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.
arXiv:2606. 11676v1 Announce Type: cross Abstract: Traditional wildfire models rely on rigid, low-dimensional parameters and static fuel maps, frequently underpredicting fire spread.
The paper introduces an AI surrogate modelling framework that accelerates wildfire hazard mapping across Canada. By training a multi‑task deep learning model on national‑scale data, the surrogate reproduces key outputs of the computationally intensive BurnP3+ simulator—burn probability, mean fire intensity, and mean rate of spread—in seconds instead of days or weeks. The framework includes standardized training, fine‑tuning, and evaluation protocols, domain‑specific metrics, and counterfactual evaluation to ensure robust out‑of‑distribution performance, achieving up to 806‑fold CPU speed‑up and 13% memory usage compared to the original simulator.
The paper presents modular deep learning augmentations for next‑day wildfire spread prediction, including wind‑ and slope‑conditioned attention biases, physics‑feature retrieval‑augmented output correction, and fire‑conditioned dual‑stream gating. These modules are evaluated on five backbone models using the Next Day Wildfire Spread benchmark, with staged ablations, directional audits, retrieval perturbations, calibration measures, and computational comparisons. The best augmented SwinUNETR model achieves an F1 score of 0.4216 and an AUC‑PR of 0.3673, while a mixed ensemble reaches 0.4292 and 0.3790, demonstrating that predictive performance, operational trustworthiness, and computational practicality can be simultaneously improved.
arXiv:2610.19191v1 Announce Type: new Abstract: Wildfire decisions are made in hours, yet most learned spread models predict daily on targets including burned area. We propose FireGraphNet which form...
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.
arXiv:2607. 07951v1 Announce Type: new Abstract: Wildfire smoke events produce extreme PM$_{2.
arXiv:2610.28818v1 Announce Type: cross Abstract: As systems engineering (SE) shifts from monolithic systems to Systems of Systems, Mission Engineering (ME) has emerged as a new line of thinking in S...
The paper presents a spatiotemporal graph neural network that predicts global fire radiative power (FRP) up to seven days ahead using recent observations and reanalysis data. Trained on 2020‑2022 data and evaluated for 2023‑2024, the model reproduces the seasonal FRP cycle and outperforms persistence, reducing mean squared error by 32–43% at one‑day lead and 24–40% at seven days at 0.1° resolution. While large fires are reliably detected, the model underestimates their radiative power and faces challenges in intensity calibration and small‑fire placement.
WildfireSpreadBench evaluates machine‑learning models for predicting next‑day wildfire spread, comparing five discriminative and one generative architecture on the WildfireSpreadTS dataset. The study shows that model rankings differ markedly when using Average Precision versus threshold‑dependent metrics such as F1 and IoU, revealing three distinct prediction profiles—over‑predicting, balanced, and under‑predicting—that AP alone cannot distinguish. Expanding input channels modestly affected AP, underscoring that AP may favor models with predictions poorly suited for operational use.
AI4Fire evaluates large language models on wildfire-related tasks, comparing bare (task input only) and grounded (task input plus a task‑specific addition) settings. The study tests six core models on five tasks in zero‑shot mode and expands to 29 additional models, revealing that grounding improves performance when the added information contains the answer, while simple rule‑based approaches often outperform the models. The paper also highlights risks in public releases, such as data leakage that can reveal sensitive information.
arXiv:2509. 25017v2 Announce Type: replace Abstract: Wildfires are among the most severe natural hazards, posing a significant threat to both humans and natural ecosystems.
arXiv:2606.17739v2 Announce Type: replace-cross Abstract: Robotics are expected to support environmental monitoring and disaster detection, where decisions must be made under uncertainty, resource li...