# N-Tree Diffusion for Long-Horizon Wildfire Risk Forecasting

arXiv: https://arxiv.org/abs/2603.07361 · HTML: https://mlsanity.com/paper/2603.07361/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Flow matching, time series and science, one of 14 directions in Diffusion models.
- Builds on 27 of its 73 references that are in the map.
- First posted on arXiv 7 Mar 2026.

## Placed in

- Diffusion models / [Flow matching, time series and science](https://mlsanity.com/diffusion/flow-matching-time-series-and-science/)

## Builds on (most cited first, 27 of 27)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [Video Diffusion Models](https://mlsanity.com/paper/2204.03458/) (2022)
- [MoCoGAN: Decomposing Motion and Content for Video Generation](https://mlsanity.com/paper/1707.04993/) (2017)
- [Generating Videos with Scene Dynamics](https://mlsanity.com/paper/1609.02612/) (2016)
- [Photorealistic Video Generation with Diffusion Models](https://mlsanity.com/paper/2312.06662/) (2023)
- [Temporal Generative Adversarial Nets with Singular Value Clipping](https://mlsanity.com/paper/1611.06624/) (2016)
- [Latent Image Animator: Learning to Animate Images via Latent Space Navigation](https://mlsanity.com/paper/2203.09043/) (2022)
- [Video Probabilistic Diffusion Models in Projected Latent Space](https://mlsanity.com/paper/2302.07685/) (2023)
- [Unsupervised Learning of Disentangled Representations from Video](https://mlsanity.com/paper/1705.10915/) (2017)
- [Disentangled Sequential Autoencoder](https://mlsanity.com/paper/1803.02991/) (2018)
- [Generating Long Videos of Dynamic Scenes](https://mlsanity.com/paper/2206.03429/) (2022)
- [VDT: General-purpose Video Diffusion Transformers via Mask Modeling](https://mlsanity.com/paper/2305.13311/) (2023)
- [VIDM: Video Implicit Diffusion Models](https://mlsanity.com/paper/2212.00235/) (2022)
- [A review of machine learning applications in wildfire science and management](https://mlsanity.com/paper/2003.00646/) (2020)
- [LEO: Generative Latent Image Animator for Human Video Synthesis](https://mlsanity.com/paper/2305.03989/) (2023)
- [Deep Learning Models for Predicting Wildfires from Historical Remote-Sensing Data](https://mlsanity.com/paper/2010.07445/) (2020)
- [Motion-Based Generator Model: Unsupervised Disentanglement of Appearance, Trackable and Intrackable Motions in Dynamic Patterns](https://mlsanity.com/paper/1911.11294/) (2019)
- [GD-VDM: Generated Depth for better Diffusion-based Video Generation](https://mlsanity.com/paper/2306.11173/) (2023)
- [Convolutional LSTM Neural Networks for Modeling Wildland Fire Dynamics](https://mlsanity.com/paper/2012.06679/) (2020)
- [FireSentry: A Multi-Modal Spatio-temporal Benchmark Dataset for Fine-Grained Wildfire Spread Forecasting](https://mlsanity.com/paper/2512.03369/) (2025)
- [Learning Wildfire Model from Incomplete State Observations](https://mlsanity.com/paper/2111.14038/) (2021)
- [Deep learning surrogate models of JULES-INFERNO for wildfire prediction on a global scale](https://mlsanity.com/paper/2409.00237/) (2024)

## Abstract (arXiv)

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.