Random Forest-Informed Cellular Automaton for Large-Scale Wildfire Spread Modelling
Abstract
Accurate large-scale wildfire spread modelling requires models that capture both the environmental conditions associated with fire occurrence and the local dynamics of fire propagation. We propose a three-stage framework that combines a Random Forest (RF) model with a cellular automaton (CA). First, an RF model trained on the 2021 Canadian fire season estimates daily pixel-level fire-occurrence probabilities. Second, quantile gradient boosting models provide optional spread-rate priors for sensitivity analysis. Third, an RF-informed CA combines the RF probability layer with neighbourhood-driven spread on a 5 km grid. The RF model achieved AUC values of 0.725--0.795 on the 2022--2024 datasets, while the RF-informed CA achieved substantially higher spatial overlap than the evaluated CA-only baselines in the 2023 simulation. A higher-resolution simulation provides an additional qualitative assessment of local spatial errors. These results suggest that combining RF-derived probabilities with local CA spread can improve large-scale wildfire simulations under the tested conditions.
Related
- Explicit Solutions in a Probabilistic Cellular Automaton Model for Self-Assembled Monolayer Degradation
- A conservative micro-continuum-cellular automaton method for multispecies biofilm dynamics in complex flows
- Random Cellular Automata and deBruijn Graphs
- Continuous logistic Gaussian random measure fields for spatial distributional modelling
- Physics-informed random neural architectures on compact boundaryless multiply connected manifolds for random-operator models in machine learning and uncertainty quantification
BibTeX
@misc{chen2026random,
title = {{Random Forest-Informed Cellular Automaton for Large-Scale Wildfire Spread Modelling}},
author = {Siyu Chen and Esha Saha and Hao Wang},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.01675},
eprint = {2609.01675},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.01675},
}
RIS
TY - UNPB
TI - Random Forest-Informed Cellular Automaton for Large-Scale Wildfire Spread Modelling
AU - Siyu Chen
AU - Esha Saha
AU - Hao Wang
PY - 2026
DA - 2026/09/01
PB - arXiv
DO - 10.48550/arxiv.2609.01675
UR - https://arxiv.org/abs/2609.01675
AB - Accurate large-scale wildfire spread modelling requires models that capture both the environmental conditions associated with fire occurrence and the local dynamics of fire propagation. We propose a three-stage framework that combines a Random Forest (RF) model with a cellular automaton (CA). First, an RF model trained on the 2021 Canadian fire season estimates daily pixel-level fire-occurrence probabilities. Second, quantile gradient boosting models provide optional spread-rate priors for sensitivity analysis. Third, an RF-informed CA combines the RF probability layer with neighbourhood-driven spread on a 5 km grid. The RF model achieved AUC values of 0.725--0.795 on the 2022--2024 datasets, while the RF-informed CA achieved substantially higher spatial overlap than the evaluated CA-only baselines in the 2023 simulation. A higher-resolution simulation provides an additional qualitative assessment of local spatial errors. These results suggest that combining RF-derived probabilities with local CA spread can improve large-scale wildfire simulations under the tested conditions.
ER -