Neural-Parameterized Cellular Automata for Wildfire Spread

• URL: http://arxiv.org/abs/2606.11676v1
• Date: Wed, 10 Jun 2026 05:40:37 GMT
• Title: Neural-Parameterized Cellular Automata for Wildfire Spread
• Abstract summary: We introduce a hybrid deep-learning parameterized Probabilistic Cellular Automata framework implemented in JAX.<n>Our approach employs a Multi-Scale Convolutional Neural Network to generate spatially varying parameters that govern fire-spread probability, wind alignment, and slope influence.<n>This hybrid design captures complex, nonlinear environmental interactions while preserving the physical interpretability of the underlying three-state CA.
• Score: 1.1287316240400744
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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 IoU > 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 ncoded in those observations.

Related papers

• SkyJEPA: Learning Long-Horizon World Models for Zero-Shot Sim-to-Real Control of Quadrotors [48.60897189520386]
  We introduce the JEPA-style model for real-time quadrotor control.<n>We combine a latent dynamics model with a novel physics-inspired prober that maps frozen latents to interpretable state.<n>To reduce the dependence on expensive and unsafe real-world data collection, we develop a structured pipeline for automated dataset generation.
  arXiv  Detail & Related papers  (2026-06-22T15:00:59Z)
• Aerial Wildfire Suppression Planning with a Hybrid CNN-Cellular Automata Fire Model [1.743048013936118]
  We present a modeling and optimization framework for aerial wildfire suppression.<n>The framework combines a hybrid neural-cellular automaton wildfire model with gradient-based design of targeted aerial drops.<n>A case study based on the 2020 Bear Fire shows that the framework can generate coherent aerial suppression schedules for reducing total fire-affected area.
  arXiv  Detail & Related papers  (2026-06-11T17:42:34Z)
• From AR to Diffusion: Efficiently Adapting Large Language Models with Strictly Causal and Elastic Horizons [74.25767873168745]
  Diffusion models promise efficient parallel text generation but rely on bidirectional attention, creating a structural mismatch with pre-trained Autoregressive (AR) models.<n>We propose FLUID, a framework that efficiently adapts AR backbones to the diffusion paradigm.<n> Experiments demonstrate that FLUID achieves state-of-the-art performance while reducing training costs by orders of magnitude.
  arXiv  Detail & Related papers  (2026-04-11T13:18:27Z)
• FireSenseNet: A Dual-Branch CNN with Cross-Attentive Feature Interaction for Next-Day Wildfire Spread Prediction [1.1417805445492082]
  Accurate prediction of next-day wildfire spread is critical for disaster response and resource allocation.<n>We propose FireSenseNet, a dual-branch convolutional neural network equipped with a novel Cross-Attentive Interaction Module.<n>We demonstrate that FireSenseNet achieves an F1 of 0.4176 and AUC-PR of 0.3435, outperforming all alternatives.
  arXiv  Detail & Related papers  (2026-04-09T00:39:03Z)
• Probabilistic Forecasting of Localized Wildfire Spread Based on Conditional Flow Matching [0.0]
  This study presents a probabilistic surrogate model for localized wildfire spread based on a conditional flow matching algorithm.<n>The approach models fire progression as a process by learning the conditional distribution of fire arrival times.<n>Results demonstrate that the method captures variability in fire evolution and produces accurate ensemble predictions.
  arXiv  Detail & Related papers  (2026-03-27T20:39:02Z)
• Target Concept Tuning Improves Extreme Weather Forecasting [51.43578341469291]
  Deep learning models for meteorological forecasting often fail in rare but high-impact events such as typhoons.<n>Existing fine-tuning methods face a trade-off between overlooking these extreme events and overfitting them at the expense of overall performance.<n>We propose TaCT, an interpretable concept-gated fine-tuning framework that solves the aforementioned issue by selective model improvement.
  arXiv  Detail & Related papers  (2026-03-17T15:34:05Z)
• LiQSS: Post-Transformer Linear Quantum-Inspired State-Space Tensor Networks for Real-Time 6G [85.58816960936069]
  Proactive and agentic control in Sixth-Generation (6G) Open Radio Access Networks (O-RAN) requires control-grade prediction under stringent Near-Time (Near-RT) latency and computational constraints.<n>This paper investigates a post-Transformer paradigm for efficient radio telemetry forecasting.<n>We propose a quantum-inspired state-space tensor network that replaces self-attention with stable structured state-space dynamics kernels.
  arXiv  Detail & Related papers  (2026-01-18T12:08:38Z)
• Leveraging Cellular Automata for Real-Time Wildfire Spread Modeling in California [0.0]
  The present study develops a predictive model based on cellular automata (CA) that incorporates key environmental variables.<n> Evaluation of the model using a confusion matrix against burn scars from the 2025 Pacific Palisades Fire yielded a recall of 0.860, a precision of 0.605, and an overall F1 score of 0.711.
  arXiv  Detail & Related papers  (2025-10-10T02:31:57Z)
• FourCastNet 3: A geometric approach to probabilistic machine-learning weather forecasting at scale [91.84761739154366]
  FourCastNet 3 advances global weather modeling by implementing a scalable, geometric machine learning (ML) approach to probabilistic ensemble forecasting.<n>FourCastNet 3 delivers forecasting accuracy that surpasses leading conventional ensemble models and rivals the best diffusion-based methods.<n>Its computational efficiency, medium-range probabilistic skill, spectral fidelity, and rollout stability at subseasonal timescales make it a strong candidate for improving meteorological forecasting and early warning systems through large ensemble predictions.
  arXiv  Detail & Related papers  (2025-07-16T11:22:18Z)
• Recurrent Diffusion for Large-Scale Parameter Generation [52.98888368644455]
  We introduce Recurrent Diffusion for Large Scale Generation (RPG), a novel framework that generates full neural network parameters up to hundreds of millions on a single GPU.<n>RPG serves as a critical advance in AI generating AI, potentially enabling efficient weight generation at scales previously deemed infeasible.
  arXiv  Detail & Related papers  (2025-01-20T16:46:26Z)
• Adaptive Federated Pruning in Hierarchical Wireless Networks [69.6417645730093]
  Federated Learning (FL) is a privacy-preserving distributed learning framework where a server aggregates models updated by multiple devices without accessing their private datasets. In this paper, we introduce model pruning for HFL in wireless networks to reduce the neural network scale. We show that our proposed HFL with model pruning achieves similar learning accuracy compared with the HFL without model pruning and reduces about 50 percent communication cost.
  arXiv  Detail & Related papers  (2023-05-15T22:04:49Z)
• A Neural Emulator for Uncertainty Estimation of Fire Propagation [12.067753469557598]
  Wildfire is a highly process where small changes in environmental conditions (such as wind speed and direction) can lead to large changes in observed behaviour. Traditional approach to quantify uncertainty in fire-front progression is to generate probability maps via ensembles of simulations. We propose a new approach to directly estimate the likelihood of fire propagation given uncertainty in input parameters.
  arXiv  Detail & Related papers  (2023-05-10T13:42:52Z)
• Convolutional LSTM Neural Networks for Modeling Wildland Fire Dynamics [0.0]
  We evaluate the feasibility of using a Convolutional Long Short-Term Memory recurrent neural network to model the dynamics of wildland fire propagation. We show that ConvLSTMs can capture local fire transmission events, as well as the overall fire dynamics, such as the rate at which the fire spreads.
  arXiv  Detail & Related papers  (2020-12-11T23:31:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.