Land Subsidence Susceptibility Mapping Using Persistent Scatterer SAR Interferometry Technique and Optimized Hybrid Machine Learning Algorithms

In this paper, land subsidence susceptibility was assessed for Shahryar County in Iran using the adaptive neuro-fuzzy inference system (ANFIS) machine learning algorithm. Another aim of present paper to assess if ensembles ANFIS with two meta-heuristic algorithms (imperialist competitive algorithm (ICA) and gray wolf optimization (GWO)) would yield a better prediction performance. A remote sensing synthetic aperture radar (SAR) dataset from 2019 2020 persistent-scatterer SAR interferometry (PS-InSAR) technique were used obtain inventory study area use it training testing models. Resulting PS points divided into parts 70% 30% models, respectively. For analysis, eleven conditioning factors taken account: altitude, slope, aspect, plan curvature, profile topographic wetness index (TWI), distance stream, road, stream density, groundwater drawdown, use/land cover (LULC). frequency ratio (FR) applied correlation occurrence. The power models their generated maps (LSSMs) validated root mean square error (RMSE) value under curve receiver operating characteristic (AUC-ROC) analysis. ROC results showed that ANFIS-ICA had best accuracy (0.932) among (ANFIS-GWO (0.926), (0.908)). work optimizing meta-heuristics considerably improves LSSM although alone an acceptable result.