Boundary-Aware Uncertainty Quantification for Wildfire Spread Prediction

ArXi:2605.03148v1 Announce Type: new Reliable wildfire spread prediction is vital for risk-aware emergency planning, yet most deep learning models lack principled uncertainty quantification (UQ). Further, for boundary-sensitive cases like wildfire spread, evaluating models with global metrics alone is often insufficient. To shift the focus of UQ evaluation toward a operationally relevant approach, the Fire-Centered Evaluation Region (FCER) framework is