Land subsidence modeling and mapping in Darab region, Iran

Land subsidence refers to the collapse of Earth's surface. This study aimed to model land subsidence using machine learning methods in the Darab region of Fars Province, which is recognized as one of the most critical provinces suffering from land subsidence in the country. Nineteen factors affecting the occurrence of land subsidence were selected as independent variables for the modeling process: slope degree, aspect, distance to rivers, stream density, elevation, land use, normalized difference vegetation index (NDVI), plan curvature, profile curvature, topographic wetness index, pH, electrical conductivity, mean annual rainfall, mean weight diameter (MWD), clay, silt, calcium carbonate equivalent (CCE), sodium content, and organic matter. Modeling was conducted using: artificial neural network (ANN), maximum entropy (MaxEnt), and support vector machine (SVM). The performance of algorithms was compared both individually and in combination. Validation results using the receiver operating characteristic (ROC) curve to identify landslide prone areas showed that land subsidence susceptibility maps produced by single MaxEnt model had highest accuracy, with area under the curve (AUC) of 0.92. According to the prioritization of effective factors, elevation and land use were determined to be the most crucial factors for land subsidence. The results of this spatial modeling of land subsidence susceptibility can greatly aid land allocation planning and water resource management in the study area.