A new GIS-based technique using an adaptive neuro-fuzzy inference system for land subsidence susceptibility mapping

摘要: In this study, we evaluated the predictive performance of an adaptive neuro-fuzzy inference system (ANFIS) with six different membership functions (MFs). Using a geographic information (GIS), applied ANFIS to land subsidence susceptibility mapping (LSSM) in study area Amol County, northern Iran. As novelty, derived inventory from differential synthetic aperture radar interferometry (DInSAR) two Sentinel-1 images. We used 70% surface deformation areas for training, while 30% were reserved testing and validation. then investigated regions that are susceptible via method resulting prediction maps using receiver operating characteristics (ROC) curves. Out versions, most accurate map was generated Gaussian function, yielding accuracy 84%.