A generative model for surrogates of spatial-temporal wildfire nowcasting
This work addresses the need for efficient wildfire prediction for emergency responders and ecoregion managers, but it is incremental as it builds on existing generative methods for a specific domain.
The authors tackled the problem of real-time wildfire nowcasting by developing a generative model using 3D Vector-Quantized Variational Autoencoders to produce spatial-temporal sequences of wildfire burned areas, tested on the Chimney fire in California, where it generated coherent fire scenarios and trained a surrogate model for prediction.
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.