# FireGraphNet: Sub-daily wildfire spread prediction with directed graph neural networks

arXiv: https://arxiv.org/abs/2610.19191 · HTML: https://mlsanity.com/paper/2610.19191/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 69 references that are in the map.
- First posted on arXiv 13 Oct 2026.

## Builds on (most cited first, 26 of 26)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Optuna: A Next-generation Hyperparameter Optimization Framework](https://mlsanity.com/paper/1907.10902/) (2019)
- [Fast Graph Representation Learning with PyTorch Geometric](https://mlsanity.com/paper/1903.02428/) (2019)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [Strategies for Pre-training Graph Neural Networks](https://mlsanity.com/paper/1905.12265/) (2019)
- [How Attentive are Graph Attention Networks?](https://mlsanity.com/paper/2105.14491/) (2021)
- [Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classification](https://mlsanity.com/paper/2009.03509/) (2020)
- [Mesogeos: A multi-purpose dataset for data-driven wildfire modeling in the Mediterranean](https://mlsanity.com/paper/2306.05144/) (2023)
- [A Spatial-temporal Graph Deep Learning Model for Urban Flood Nowcasting Leveraging Heterogeneous Community Features](https://mlsanity.com/paper/2111.08450/) (2021)
- [A Probabilistic Approach to Wildfire Spread Prediction Using a Denoising Diffusion Surrogate Model](https://mlsanity.com/paper/2507.00761/) (2025)
- [Spatio-Temporal Graph Convolutional Networks for Road Network Inundation Status Prediction during Urban Flooding](https://mlsanity.com/paper/2104.02276/) (2021)
- [Improved Wildfire Spread Prediction with Time-Series Data and the WSTS+ Benchmark](https://mlsanity.com/paper/2502.12003/) (2025)
- [Recommendations for Comprehensive and Independent Evaluation of Machine Learning-Based Earth System Models](https://mlsanity.com/paper/2410.19882/) (2024)
- [Automated Wildfire Damage Assessment from Multi view Ground level Imagery Via Vision Language Models](https://mlsanity.com/paper/2509.01895/) (2025)
- [Reinforcement Learning for Wildfire Mitigation in Simulated Disaster Environments](https://mlsanity.com/paper/2311.15925/) (2023)
- [Conformal Risk Control for Safety-Critical Wildfire Evacuation Mapping: A Comparative Study of Tabular, Spatial, and Graph-Based Models](https://mlsanity.com/paper/2603.22331/) (2026)
- [FireSenseNet: A Dual-Branch CNN with Cross-Attentive Feature Interaction for Next-Day Wildfire Spread Prediction](https://mlsanity.com/paper/2604.07675/) (2026)
- [Spatial Uncertainty Quantification in Wildfire Forecasting for Climate-Resilient Emergency Planning](https://mlsanity.com/paper/2510.09666/) (2025)
- [Assessment of deep learning models integrated with weather and environmental variables for wildfire spread prediction and a case study of the 2023 Maui fires](https://mlsanity.com/paper/2509.21327/) (2025)
- [Set Prediction for Next-Day Active Fire Forecasting](https://mlsanity.com/paper/2605.10298/) (2026)
- [Modular Deep Learning Mechanisms for Auditable Next-Day Wildfire Spread Prediction](https://mlsanity.com/paper/2609.17763/) (2026)
- [WildfireSpreadBench: The Metric Decides the Model in Wildfire Spread Prediction](https://mlsanity.com/paper/2609.22191/) (2026)

## Abstract (arXiv)

Wildfire decisions are made in hours, yet most learned spread models predict daily on targets including burned area. We propose FireGraphNet which formulates 12-hour growth as node classification on directed H3 graphs, with candidates ahead of the front and wind alignment, terrain, fuel continuity and barriers on edges. On satellite perimeters it achieves average precision 1.7-1.9x the strongest distance baseline on test California fires and 1.62x out of state. We show this skill comes from message passing rather than cell features or the aggregator, is highest on young fires in state, is carried deep along the wind by its edges, and is hidden by pooling. A convolutional network matches this ranking once trained on new growth, at worse calibration, so candidate construction, target definition, and aggregation shape conclusions about model skill. Editing fuel and barrier attributes reduces predicted spread more under guided than random placement, extending FireGraphNet to operational intervention analysis.