Geospatial Wildfire Risk Assessment from Social, Infrastructural and Environmental Perspectives: A Case Study in Queensland Australia

Although it is hard to predict wildfires, risky areas can be systematically assessed and managed. Some of the factors for decision-making are hazard, vulnerability, risk maps, which end product wildfire mapping. This study deals with analysis in Queensland, Australia. A review previous studies focusing on each aspect has been done used records from 2011 2019 Australia, compile required input models detect regions. Machine learning (ML) methods Decision Tree (DT) Support Vector (SVM) were perform hazard assessment. The reason was select most accurate outcomes rest analysis. Among accuracy assessment techniques, Area Under Curvature (AUC) method evaluate maps. Prediction rates 89.21% 83.78% obtained DT SVM, respectively. prediction value showed that DT-hazard map more than SVM-hazard map. Vulnerability implemented by assigning weights factor according literature. Lastly, order create map, vulnerability indices combined. particularly dense urbanization regions under future risk. To preliminary land use planning, this output local governmental authorities.