Climate change has exacerbated natural hazards, including wildfires. In recent years, wildfires have become stronger and more frequent, threatening not only human lives worldwide but also ecosystems and wildlife. The proliferation of remote sensing data and derived variables has enabled deep learning models to help authorities to understand, mitigate, and manage wildfires. In this context, our work presents FireEx, a modality-aware Ensemble-of-Experts model for next-day wildfire spread prediction using remote sensing data of wildfires in Canada and Alaska. The dataset contains multi-source remote sensing data to segment next-day incremental wildfire growth, using the previous 24 h data. FireEx is based on a U-Net-designed multi-kernel Convolutional Neural Network, and is a combination of three models: two experts based on fuel data and weather data, respectively, and a generalist model trained on all the input channels of the dataset. The two experts and the generalist are trained independently and fused together using averaging. FireEx demonstrates strong performance with an F1-score of 48.9%, and ablation studies demonstrate the robustness of the architecture design, showing degraded performance when one of the experts is removed, therefore highlighting the importance of each expert and the generalist model. To the best of our knowledge, FireEx is the first Ensemble-of-Experts model for wildfire spread prediction, offering a modality-aware design approach and laying the groundwork for similar architectures in the field.
Andrianarivony et al. (Sun,) studied this question.