Data-based wildfire risk model for Mediterranean ecosystems – case study of the Concepción metropolitan area in central Chile

Abstract. Wildfire risk is latent in Chilean metropolitan areas characterized by the strong presence of wildland–urban interfaces (WUIs). The Concepción area (CMA) constitutes one most representative samples that dynamic. wildfire CMA was addressed establishing a model five categories (near zero, low, moderate, high, and very high) represent discernible thresholds fire occurrence, using geospatial data satellite images describing anthropic–biophysical factors trigger fires. Those were used to deliver hazard machine learning algorithms, including principal component analysis Kohonen self-organizing maps two experimental scenarios: only native forest forestry plantation. validated hotspots obtained from government organization. results indicated 12.3 % CMA's surface has high fire, 29.4 moderate risk, 58.3 low risk. Lastly, observed main drivers have deepened this discussed: first, evident proximity between increasing urban with exotic plantations and, second, climate change threatens triggering more severe large wildfires because human activities.