Abstract

As wildfires become increasingly more frequent and severe, more accurate models to predict wildfires are vital to mitigating risks and developing more informed decision-making. The emerging tools of artificial intellegince (AI) has a potential to enhance wildfire risk analytics at multiple fronts. For example, deep learning (DL) has been successfully used to classify active fires, burned scars, smoke plumes and to track the spread of active wildfires. Since wildfire spread tends to exhibit highly complex spatio-temporal dependencies which often cannot be accurately described with conventional Euclidean-based approaches, we postulate that the tools of topological and geometric deep learning, specifically designed for non-Euclidean objects such as manifolds and graphs, may offer a more competitive solution. We discuss pros and cons of such solutions and their potential to open a new path toward more accurate wildfire risk analytics, especially under scenarios of limited and noisy data records.