A Comparative Study of Forest Fire Mapping Using GIS-Based Data Mining Approaches in Western Iran

Mapping fire risk accurately is essential for the planning and protection of forests. This study aims to map (probability ignition) in Marivan County Kurdistan province, Iran, using data mining approaches evidential belief function (EBF) weight evidence (WOE) models, with an emphasis placed on climatic variables. Firstly, 284 incidents region were randomly divided into two groups, including training group (70%, 199 points) validation (30%, 85 points). Given previous studies conditions region, variables slope percentage, direction, altitude, distance from rivers, roads, settlements, land use, curvature, rainfall, maximum annual temperature considered zoning risk. Then, forest maps prepared EBF WOE models. The performance each model was examined Relative Operating Characteristic (ROC) curve. results showed that are effective tools mapping risks area. However, shows a slightly higher Area Under Curve value (0.896) compared (0.886), indicating better performance. this can provide valuable information preventing fires