UWF’s Derek Morgan was part of a team that introduced a new benchmark dataset and evaluation of AI methods that could improve how wildfire damage is mapped and monitored. The new CalFireSeg-50 dataset was built from satellite imagery and data from 50 of California’s largest wildfires between 2019 and 2023.
This benchmark can help models identify where fires burn the hottest, helping emergency responders understand how wildfires spread and quickly pinpoint high-priority zones. The datasets and detailed maps of wildfire damage could also support other work, such as tracking vegetation recovery after a wildfire.
View Related Expert Profiles: Go to Source