Forest fire mapping: a comparison between GIS-based random forest and Bayesian models

Abstract

In recent decades, res in natural ecosystems, particularly forests and rangelands, have emerged as a signi cant threat. To address this challenge, our study aims to identify and prioritize forest re-prone areas while highlighting key environmental and anthropogenic factors contributing to forest res in Iran's Firouzabad region, Fars province. We compiled a forest re incident map using data from the Data Center of the Natural Resources Department in Fars province, cross-referenced with eld surveys. We examined 80 forest re sites, randomly divided into a "training dataset" (70%) and a "validation dataset" (30%). We created "Forest Fire Susceptibility" (FFS) maps using GIS-based Bayesian and Random Forest (RF) methodologies, incorporating twelve unique environmental and human-induced variables. The performance of these methodologies was evaluated using the "Area Under the Curve-AUC." RF outperformed the Bayesian model with AUC scores of 0.876 and 0.807, respectively. The RF model identi ed 37.86% of the area as having a high re risk, compared to the Bayesian model's estimate of 48.46%. Key factors in uencing re occurrences included elevation, mean annual precipitation, distance to roads, and mean annual temperature. Conversely, variables such as slope direction, topographic wetness index, and slope percent had a lesser impact. Given the presence of at-risk ora and fauna species in the area, our ndings provide essential tools for pinpointing high re susceptibility zones, aiding regional authorities in implementing preventive measures to mitigate re hazards in forest ecosystems. In conclusion, our methodologies allow for the rapid creation of contemporary re susceptibility maps based on fresh data.