Comparable analysis of analytical hierarchy process and fuzzy logic methods based on GIS and remote sensing for anticipating landslide susceptibility in the Iraqi Kurdistan Region, Koya district

Landslides pose a serious threat in urban areas with steep and varied terrain, such as the Koya district in northern Iraq. This study aims to produce landslide susceptibility maps (LSMs) using remote sensing data and three models: Analytical Hierarchy Process (AHP), Fuzzy Logic SUM, and Fuzzy Gamma 0.9. A total of 280 landslides were identified through field surveys, GPS, and Google Earth, and used for model training and validation. Fifteen conditioning factors were used, including slope, geology, land cover, rainfall, and drainage density. The resulting LSMs were classified into five susceptibility levels. The Fuzzy Gamma 0.9 model identified 9.15% of the area as highly susceptible, while the Fuzzy SUM model showed 20.79%. Validation using the Area Under the Curve (AUC) revealed that the Fuzzy Gamma 0.9 model (AUC = 0.80) performed better than AHP (0.711) and Fuzzy SUM (0.716). These results provide valuable insights for land use planning and hazard mitigation.