Modelling wildfire susceptibility in Belize’s ecosystems and protected areas using machine learning and knowledge-based methods

Wildfires are serious threats to Belize’s protected areas and ecosystems. In Belize the spatial variability of wildfire susceptibility and influencing factors at a national scale are poorly understood which hinders wildfire management interventions. Hence, in this research we conducted a joint application and performance comparison of AHP (Analytical Hierarchical Process), RF (Random Forest) and FAHP (Fuzzy Analytical Hierarchical Process). The analysis revealed that RF (AUC = 83.1%) is the model with better predictive accuracy followed by FAHP (AUC = 71.2) and AHP (AUC = 66.8). The RF, AHP and FAHP models classified 22%, 32% and 37% of the country as having high and very high wildfire susceptibility, respectively. These susceptible areas are located mainly in lowland savanna and lowland broad-leaved moist forest; especially, in areas that are unprotected, the outer boundaries of protected areas and small and isolated protected areas. The main factors that are influencing wildfire susceptibility in Belize are distance to agriculture, landcover and temperature. The comparison of these methods provides a better understanding of the implementation and performance of knowledge-based methods (AHP and FAHP) in comparison with a well-established machine learning method (RF) in a country where local data availability, accessibility and reliability are an issue. Our study also provides new wildfire susceptibility information to Belize’s wildfire managers and demonstrates the need to improve wildfire management.