Saturday, February 03, 2024

Using AI to Detect Oil Spills

SkyTruth's Cerulean is a global monitoring system which uses AI to detect oil slick pollution in satellite imagery. It also identifies nearby vessels which might have been responsible for the pollution. The Cerulean interactive map identifies the locations of possible oil slicks that might go unnoticed by traditional methods, hopefully leading to faster response and cleanup efforts.

Cerulean uses a machine learning model which has been trained on a massive dataset of satellite images in order to identify potential oil slicks. This model continuously learns and improves its accuracy over time. However Cerulean doesn't just stop once a potential oil slick has been detected. It then analyzes AIS data to identify vessels that were in the vicinity of the slick when it was detected. 

Cerulean joins a growing arsenal of tools developed by SkyTruth in order to help protect marine environments. For example Global Fishing Watch (founded by Oceana, SkyTruth and Google) uses AIS data and satellite imagery to track the activities of fishing vessels across the world in real-time. Authorities around the world can use the Global Fishing Watch map in order to detect illegal fishing and to cross-check information reported by vessel operators.

SkyTruth's Flaring Map visualizes daily infrared detections of oil wells around the world burning off excess gas. The SkyTruth Flaring Map uses data detected by NOAA’s Suomi NPP satellite. The map is updated daily to show all infrared detections hot enough to be gas flares. The map then animates through these nightly detections of global flaring.

Hat-tip: Webcurios

No comments: