N-Tree Diffusion for Long-Horizon Wildfire Risk Forecasting
Fuente:
arXiv
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917322036346880 |
|---|---|
| author | Xing, Yucheng Wang, Xin |
| author_facet | Xing, Yucheng Wang, Xin |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_07361 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | N-Tree Diffusion for Long-Horizon Wildfire Risk Forecasting Xing, Yucheng Wang, Xin Machine Learning Computer Vision and Pattern Recognition 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. |
| title | N-Tree Diffusion for Long-Horizon Wildfire Risk Forecasting |
| topic | Machine Learning Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.07361 |