XGBoost meets INLA: a two-stage spatio-temporal forecasting of wildfires in Portugal

TL;DR

This paper introduces a novel two-stage ensemble model combining XGBoost and INLA with an extended generalized Pareto likelihood for accurate spatio-temporal wildfire forecasting in Portugal, addressing data limitations and extreme event prediction.

Contribution

It develops a new two-stage ensemble framework integrating gradient boosting and latent Gaussian models with advanced likelihoods for wildfire prediction.

Findings

Strong performance for one-month-ahead forecasts

Effective modeling of both moderate and extreme fire events

Comparison shows eGP likelihood outperforms common alternatives

Abstract

Wildfires pose a major threat to Portugal, with over 115,000 hectares burned annually on average during 1980-2024, and the country has faced devastating mega-fires such as those in 2017. Accurate forecasts of wildfire occurrence and burned area are therefore essential for firefighting resource allocation and emergency preparedness. In this study, we propose a novel two-stage ensemble that extends the widely used latent Gaussian modelling framework with integrated nested Laplace approximation (INLA) for spatio-temporal wildfire forecasting. Stage 1 applies a gradient boosting model (XGBoost) to environmental covariates and historical fire records to produce one-month-ahead point forecasts of fire counts and burned area. Stage 2 uses these predictions as external covariates in a latent Gaussian model with additional spatiotemporal random effects to generate probabilistic forecasts of monthly total fire counts and burned area at the council level. To capture both moderate and extreme events, we implement the extended generalised Pareto (eGP) likelihood (a sub-asymptotic distribution) within INLA, develop Penalised Complexity (PC) priors for its parameters, and compare the eGP likelihood with common alternatives (e.g., Gamma and Weibull). Our framework tackles the unavailability of future environmental covariates at prediction time and performs strongly for one-month-ahead forecasts.