A generative model for surrogates of spatial-temporal wildfire nowcasting

TL;DR

This paper introduces a 3D Vector-Quantized Variational Autoencoder-based generative model that creates realistic wildfire spread scenarios for specific ecoregions, aiding real-time fire nowcasting and reducing computational costs.

Contribution

It presents a novel generative model for wildfire nowcasting that captures spatial-temporal fire dynamics and geophysical influences, improving over region-specific and data-intensive existing models.

Findings

Successfully generated coherent wildfire scenarios in California.

Generated data improved wildfire dissemination prediction accuracy.

Model accounts for vegetation and slope effects.

Abstract

Recent increase in wildfires worldwide has led to the need for real-time fire nowcasting. Physics-driven models, such as cellular automata and computational fluid dynamics can provide high-fidelity fire spread simulations but they are computationally expensive and time-consuming. Much effort has been put into developing machine learning models for fire prediction. However, these models are often region-specific and require a substantial quantity of simulation data for training purpose. This results in a significant amount of computational effort for different ecoregions. In this work, a generative model is proposed using a three-dimensional Vector-Quantized Variational Autoencoders to generate spatial-temporal sequences of unseen wildfire burned areas in a given ecoregion. The model is tested in the ecoregion of a recent massive wildfire event in California, known as the Chimney fire. Numerical results show that the model succeed in generating coherent and structured fire scenarios, taking into account the impact from geophysical variables, such as vegetation and slope. Generated data are also used to train a surrogate model for predicting wildfire dissemination, which has been tested on both simulation data and the real Chimney fire event.