Fire‐EnSF: Data Assimilation for Wildfire Spread Models Using Ensemble Score Filter

Abstract

As wildfires become increasingly destructive and expensive to control, effective management of active wildfires requires accurate and real‐time fire spread predictions. To enhance the forecasting accuracy of active fires, data assimilation plays a vital role by integrating observations (such as remote‐sensing data) and fire predictions generated from numerical models. This paper provides a comprehensive investigation of a diffusion‐model‐based filtering algorithm—the ensemble score filter (EnSF)—to the data assimilation problem for real‐time active wildfire spread predictions. Leveraging a score‐based generative diffusion model, EnSF has been shown to achieve superior accuracy on high‐dimensional and nonlinear filtering problems, making it a potentially ideal candidate for wildfire spread modeling. Technical details are provided, and our numerical investigations demonstrate that EnSF provides superior accuracy, stability, and computational efficiency, establishing it as a robust and practical method for wildfire data assimilation. Code has been made publicly available.