{"id":772063,"date":"2026-03-31T19:59:09","date_gmt":"2026-04-01T02:59:09","guid":{"rendered":"https:\/\/www.esri.com\/about\/newsroom\/?post_type=arcnews&#038;p=772063"},"modified":"2026-03-31T15:10:28","modified_gmt":"2026-03-31T22:10:28","slug":"geoai-in-the-age-of-foundation-models","status":"publish","type":"arcnews","link":"https:\/\/www.esri.com\/about\/newsroom\/arcnews\/geoai-in-the-age-of-foundation-models","title":{"rendered":"GeoAI in the Age of Foundation Models"},"author":6921,"featured_media":0,"menu_order":0,"template":"","format":"standard","meta":{"_acf_changed":false,"sync_status":"","episode_type":"","audio_file":"","castos_file_data":"","podmotor_file_id":"","cover_image":"","cover_image_id":"","duration":"","filesize":"","filesize_raw":"","date_recorded":"","explicit":"","block":"","itunes_episode_number":"","itunes_title":"","itunes_season_number":"","itunes_episode_type":"","_links_to":"","_links_to_target":""},"categories":[369852,491742,472991],"tags":[1741,157432,10332,476602,12662],"arcnews_issues":[493400],"class_list":["post-772063","arcnews","type-arcnews","status-publish","format-standard","hentry","category-artificial-intelligence--ai","category-geoai","category-gis","tag-ai","tag-arcgis","tag-imagery","tag-predictive-modeling","tag-remote-sensing","arcnews_issues-spring-2026","arcnews_sections-esri-technology"],"acf":{"short_description":"The rapid progress of AI has produced a new type of model that promises to revolutionize Earth observation\u2014and Esri is at the forefront.","pdf":{"host_remotely":false,"file":"","file_url":""},"flexible_content":[{"acf_fc_layout":"sidebar","layout":"standard","image_reference":null,"image_reference_figure":"","spotlight_image":null,"section_title":"","spotlight_name":"","position":"Left","content":"<h3 style=\"text-align: center;\">Understanding the Two Types of GeoAI Models<\/h3>\r\n<strong>Pretrained GeoAI models<\/strong> are task-specific deep learning models trained to perform particular functions, such as building footprint extraction, road digitization, or land-cover classification. These models are ready to use and require no additional fine-tuning. Organizations apply pretrained models directly to their imagery to extract features or classify pixels without gathering training data or building custom models. They are ideal for when an organization needs to rapidly deploy AI capabilities. Read <a href=\"https:\/\/www.esri.com\/about\/newsroom\/arcnews\/quick-start-guide-to-esri-pretrained-geoai-models\">\u201cA Quick-Start Guide to Esri\u2019s Pretrained GeoAI Models\u201d<\/a> to learn more.\r\n\r\n<strong>Geospatial foundation models<\/strong> are large-scale neural networks with billions of parameters, and they are trained on massive, diverse datasets. Rather than performing a single task, they learn general representations that can be adapted to many downstream applications. Data scientists use foundation models as starting points for developing custom workflows\u2014fine-tuning them for specialized tasks or using their embeddings to enhance machine learning models. They provide more flexibility than pretrained GeoAI models but generally require more expertise, at least for now. Foundation models in GIS can enhance various applications and workflows, such as analyzing satellite data to predict environmental changes or improving the accuracy of imagery interpretations.","snippet":""},{"acf_fc_layout":"content","content":"The rapid progress of AI has produced a new category of models that promise to revolutionize Earth observation. Foundation models, characterized by their massive scale and diverse training data, teach computers to understand the planet with unprecedented depth. Esri is at the forefront of this transformation, bringing these powerful models into ArcGIS workflows.\r\n<h2>What Foundation Models Are<\/h2>\r\nA foundation model is a large, deep neural network\u2014a type of machine learning that processes complex, nonlinear data to recognize patterns. Foundation models often have billions of parameters and are trained on vast, diverse datasets.\r\n\r\nOnce trained, a foundation model can be adapted to a wide variety of downstream tasks, depending on the data format. For imagery, the tasks include object detection and tracking, along with pixel and feature classification. For natural-language text data, a foundation model can classify, transform, and extract entities from text. For vector, tabular, and time series data, the downstream tasks include prediction\u2014including regression and classification\u2014and forecasting.