FireGraphNet: Sub-daily wildfire spread prediction with directed graph neural networks
Not on the map. Why?
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.
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
26 of 69 references.
References · 26
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
- 2017Graph Attention Networkscited by 8,923
- 2017Inductive Representation Learning on Large Graphscited by 6,320
- 2018How Powerful are Graph Neural Networks?cited by 4,393
- 2019Optuna: A Next-generation Hyperparameter Optimization Frameworkcited by 2,501
- 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,434
- 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,333
- 2019Strategies for Pre-training Graph Neural Networkscited by 971
- 2021How Attentive are Graph Attention Networks?cited by 835
- 2020Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classificationcited by 506
- 2023Mesogeos: A multi-purpose dataset for data-driven wildfire modeling in the Mediterraneancited by 19
14 more
- 2021A Spatial-temporal Graph Deep Learning Model for Urban Flood Nowcasting Leveraging Heterogeneous Community Featurescited by 13
- 2025A Probabilistic Approach to Wildfire Spread Prediction Using a Denoising Diffusion Surrogate Modelcited by 11
- 2021Spatio-Temporal Graph Convolutional Networks for Road Network Inundation Status Prediction during Urban Floodingcited by 9
- 2025Improved Wildfire Spread Prediction with Time-Series Data and the WSTS+ Benchmarkcited by 8
- 2024Recommendations for Comprehensive and Independent Evaluation of Machine Learning-Based Earth System Modelscited by 6
- 2025Automated Wildfire Damage Assessment from Multi view Ground level Imagery Via Vision Language Modelscited by 4
- 2023Reinforcement Learning for Wildfire Mitigation in Simulated Disaster Environmentscited by 3
- 2026Conformal Risk Control for Safety-Critical Wildfire Evacuation Mapping: A Comparative Study of Tabular, Spatial, and Graph-Based Modelscited by 3
- 2026FireSenseNet: A Dual-Branch CNN with Cross-Attentive Feature Interaction for Next-Day Wildfire Spread Predictioncited by 3
- 2025Spatial Uncertainty Quantification in Wildfire Forecasting for Climate-Resilient Emergency Planningcited by 2
- 2025Assessment of deep learning models integrated with weather and environmental variables for wildfire spread prediction and a case study of the 2023 Maui firescited by 1
- 2026Set Prediction for Next-Day Active Fire Forecastingcited by 1
- 2026Modular Deep Learning Mechanisms for Auditable Next-Day Wildfire Spread Predictioncited by 1
- 2026WildfireSpreadBench: The Metric Decides the Model in Wildfire Spread Predictioncited by 1
Built on by
Not cited yet.