/gisgeography.com\\\/author\\\/gisgeo\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Unsupervised Classification in Remote Sensing - GIS Geography","description":"Unsupervised classification is a technique in remote sensing that clusters pixels within a satellite or aerial image into distinct classes.","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:\/\/gisgeography.com\/unsupervised-classification-remote-sensing\/","og_locale":"en_US","og_type":"article","og_title":"Unsupervised Classification in Remote Sensing - GIS Geography","og_description":"Unsupervised classification is a technique in remote sensing that clusters pixels within a satellite or aerial image into distinct classes.","og_url":"https:\/\/gisgeography.com\/unsupervised-classification-remote-sensing\/","og_site_name":"GIS Geography","article_publisher":"https:\/\/www.facebook.com\/gisgeography","article_author":"https:\/\/www.facebook.com\/gisgeography","article_published_time":"2023-08-14T12:28:24+00:00","article_modified_time":"2025-06-01T02:48:09+00:00","og_image":[{"width":938,"height":563,"url":"https:\/\/gisgeography.com\/wp-content\/uploads\/2023\/08\/Unsupervised-Classification-Remote-Sensing.jpg","type":"image\/jpeg"}],"author":"GISGeography","twitter_card":"summary_large_image","twitter_creator":"@https:\/\/twitter.com\/GisGeography","twitter_site":"@GisGeography","twitter_misc":{"Written by":"GISGeography","Est. reading time":"5 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/gisgeography.com\/unsupervised-classification-remote-sensing\/#article","isPartOf":{"@id":"https:\/\/gisgeography.com\/unsupervised-classification-remote-sensing\/"},"author":{"name":"GISGeography","@id":"https:\/\/gisgeography.com\/#\/schema\/person\/9e7385da3acea92bc45d45be5dfe191e"},"headline":"Unsupervised Classification in Remote Sensing","datePublished":"2023-08-14T12:28:24+00:00","dateModified":"2025-06-01T02:48:09+00:00","mainEntityOfPage":{"@id":"https:\/\/gisgeography.com\/unsupervised-classification-remote-sensing\/"},"wordCount":647,"commentCount":0,"publisher":{"@id":"https:\/\/gisgeography.com\/#organization"},"image":{"@id":"https:\/\/gisgeography.com\/unsupervised-classification-remote-sensing\/#primaryimage"},"thumbnailUrl":"https:\/\/gisgeography.com\/wp-content\/uploads\/2023\/08\/Unsupervised-Classification-Remote-Sensing.jpg","keywords":["Image Classification"],"articleSection":["GIS Analysis"],"inLanguage":"en-US","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/gisgeography.com\/unsupervised-classification-remote-sensing\/#respond"]}]},{"@type":"WebPage","@id":"https:\/\/gisgeography.com\/unsupervised-classification-remote-sensing\/","url":"https:\/\/gisgeography.com\/unsupervised-classification-remote-sensing\/","name":"Unsupervised Classification in Remote Sensing - GIS Geography","isPartOf":{"@id":"https:\/\/gisgeography.com\/#website"},"primaryImageOfPage":{"@id":"https:\/\/gisgeography.com\/unsupervised-classification-remote-sensing\/#primaryimage"},"image":{"@id":"https:\/\/gisgeography.com\/unsupervised-classification-remote-sensing\/#primaryimage"},"thumbnailUrl":"https:\/\/gisgeography.com\/wp-content\/uploads\/2023\/08\/Unsupervised-Classification-Remote-Sensing.jpg","datePublished":"2023-08-14T12:28:24+00:00","dateModified":"2025-06-01T02:48:09+00:00","description":"Unsupervised classification is a technique in remote sensing that clusters pixels within a satellite or aerial image into distinct classes.","breadcrumb":{"@id":"https:\/\/gisgeography.com\/unsupervised-classification-remote-sensing\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/gisgeography.com\/unsupervised-classification-remote-sensing\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/gisgeography.com\/unsupervised-classification-remote-sensing\/#primaryimage","url":"https:\/\/gisgeography.com\/wp-content\/uploads\/2023\/08\/Unsupervised-Classification-Remote-Sensing.jpg","contentUrl":"https:\/\/gisgeography.com\/wp-content\/uploads\/2023\/08\/Unsupervised-Classification-Remote-Sensing.jpg","width":938,"height":563,"caption":"Unsupervised