# Probabilistic Forecasting of Localized Wildfire Spread Based on Conditional Flow Matching

arXiv: https://arxiv.org/abs/2603.26975 · HTML: https://mlsanity.com/paper/2603.26975/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 28 references that are in the map.
- First posted on arXiv 27 Mar 2026.

## Builds on (most cited first, 8 of 8)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [A review of machine learning applications in wildfire science and management](https://mlsanity.com/paper/2003.00646/) (2020)
- [A Spatio-Temporal Neural Network Forecasting Approach for Emulation of Firefront Models](https://mlsanity.com/paper/2206.08523/) (2022)
- [Generative Algorithms for Fusion of Physics-Based Wildfire Spread Models with Satellite Data for Initializing Wildfire Forecasts](https://mlsanity.com/paper/2309.02615/) (2023)
- [Recurrent Convolutional Deep Neural Networks for Modeling Time-Resolved Wildfire Spread Behavior](https://mlsanity.com/paper/2210.16411/) (2022)
- [Generative Algorithms for Wildfire Progression Reconstruction from Multi-Modal Satellite Active Fire Measurements and Terrain Height](https://mlsanity.com/paper/2506.10404/) (2025)
- [Conditional flow matching for physics-constrained inverse problems with finite training data](https://mlsanity.com/paper/2603.14135/) (2026)

## Abstract (arXiv)

This study presents a probabilistic surrogate model for localized wildfire spread based on a conditional flow matching algorithm. The approach models fire progression as a stochastic process by learning the conditional distribution of fire arrival times given the current fire state along with environmental and atmospheric inputs. Model inputs include current burned area, near-surface wind components, temperature, relative humidity, terrain height, and fuel category information, all defined on a high-resolution spatial grid. The outputs are samples of arrival time within a three-hour time window, conditioned on the input variables. Training data are generated from coupled atmosphere-wildfire spread simulations using WRF-SFIRE, paired with weather fields from the North American Mesoscale model. The proposed framework enables efficient generation of ensembles of arrival times and explicitly represents uncertainty arising from incomplete knowledge of the fire-atmosphere system and unresolved variables. The model supports localized prediction over subdomains, reducing computational cost relative to physics-based simulators while retaining sensitivity to key drivers of fire spread. Model performance is evaluated against WRF-SFIRE simulations for both single-step (3-hour) and recursive multi-step (24-hour) forecasts. Results demonstrate that the method captures variability in fire evolution and produces accurate ensemble predictions. The framework provides a scalable approach for probabilistic wildfire forecasting and offers a pathway for integrating machine learning models with operational fire prediction systems and data assimilation.