Probabilistic model forecasts wildfire size changes with weather and terrain
Probabilistic Forecasting of Wildfire Size Using Conditional Flow Matching
Machine Learning
Summary
Wildfires can grow quickly and unpredictably, which makes planning responses difficult. The authors created a computer model that predicts how much a wildfire’s size will change every few hours using weather, land, and vegetation data. Instead of showing exactly where the fire spreads, the model focuses on the total area burning, which is faster to compute and easier to use with warning systems. They tested it using simulated wildfires and found it could predict fire growth accurately and also provide estimates of uncertainty.
What this means in practice
- •For emergency management teams: Integrate probabilistic wildfire size forecasts into early warning systems to improve evacuation timing and resource allocation during wildfire events.
- •For insurance risk assessors: Use modeling to estimate potential wildfire spread and area for better risk assessment and policy pricing based on probabilistic forecasts.
Authors
Isaac Lee, Bryan Shaddy, Assad Oberai
Abstract
In this work we present a probabilistic model for predicting the temporal evolution of wildfire size using conditional generative algorithms, namely flow matching. Rather than predicting spatially resolved fire progression, the proposed model forecasts a time series of fire acreage, substantially reducing computational cost and enabling efficient integration with downstream applications such as early warning systems and risk assessment tools. Given estimates of the fire size at the current and previous forecasting steps, alongside spatially averaged weather conditions, terrain characteristics, and fuel composition, the model predicts the change in fire area over a 3-hour interval. Training data are drawn from 140 coupled atmosphere-wildfire simulations generated using WRF-SFIRE, paired with weather data from the North American Mesoscale (NAM) model. Sensitivity analysis demonstrates that the model captures physically-consistent responses to variations in wind speed, temperature, and relative humidity. Model performance is evaluated against reference solutions from WRF-SFIRE. For single-step predictions, the model achieves a symmetric mean absolute percentage error (sMAPE) of 0.39 relative to the reference WRF-SFIRE solutions. Recursive multi-step predictions over 24 hours are performed for 12 held-out test cases, where the flow matching model achieves a final fire area sMAPE of 0.39 while further providing meaningful quantification of forecast uncertainty.