Predicting spatio-temporal wildfire propagation with dynamic firebreaks

Zheng, J., Xu, Z., Arcucci, R., Harrison, S. P. ORCID: https://orcid.org/0000-0001-5687-1903, Xu, L. L. and Cheng, S. (2026) Predicting spatio-temporal wildfire propagation with dynamic firebreaks. Natural Hazards and Earth System Science, 26 (6). pp. 2871-2895. ISSN 1684-9981 doi: 10.5194/nhess-26-2871-2026

Abstract/Summary

Wildfire management strategies increasingly demand accurate predictive models that integrate real-time intervention measures. Despite advances in machine learning (ML) for wildfire modelling, existing approaches largely overlook the role of firebreak placement. In this work, we present the first deep learning-based predictive model for simulating spatio-temporal wildfire propagation with dynamic firebreaks. Utilizing a Convolutional Long Short-Term Memory (ConvLSTM) architecture, the model captures both the spatial and temporal complexities of wildfire spread while incorporating data on firebreak positioning and effectiveness. Our training dataset, derived from Cellular Automata (CA) simulations, integrates key geophysical parameters and human intervention strategies, including temporary and permanent firebreaks. Model validation across three major wildfire events in California demonstrates robust performance, with significant accuracy gains in scenarios involving strategic firebreak placement. This integration of movable firebreak placement into a wildfire spread model provides a tool for improving real-time wildfire management efforts.

Item Type	Article
URI	https://centaur.reading.ac.uk/id/eprint/130675
Identification Number/DOI	10.5194/nhess-26-2871-2026
Refereed	Yes
Divisions	Science > School of Archaeology, Geography and Environmental Science > Department of Geography and Environmental Science
Publisher	European Geosciences Union
Download/View statistics	View download statistics for this item