N-Tree Diffusion for Long-Horizon Wildfire Risk Forecasting
This work provides an improved method for long-horizon probabilistic wildfire risk forecasting, which is crucial for environmental management and disaster preparedness.
This paper addresses long-horizon wildfire risk forecasting by generating probabilistic spatial fields. The proposed N-Tree Diffusion model shares early denoising stages and branches later for horizon-specific refinement, leading to consistent accuracy improvements and reduced inference cost compared to baseline forecasting approaches.
Long-horizon wildfire risk forecasting requires generating probabilistic spatial fields under sparse event supervision while maintaining computational efficiency across multiple prediction horizons. Extending diffusion models to multi-step forecasting typically repeats the denoising process independently for each horizon, leading to redundant computation. We introduce N-Tree Diffusion (NT-Diffusion), a hierarchical diffusion model designed for long-horizon wildfire risk forecasting. Fire occurrences are represented as continuous Fire Risk Maps (FRMs), which provide a smoothed spatial risk field suitable for probabilistic modeling. Instead of running separate diffusion trajectories for each predicted timestamp, NT-Diffusion shares early denoising stages and branches at later levels, allowing horizon-specific refinement while reducing redundant sampling. We evaluate the proposed framework on a newly collected real-world wildfire dataset constructed for long-horizon probabilistic prediction. Results indicate that NT-Diffusion achieves consistent accuracy improvements and reduced inference cost compared to baseline forecasting approaches.