\r\n<h2>The Building Blocks<\/h2>\r\nThe success of foundation models rests on several key innovations. Transformers\u2014neural network architectures that process sequential data in parallel rather than sequentially\u2014capture relationships in data, scale well, and are now widely adopted across domains beyond text. Autosupervised learning enables models to learn from raw, unlabeled data rather than requiring labeled examples. For imagery, this often involves masked image modeling, where parts of an image are hidden and the model learns to reconstruct them. Scale completes the picture: As a model\u2019s size and dataset volume grow, the model\u2019s predictive accuracy improves.\r\n<h2>Embeddings as Geospatial Data<\/h2>\r\nFoundation models learn to create embeddings, which are numerical representations of words, images, and other data. In geospatial models, embeddings encapsulate the essential properties of each location, such as geographic coordinates and contextual information like environmental factors.\r\n\r\nAlso, embeddings can be stored as feature layers in ArcGIS, where each geographic feature carries its own multidimensional embedding as part of its attributes. Machine learning tools in ArcGIS can use such embedding datasets for clustering; classification; regression; or other analysis tasks, including predicting places where certain things\u2014like species or buildings\u2014might be found."},{"acf_fc_layout":"image","image":772065,"image_position":"center","orientation":"horizontal","hyperlink":""},{"acf_fc_layout":"content","content":"<h2>Remote Sensing Foundation Models in ArcGIS<\/h2>\r\nRemote sensing foundation models are large-scale computer vision models designed to extract insight from satellite and aerial imagery. These models use Vision Transformer architectures that are trained via autosupervised learning on vast collections of satellite imagery. Unlike traditional models trained on everyday photos, these are specifically pretrained on optical, radar, lidar, and multispectral images of Earth\u2019s surface.\r\n\r\nArcGIS integrates several innovative remote sensing foundation models as ready-to-use backbones for geospatial deep learning. These models include Prithvi, Dynamic-One-For-All, and Clay. Esri is also developing its own model, designed to perform effectively across multispectral and high-resolution satellite imagery.\r\n<h2>Location-Embedding Models<\/h2>\r\nLocation-embedding foundation models represent geographic coordinates as high-dimensional feature embeddings. These embeddings encode spatial context, capturing human-environment interactions, natural geography, and socioeconomic patterns. Unlike traditional approaches that treat latitude and longitude as simple numbers, these models learn to represent place, not just position.\r\n\r\nArcGIS integrates location embeddings with its AutoML machine learning tool to enhance regression and classification on vector data. Users access this via the Use Location Embeddings option in the Train Using AutoML tool in ArcGIS Pro. Esri is extending this approach to incorporate high-resolution imagery and curated demographic data.\r\n<h2>The Road Ahead<\/h2>\r\nAs foundation models become central to geospatial science, their integration into ArcGIS marks a major step toward more intelligent, data-driven ways of understanding the world. Users can apply AI-based methods for geospatial analysis via graphical tools in ArcGIS, even if they don\u2019t have specialized programming expertise."},{"acf_fc_layout":"sidebar","layout":"standard","image_reference":null,"image_reference_figure":"","spotlight_image":null,"section_title":"","spotlight_name":"","position":"Center","content":"Learn more about <a href=\"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-pro\/geoai\/use-remote-sensing-foundation-models-with-arcgis?rsource=https%3A%2F%2Flinks.esri.com%2Ffoundation-models\">using foundation models with ArcGIS<\/a>.","snippet":""}],"references":null},"yoast_head":"<!-- This site is optimized with the Yoast SEO Premium plugin v25.9 (Yoast SEO v25.9) - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>GeoAI in the Age of Foundation Models | Spring 2026 | ArcNews<\/title>\n<meta name=\"description\" content=\"The rapid progress of AI has produced a new type of model that promises to revolutionize Earth observation\u2014and Esri is at the forefront.\" \/>\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\/about\/newsroom\/arcnews\/geoai-in-the-age-of-foundation-models\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"GeoAI in the Age of Foundation Models\" \/>\n<meta property=\"og:description\" content=\"The rapid progress of AI has produced a new type of model that promises to revolutionize Earth observation\u2014and Esri is at the forefront.