AI RESEARCH
Set Prediction for Next-Day Active Fire Forecasting
arXiv CS.LG
•
ArXi:2605.10298v1 Announce Type: new Accurate next-day active fire forecasts can early warning, disaster response, forest risk assessment, and downstream estimation of fire-related carbon emissions. Existing machine learning approaches to wildfire forecasting typically predict wildfire danger or fire probability on kilometre-scale daily grids, which is useful for regional warning but does not directly represent localized fire events. We propose Wildfire Ignition Set Predictor (WISP), a query-based model that reformulates next-day active fire forecasting as point-set prediction.