2026/06/10 by Maksym Zhenirovskyy, Ion Matei, Rohit Vuppala +3
Computer Science · Engineering · #Artificial life #Automaton #Cellular Automata and Applications #Cellular automaton #Evacuation and Crowd Dynamics #Field (mathematics) #Neural Networks Stability and Synchronization
paper · pdf · open access · doi:10.1016/j.ecoinf.2026.103928
published in Ecological Informatics 97, 103928 (Elsevier BV)
openalex publication_date 2026/07/18 · openalex created_date 2026/07/19 · openalex updated_date 2026/08/05
Traditional wildfire models rely on rigid, low-dimensional parameters and static fuel maps, frequently underpredicting fire spread. To address this weakness, we introduce a hybrid deep-learning parameterized Probabilistic Cellular Automata (CA) framework implemented in JAX. Our approach employs a Multi-Scale Convolutional Neural Network to dynamically generate spatially varying parameters that govern fire-spread probability, wind alignment, and slope influence. This hybrid design captures complex, nonlinear environmental interactions while preserving the physical interpretability of the underlying three-state CA. The JAX implementation enables hardware acceleration and gradient-based parameter calibration. Evaluated on six large-scale wildfires in the western United States, the model maintains I o U > 0.6 over 72-hour forecast horizons after a 10-day data assimilation window during which the model is fitted incrementally to observed perimeters; the resulting forecast is a conditional projection of fire growth under the suppression regime already encoded in those observations.