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.esri.com\/about\/newsroom\/arcnews\/geoai-in-the-age-of-foundation-models\" \/>\n<meta property=\"og:site_name\" content=\"Esri\" \/>\n<meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/esrigis\/\" \/>\n<meta property=\"og:image\" content=\"https:\/\/www.esri.com\/about\/newsroom\/app\/uploads\/2026\/03\/arcnews-banner-geoaiinthe-wide.jpg\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:description\" content=\"The rapid progress of AI has produced a new type of model that promises to revolutionize Earth observation\u2014and Esri is at the forefront.\" \/>\n<meta name=\"twitter:site\" content=\"@Esri\" \/>\n<meta name=\"twitter:label1\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data1\" content=\"5 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\n\t    \"@context\": \"https:\/\/schema.org\",\n\t    \"@graph\": [\n\t        {\n\t            \"@type\": \"WebPage\",\n\t            \"@id\": \"https:\/\/www.esri.com\/about\/newsroom\/arcnews\/geoai-in-the-age-of-foundation-models\",\n\t            \"url\": \"https:\/\/www.esri.com\/about\/newsroom\/arcnews\/geoai-in-the-age-of-foundation-models\",\n\t            \"name\": \"GeoAI in the Age of Foundation Models | Spring 2026 | ArcNews\",\n\t            \"isPartOf\": {\n\t                \"@id\": \"https:\/\/www.esri.com\/about\/newsroom\/#website\"\n\t            },\n\t            \"datePublished\": \"2026-04-01T02:59:09+00:00\",\n\t            \"description\": \"The rapid progress of AI has produced a new type of model that promises to revolutionize Earth observation\u2014and Esri is at the forefront.\",\n\t            \"breadcrumb\": {\n\t                \"@id\": \"https:\/\/www.esri.com\/about\/newsroom\/arcnews\/geoai-in-the-age-of-foundation-models#breadcrumb\"\n\t            },\n\t            \"inLanguage\": \"en-US\",\n\t            \"potentialAction\": [\n\t                {\n\t                    \"@type\": \"ReadAction\",\n\t                    \"target\": [\n\t                        \"https:\/\/www.esri.com\/about\/newsroom\/arcnews\/geoai-in-the-age-of-foundation-models\"\n\t                    ]\n\t                }\n\t            ]\n\t        },\n\t        {\n\t            \"@type\": \"BreadcrumbList\",\n\t            \"@id\": \"https:\/\/www.esri.com\/about\/newsroom\/arcnews\/geoai-in-the-age-of-foundation-models#breadcrumb\",\n\t            \"itemListElement\": [\n\t                {\n\t                    \"@type\": \"ListItem\",\n\t                    \"position\": 1,\n\t                    \"name\": \"Home\",\n\t                    \"item\": \"https:\/\/www.esri.com\/about\/newsroom\"\n\t                },\n\t                {\n\t                    \"@type\": \"ListItem\",\n\t                    \"position\": 2,\n\t                    \"name\": \"ArcNews Articles\",\n\t                    \"item\": \"https:\/\/www.esri.com\/about\/newsroom\/arcnews\"\n\t                },\n\t                {\n\t                    \"@type\": \"ListItem\",\n\t                    \"position\": 3,\n\t                    \"name\": \"GeoAI in the Age of Foundation Models\"\n\t                }\n\t            ]\n\t        },\n\t        {\n\t            \"@type\": \"WebSite\",\n\t            \"@id\": \"https:\/\/www.esri.com\/about\/newsroom\/#website\",\n\t            \"url\": \"https:\/\/www.esri.com\/about\/newsroom\/\",\n\t            \"name\": \"Esri\",\n\t            \"description\": \"Esri Newsroom\",\n\t            \"potentialAction\": [\n\t                {\n\t                    \"@type\": \"SearchAction\",\n\t                    \"target\": {\n\t                        \"@type\": \"EntryPoint\",\n\t                        \"urlTemplate\": \"https:\/\/www.esri.com\/about\/newsroom\/?s={search_term_string}\"\n\t                    },\n\t                    \"query-input\": {\n\t                        \"@type\": \"PropertyValueSpecification\",\n\t                        \"valueRequired\": true,\n\t                        \"valueName\": \"search_term_string\"\n\t                    }\n\t                }\n\t            ],\n\t            \"inLanguage\": \"en-US\"\n\t        },\n\t        {\n\t            \"@type\": \"Person\",\n\t            \"@id\": \"https:\/\/www.esri.com\/about\/newsroom\/#\/schema\/person\/2ea2e24ff1bf1335829717357eaf3b3a\",\n\t            \"name\": \"Lidia Davidson\",\n\t            \"image\": {\n\t                \"@type\": \"ImageObject\",\n\t                \"inLanguage\": \"en-US\",\n\t                \"@id\": \"https:\/\/www.esri.com\/about\/newsroom\/#\/schema\/person\/image\/\",\n\t                \"url\": \"https:\/\/secure.gravatar.com\/avatar\/69fae831c26e7d10c2c6cdaff1c8c9f2e148d083fe79f851e5ad201f7793fad5?s=96&d=blank&r=g\",\n\t                \"contentUrl\": \"https:\/\/secure.gravatar.com\/avatar\/69fae831c26e7d10c2c6cdaff1c8c9f2e148d083fe79f851e5ad201f7793fad5?s=96&d=blank&r=g\",\n\t                \"caption\": \"Lidia Davidson\"\n\t            },\n\t            \"url\": \"\"\n\t        }\n\t    ]\n\t}<\/script>\n<!