Classification Remote Sensing"},{"@type":"BreadcrumbList","@id":"https:\/\/gisgeography.com\/unsupervised-classification-remote-sensing\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/gisgeography.com\/"},{"@type":"ListItem","position":2,"name":"GIS Analysis","item":"https:\/\/gisgeography.com\/category\/gis-analysis\/"},{"@type":"ListItem","position":3,"name":"Unsupervised Classification in Remote Sensing"}]},{"@type":"WebSite","@id":"https:\/\/gisgeography.com\/#website","url":"https:\/\/gisgeography.com\/","name":"GIS Geography","description":"Geographic Information Systems","publisher":{"@id":"https:\/\/gisgeography.com\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/gisgeography.com\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/gisgeography.com\/#organization","name":"GIS Geography","url":"https:\/\/gisgeography.com\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/gisgeography.com\/#\/schema\/logo\/image\/","url":"https:\/\/gisgeography.com\/wp-content\/uploads\/2015\/11\/cropped-GIS-Geography-Logo0.png","contentUrl":"https:\/\/gisgeography.com\/wp-content\/uploads\/2015\/11\/cropped-GIS-Geography-Logo0.png","width":500,"height":100,"caption":"GIS Geography"},"image":{"@id":"https:\/\/gisgeography.com\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/www.facebook.com\/gisgeography","https:\/\/x.com\/GisGeography"]},{"@type":"Person","@id":"https:\/\/gisgeography.com\/#\/schema\/person\/9e7385da3acea92bc45d45be5dfe191e","name":"GISGeography","description":"We help you learn Geographic Information Systems and remote sensing","sameAs":["https:\/\/www.facebook.com\/gisgeography","https:\/\/x.com\/https:\/\/twitter.com\/GisGeography"],"url":"https:\/\/gisgeography.com\/author\/gisgeo\/"}]}},"taxonomy_info":{"category":[{"value":90,"label":"GIS Analysis"}],"post_tag":[{"value":67,"label":"Image Classification"}]},"featured_image_src_large":["https:\/\/gisgeography.com\/wp-content\/uploads\/2023\/08\/Unsupervised-Classification-Remote-Sensing-678x407.jpg",678,407,true],"author_info":{"display_name":"GISGeography","author_link":"https:\/\/gisgeography.com\/author\/gisgeo\/"},"comment_info":1,"category_info":[{"term_id":90,"name":"GIS Analysis","slug":"gis-analysis","term_group":0,"term_taxonomy_id":91,"taxonomy":"category","description":"","parent":0,"count":124,"filter":"raw","cat_ID":90,"category_count":124,"category_description":"","cat_name":"GIS Analysis","category_nicename":"gis-analysis","category_parent":0}],"tag_info":[{"term_id":67,"name":"Image Classification","slug":"image-classification","term_group":0,"term_taxonomy_id":68,"taxonomy":"post_tag","description":"","parent":0,"count":6,"filter":"raw"}],"_links":{"self":[{"href":"https:\/\/gisgeography.com\/wp-json\/wp\/v2\/posts\/84050","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/gisgeography.com\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/gisgeography.com\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/gisgeography.com\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/gisgeography.com\/wp-json\/wp\/v2\/comments?post=84050"}],"version-history":[{"count":13,"href":"https:\/\/gisgeography.com\/wp-json\/wp\/v2\/posts\/84050\/revisions"}],"predecessor-version":[{"id":97986,"href":"https:\/\/gisgeography.com\/wp-json\/wp\/v2\/posts\/84050\/revisions\/97986"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/gisgeography.com\/wp-json\/wp\/v2\/media\/84053"}],"wp:attachment":[{"href":"https:\/\/gisgeography.com\/wp-json\/wp\/v2\/media?parent=84050"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/gisgeography.com\/wp-json\/wp\/v2\/categories?post=84050"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/gisgeography.com\/wp-json\/wp\/v2\/tags?post=84050"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}