Spatiotemporal wildfire modeling through point processes with moderate and extreme marks
share
Accurate spatiotemporal modeling of conditions leading to moderate and large wildfires provides better understanding of mechanisms driving fire-prone ecosystems and improves risk management. We study daily summer wildfire data for the French Mediterranean basin during 1995–2018. We jointly model occurrence intensity and wildfire sizes by combining extreme-value theory and point processes within a novel Bayesian hierarchical model. The occurrence component models wildfire ignitions as a spatiotemporal log-Gaussian Cox process. Burnt areas are numerical marks attached to points, and we consider fires with marks exceeding a high threshold as extreme. The size component is a two-component mixture varying in space and time that jointly models moderate and extreme fires. We capture non-linear influence of covariates (Fire Weather Index, forest cover) through component-specific smooth functions, which may vary with season. To reveal common drivers of different aspects of wildfire activity, we share random effects between model components to improve interpretability and parsimony without compromising predictive skill. Stratified subsampling of zero counts is implemented to cope with large observation vectors. We compare and validate models through predictive scores and visual diagnostics. Our methodology provides a holistic approach to explaining and predicting the drivers of wildfire activity and their associated uncertainties.
READ FULL TEXT
