mlsanityData to 14 Oct 2026

A Probabilistic Approach to Wildfire Spread Prediction Using a Denoising Diffusion Surrogate Model

arXiv 2507.00761 ↗First posted 1 Jul 2025cs.LGcited by 11

On the map: Diffusion models → Flow matching, time series and science

Abstract (arXiv)

Thanks to recent advances in generative AI, computers can now simulate realistic and complex natural processes. We apply this capability to predict how wildfires spread, a task made difficult by the unpredictable nature of fire and the variety of environmental conditions it depends on. In this study, We present the first denoising diffusion model for predicting wildfire spread, a new kind of AI framework that learns to simulate fires not just as one fixed outcome, but as a range of possible scenarios. By doing so, it accounts for the inherent uncertainty of wildfire dynamics, a feature that traditional models typically fail to represent. Unlike deterministic approaches that generate a single prediction, our model produces ensembles of forecasts that reflect physically meaningful distributions of where fire might go next. This technology could help us develop smarter, faster, and more reliable tools for anticipating wildfire behavior, aiding decision-makers in fire risk assessment and response planning.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Placed in Flow matching, time series and science, one of 14 directions in Diffusion models. Builds on 25 of its 71 references that are in the map. First posted on arXiv 1 Jul 2025.

Builds on

25 of 71 references.

Closest ancestors · 7

Same direction, newest first

  1. 2025Appa: Bending Weather Dynamics with Latent Diffusion Models for Global Data Assimilation25 Apr
  2. 2024Latent Diffusion Model for Generating Ensembles of Climate Simulations2 Jul
  3. 2023Generating High-Resolution Regional Precipitation Using Conditional Diffusion Model12 Dec
  4. 2023Turbulence Scaling from Deep Learning Diffusion Generative Models10 Nov
  5. 2023PreDiff: Precipitation Nowcasting with Latent Diffusion Models19 Jul
  6. 2023Latent diffusion models for generative precipitation nowcasting with accurate uncertainty quantification25 Apr
  7. 2023A Denoising Diffusion Model for Fluid Field Prediction27 Jan

Other references · 18

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  4. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  5. 2020Denoising Diffusion Implicit Modelscited by 9,781
  6. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  7. 2021Structured Denoising Diffusion Models in Discrete State-Spacescited by 1,719
  8. 2022Analog Bits: Generating Discrete Data using Diffusion Models with Self-Conditioningcited by 373
  9. 2020WeatherBench: A benchmark dataset for data-driven weather forecastingcited by 275
  10. 2017VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learningcited by 200
  11. 2023GenCast: Diffusion-based ensemble forecasting for medium-range weathercited by 177
  12. 2018Gaussian Process Prior Variational Autoencoderscited by 72
6 more
  1. 2020A review of machine learning applications in wildfire science and managementcited by 65
  2. 2020Generative Adversarial Networks (GANs Survey): Challenges, Solutions, and Future Directionscited by 65
  3. 2021On the Limitations of Multimodal VAEscited by 38
  4. 2023Forecasting Tropical Cyclones with Cascaded Diffusion Modelscited by 10
  5. 2024Comparative Analysis of Generative Models: Enhancing Image Synthesis with VAEs, GANs, and Stable Diffusioncited by 7
  6. 2019Improving VAE generations of multimodal data through data-dependent conditional priorscited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 9.

11 papers.

  1. 2026Neural-Parameterized Cellular Automata for Wildfire Spreadcited by 1
  2. 2026WildfireSpreadBench: The Metric Decides the Model in Wildfire Spread Predictioncited by 1
  3. 2025Probabilistic Wildfire Spread Prediction Using an Autoregressive Conditional Generative Adversarial Networkcited by 0
  4. 2025Diffusion Posterior Sampler for Hyperspectral Unmixing with Spectral Variability Modelingcited by 0
  5. 2026Trustworthy Data-Driven Wildfire Risk Prediction and Understanding in Western Canadacited by 0
  6. 2026Large-Scale 3D Ground-Motion Synthesis with Physics-Inspired Latent Operator Flow Matchingcited by 0
  7. 2026Wildfire Spread Scenarios: Increasing Sample Diversity of Segmentation Diffusion Models with Training-Free Methodscited by 0
  8. 2026DiffUNet^2: Bidirectional Conditional Diffusion for Probabilistic Scientific Spatiotemporal Modelingcited by 0
  9. 2026Multi-Agent Reinforcement Learning for Autonomous UAV Exploration in Wildfire Responsecited by 0
  10. 2026Interpretable Patch-Based Deep Learning for Wildfire Spread Prediction from Ensemble Simulationscited by 0
  11. 2026FireGraphNet: Sub-daily wildfire spread prediction with directed graph neural networkscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026N-Tree Diffusion for Long-Horizon Wildfire Risk Forecasting
  2. 2025Generative AI as a Pillar for Predicting 2D and 3D Wildfire Spread: Beyond Physics-Based Models and Traditional Deep Learning
  3. 2023A generative model for surrogates of spatial-temporal wildfire nowcasting
  4. 2022An Emulation Framework for Fire Front Spread
  5. 2026Probabilistic Forecasting of Localized Wildfire Spread Based on Conditional Flow Matching
  6. 2026Robust Wildfire Forecasting under Partial Observability: From Reconstruction to Prediction ↗
  7. 2026Spatiotemporal Wildfire Prediction and Reinforcement Learning for Helitack Suppression
  8. 2026PyroAdapt: Adapting Wildfire Prediction under Spatial Heterogeneity and Temporal Shift