N-Tree Diffusion for Long-Horizon Wildfire Risk Forecasting

TL;DR

This paper introduces N-Tree Diffusion, a hierarchical probabilistic model that efficiently forecasts long-term wildfire risk by sharing computation across multiple prediction horizons, improving accuracy and reducing inference costs.

Contribution

The paper presents N-Tree Diffusion, a novel hierarchical diffusion model that enables efficient multi-horizon wildfire risk forecasting by sharing early denoising stages.

Findings

Achieves higher accuracy than baseline models.

Reduces inference cost significantly.

Demonstrates effectiveness on real-world wildfire data.

Abstract

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.