Spatiotemporal wildfire modeling through point processes with moderate and extreme marks

2021/05/17 by Jonathan Koh, François Pimont, Koh, Jonathan +6 · 5 citations
Earth and Planetary Sciences · Environmental Science · Mathematics · #Aeolian processes and effects #Applications (stat.AP) #FOS: Computer and information sciences #Fire effects on ecosystems #Methodology (stat.ME) #Remote Sensing in Agriculture #stat.AP #stat.ME

paper · pdf · doi:10.48550/arxiv.2105.08004

openalex publication_date 2021/05/17 · arxiv created 2021/07/14 · arxiv updated 2021/07/15 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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 here develop a joint model for the occurrence intensity and the wildfire size distribution by combining extreme-value theory and point processes within a novel Bayesian hierarchical model, and use it to study daily summer wildfire data for the French Mediterranean basin during 1995--2018. The occurrence component models wildfire ignitions as a spatiotemporal log-Gaussian Cox process. Burnt areas are numerical marks attached to points and are considered as extreme if they exceed a high threshold. 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. We propose estimating shared random effects between model components to reveal and interpret common drivers of different aspects of wildfire activity. This leads to increased parsimony and reduced estimation uncertainty with better predictions. Specific 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 associated uncertainties.

Cited by

• Quantile-based causal inference for spatio-temporal processes: Assessing the impacts of wildfires on US air quality
• MVeLMA: Multimodal Vegetation Loss Modeling Architecture for Predicting Post-fire Vegetation Loss
• A nonparametric Bayesian analysis of independent and identically distributed observations of covariate-driven Poisson processes
• XGBoost meets INLA: a two-stage spatio-temporal forecasting of wildfires in Portugal
• Geometry-aware Active Learning of Spatiotemporal Dynamic Systems

Related

• Point-process based Bayesian modeling of space-time structures of forest fire occurrences in Mediterranean France
• Bayesian spatiotemporal modelling of wildfire occurrences and sizes for projections under climate change
• Insights into the drivers and spatio-temporal trends of extreme Mediterranean wildfires with statistical deep-learning
• Joint Modeling and Prediction of Massive Spatio-Temporal Wildfire Count and Burnt Area Data with the INLA-SPDE Approach
• Spatial wildfire risk modeling using mixtures of tree-based multivariate Pareto distributions