{"id":2655222,"date":"2026-01-28T15:29:34","date_gmt":"2026-01-28T23:29:34","guid":{"rendered":"https:\/\/www.esri.com\/arcgis-blog\/?post_type=blog&p=2655222"},"modified":"2026-03-04T13:24:02","modified_gmt":"2026-03-04T21:24:02","slug":"learn-to-map-oil-spills-with-sentinel1","status":"publish","type":"blog","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/arcgis-living-atlas\/imagery\/learn-to-map-oil-spills-with-sentinel1","title":{"rendered":"Learn to map oil spills with Sentinel-1 imagery and GeoAI"},"author":341062,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"open","ping_status":"closed","template":"","format":"standard","meta":{"_acf_changed":false,"_searchwp_excluded":""},"categories":[22931],"tags":[186132,780072,762292,758071,771012],"industry":[],"product":[36581,36551],"class_list":["post-2655222","blog","type-blog","status-publish","format-standard","hentry","category-imagery","tag-deep-learning","tag-lawrasteranalysis","tag-oil","tag-sar","tag-sentinel-1","product-arcgis-living-atlas","product-arcgis-online"],"acf":{"authors":[{"ID":341062,"user_firstname":"Samira","user_lastname":"Daneshgar Asl","nickname":"Samira Daneshgar Asl","user_nicename":"sdaneshgar","display_name":"Samira Daneshgar Asl","user_email":"sdaneshgar@esri.com","user_url":"","user_registered":"2023-06-21 20:18:16","user_description":"Samira is a senior product engineer for imagery analytics on the ArcGIS Living Atlas team at Esri, where she combines her passion for AI and remote sensing, to advance the Science of Where. With a PhD in oceanography from Florida State University and postdoctoral experience at UC Santa Barbara, she specializes in synthetic aperture radar (SAR) imagery analysis. Her work tackles environmental challenges, including modeling oil slick dynamics and using deep learning to map supraglacial rivers on Greenland\u2019s Ice Sheet.","user_avatar":""}],"short_description":"Identify an oil slick with radar satellite imagery from ArcGIS Living Atlas of the World and a pretrained deep learning model.","flexible_content":[{"acf_fc_layout":"content","content":"

Oil spills from ships, tanker accidents, and offshore platforms have been a global concern for marine ecosystems, coastal communities, and fisheries. Early identification of oil spills is essential for guiding effective response efforts, minimizing environmental damage, and reducing economic losses.<\/p>\n

The Taylor Energy oil spill<\/a>, which continued from 2004 to 2019, is the longest-running oil spill in United States history. The spill was caused by the destruction of the Taylor Energy platform about 15 kilometers off the shore of South Pass, Louisiana, during Hurricane Ivan. It resulted in thin layers of floating oil, called oil slicks, and significantly contributed to oil pollution in the region.<\/p>\n

As an image analyst working for an environmental agency, your objective is to efficiently extract an oil slick from a Synthetic Aperture Radar (SAR) satellite image and show the extent of the oil pollution. Manual oil slick detection in satellite imagery can be costly, time consuming, and relies upon an experienced analyst to correctly identify the targets. In this blog tutorial, you’ll detect the oil slick in a more automated fashion using a deep learning model. Over the course of approximately 50 minutes, you\u2019ll create a web map containing Sentinel-1 RTC dynamic imagery available through ArcGIS Living Atlas of the World, preprocess your imagery of interest, and apply a pretrained deep learning model to it to extract the oil slick.<\/p>\n"},{"acf_fc_layout":"content","content":"

\"\"<\/h3>\n

Table of Contents<\/strong><\/h3>\n