-- \/ Yoast SEO Premium plugin. -->","yoast_head_json":{"title":"GeoAI in the Age of Foundation Models | Spring 2026 | ArcNews","description":"The rapid progress of AI has produced a new type of model that promises to revolutionize Earth observation\u2014and Esri is at the forefront.","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\/about\/newsroom\/arcnews\/geoai-in-the-age-of-foundation-models","og_locale":"en_US","og_type":"article","og_title":"GeoAI in the Age of Foundation Models","og_description":"The rapid progress of AI has produced a new type of model that promises to revolutionize Earth observation\u2014and Esri is at the forefront.","og_url":"https:\/\/www.esri.com\/about\/newsroom\/arcnews\/geoai-in-the-age-of-foundation-models","og_site_name":"Esri","article_publisher":"https:\/\/www.facebook.com\/esrigis\/","og_image":[{"url":"https:\/\/www.esri.com\/about\/newsroom\/app\/uploads\/2026\/03\/arcnews-banner-geoaiinthe-wide.jpg","type":"","width":"","height":""}],"twitter_card":"summary_large_image","twitter_description":"The rapid progress of AI has produced a new type of model that promises to revolutionize Earth observation\u2014and Esri is at the forefront.","twitter_site":"@Esri","twitter_misc":{"Est. reading time":"5 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/www.esri.com\/about\/newsroom\/arcnews\/geoai-in-the-age-of-foundation-models","url":"https:\/\/www.esri.com\/about\/newsroom\/arcnews\/geoai-in-the-age-of-foundation-models","name":"GeoAI in the Age of Foundation Models | Spring 2026 | ArcNews","isPartOf":{"@id":"https:\/\/www.esri.com\/about\/newsroom\/#website"},"datePublished":"2026-04-01T02:59:09+00:00","description":"The rapid progress of AI has produced a new type of model that promises to revolutionize Earth observation\u2014and Esri is at the forefront.","breadcrumb":{"@id":"https:\/\/www.esri.com\/about\/newsroom\/arcnews\/geoai-in-the-age-of-foundation-models#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.esri.com\/about\/newsroom\/arcnews\/geoai-in-the-age-of-foundation-models"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/www.esri.com\/about\/newsroom\/arcnews\/geoai-in-the-age-of-foundation-models#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.esri.com\/about\/newsroom"},{"@type":"ListItem","position":2,"name":"ArcNews Articles","item":"https:\/\/www.esri.com\/about\/newsroom\/arcnews"},{"@type":"ListItem","position":3,"name":"GeoAI in the Age of Foundation Models"}]},{"@type":"WebSite","@id":"https:\/\/www.esri.com\/about\/newsroom\/#website","url":"https:\/\/www.esri.com\/about\/newsroom\/","name":"Esri","description":"Esri Newsroom","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.esri.com\/about\/newsroom\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Person","@id":"https:\/\/www.esri.com\/about\/newsroom\/#\/schema\/person\/2ea2e24ff1bf1335829717357eaf3b3a","name":"Lidia Davidson","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.esri.com\/about\/newsroom\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/69fae831c26e7d10c2c6cdaff1c8c9f2e148d083fe79f851e5ad201f7793fad5?s=96&d=blank&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/69fae831c26e7d10c2c6cdaff1c8c9f2e148d083fe79f851e5ad201f7793fad5?s=96&d=blank&r=g","caption":"Lidia Davidson"},"url":""}]}},"sort_order":"6","_links":{"self":[{"href":"https:\/\/www.esri.com\/about\/newsroom\/wp-json\/wp\/v2\/arcnews\/772063","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.esri.com\/about\/newsroom\/wp-json\/wp\/v2\/arcnews"}],"about":[{"href":"https:\/\/www.esri.com\/about\/newsroom\/wp-json\/wp\/v2\/types\/arcnews"}],"author":[{"embeddable":true,"href":"https:\/\/www.esri.com\/about\/newsroom\/wp-json\/wp\/v2\/users\/6921"}],"version-history":[{"count":0,"href":"https:\/\/www.esri.com\/about\/newsroom\/wp-json\/wp\/v2\/arcnews\/772063\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.esri.com\/about\/newsroom\/wp-json\/wp\/v2\/media?parent=772063"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.esri.com\/about\/newsroom\/wp-json\/wp\/v2\/categories?post=772063"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.esri.com\/about\/newsroom\/wp-json\/wp\/v2\/tags?post=772063"},{"taxonomy":"arcnews_issues","embeddable":true,"href":"https:\/\/www.esri.com\/about\/newsroom\/wp-json\/wp\/v2\/arcnews_issues?post=772063"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}