arXiv AI

Wildfire Suppression: Complexity, Models, and Instances

The paper investigates how to allocate wildfire suppression resources over time on a graph-based landscape model. It proves the problem and two variants are strongly NP-complete on planar graphs and weighted directed grids, and remains hard even when all resources are released simultaneously. The authors introduce a new mixed-integer programming formulation that outperforms previous methods, and present a physics‑grounded instance generator based on Rothermel's model to benchmark algorithms on realistic scenarios.

arXiv Machine Learning
4d ago

Aerial Wildfire Suppression Planning with a Hybrid CNN-Cellular Automata Fire Model

The paper introduces a hybrid CNN‑cellular automaton (CNN‑CA) simulator for planning aerial wildfire suppression, trained on six historical fires. It jointly optimizes binary drop decisions and continuous aircraft trajectories while accounting for aircraft constraints, wind drift, and fuel reduction effects of water and retardant. The authors evaluate the method against random, tactical, greedy, and derivative‑free planners, showing significant reductions in simulated fire extent under a 2020 Bear Fire case study, though noting the results are conditional on the frozen simulator and not operational evidence.

By Ion Matei, Maksym Zhenirovskyy, Takuya Kurihana, Rohit Vupala, Anthony Wong
arXiv AI
2d ago

Interpretable Patch-Based Deep Learning for Wildfire Spread Prediction from Ensemble Simulations

The study evaluates deep learning surrogates for wildfire spread prediction, training four architectures on 10,584 high‑resolution simulations from Catalonia. Results show that only surface fuel load significantly predicts burn probability, and convolutional models mainly use distance to the fire front while a transformer model emphasizes fuel and terrain. When applied to a new region without retraining, the models still perform reasonably, with only a modest accuracy drop.

By Marcin Lawenda, Aleksandra Krasicka, David Caballero, Luis Torres, {\L}ukasz Szustak
arXiv AI
Aug 6

Risk Is Not the Target: A Monotonic Framework for Evaluating Wildfire Operational Risk Signals

arXiv:2607. 21597v2 Announce Type: replace Abstract: Evaluating wildfire risk systems using standard machine-learning metrics such as F1-score or IoU is fundamentally flawed: these metrics assess event prediction accuracy, not the operational coherence of a continuous risk signal.

By Nicolas Caron, Christophe Guyeux, Hassan Noura, Maxime Coulmeau, Benjamin Aynes
arXiv Machine Learning
Jun 8

The Proxy Benders Decomposition

arXiv:2606. 07403v1 Announce Type: cross Abstract: Benders decomposition is a fundamental framework for solving large-scale mixed-integer optimization problems with complicating variables that, when fixed, yield significantly easier subproblems.

By Changkun Guan, El Mehdi Er Raqabi, Mathieu Tanneau, Pascal Van Hentenryck
arXiv Machine Learning
Sep 3

Random Forest-Informed Cellular Automaton for Large-Scale Wildfire Spread Modelling

The paper presents a three‑stage framework that merges a Random Forest (RF) model with a cellular automaton (CA) to model large‑scale wildfire spread. First, an RF trained on the 2021 Canadian fire season predicts daily pixel‑level fire‑occurrence probabilities. Second, optional spread‑rate priors are supplied by quantile gradient boosting models for sensitivity analysis. Third, an RF‑informed CA integrates the RF probability layer with neighbourhood‑driven spread on a 5 km grid, achieving higher spatial overlap than CA‑only baselines in 2023 simulations and demonstrating improved performance on 2022–2024 datasets (AUC 0.725–0.795).

By Siyu Chen, Esha Saha, Hao Wang
arXiv Computer Vision
3d ago

Multisource Remote Sensing and Geospatial Analysis of Vineyard Wildfire Impacts and Resilience: The 2019 Kincade Fire

The study analyzes vineyard resilience to the 2019 Kincade Fire in Sonoma County using a comprehensive geospatial framework that includes Sentinel‑2 imagery, weather data, soil and terrain models, and smoke polygons. It finds that vineyard fields experienced lower immediate spectral damage (dNBR) than surrounding wildland vegetation, yet this advantage does not translate into a universal firebreak effect; conditional models reveal a positive association between vineyard fraction and dNBR after accounting for location, terrain, and water use. Additionally, all vineyards were exposed to smoke, a significant portion of road nodes became dead ends, and vineyards inside the fire perimeter showed a slightly larger greenness deficit through 2021, indicating incomplete resilience. whyItMatters":"The findings demonstrate that lower spectral impact does not guarantee full resilience, highlighting the need for nuanced, data‑driven decision support in managing agricultural landscapes during wildfires."

By Parastoo Farajpoor, Mahla Ardebili Pour, Mohammad Bagher Ghiasi, Mohammadreza Narimani
arXiv Machine Learning
3d ago

A Sentinel-2 benchmark dataset for deep-learning active-fire segmentation across 25 California wildfires

The article introduces an open image dataset for active‑fire segmentation in satellite imagery, comprising 2,148 image‑mask pairs from 25 California wildfires captured between July 2020 and August 2026. Each 512×512 pixel, three‑channel image is a Sentinel‑2 Level‑2A composite of bands B12, B11, and B8A, with a fixed linear rendering applied uniformly. Masks distinguish background, short‑wave‑infrared rule‑based active fire, and invalid observations, and the dataset includes chip‑level metadata, an incident‑disjoint split, and a mask‑blind analyst review of 233 test chips.

By Shreyan Mitra, Mohammadreza Narimani, Parastoo Farajpoor