CGI IT UK LIMITED (GB)
The Artificial Intelligence for Earth Observation (AI4EO) Wildfires project began in December 2020 and run for 8 months, focussing on developing and demonstrating a burned area (BA) mapping service that combines EO data, specifically Sentinel-2 optical data, with an AI-enabled algorithm.
The project consortium is led by CGI UK, utilising their legacy of developing cloud-based EO-data processing portals, with project partner University of Leicester (UK) who has been involved in a number of projects focused on wildfire mapping including the European Space Agency (ESA) CCI Fire project.
The AI4EO project and demonstration service has shown the potential of combining increasingly frequent and high-resolution satellite observations with AI/ML to provide improved BA mapping products to support wildfire management organisations.
ML enables the service to be easily trained using real wildfire events over a range of differing biomes and scenarios to create a collection of mapping solutions. When executed, the demonstration service automatically selects the most relevant mapping solution to the scene, allowing the creation of a simple, easy to interpret, map of Burned Areas. The service is deployed on a cloud-based online processing platform, the EO4SD Lab. It provides useRs with a robust scalable service that creates Burned Area maps, which can be easily analysed and ingested into the user’s established systems.