Land subsidence is defined as the gradual settling or sudden subsidence of the earth's surface due to the movement of earth materials. Land subsidence can be caused by natural factors and anthropogenic factors. Land subsidence has emerged as a significant hazard in numerous regions of Iran as a consequence of the over-extraction of groundwater. The primary aim of this study is to assess monthly LS using the differential interferometry synthetic aperture radar (D-InSAR) method and to predict LS using artificial intelligence (AI) models. Sentinel-1 (a radar imagery satellite) time series images were leveraged for LS estimation on a 60 days interval (2 months) basis spanning from 2017 to 2024. In this paper, two models of AI learning are used: to predict LS using regional data and Sentinel-1 time series images, artificial neural network (ANN) and support vector machine (SVM) models were used. Groundwater level, rainfall, discharge, and temperature served as independent variables for LS estimation as inputs to the models. The results of prediction of models indicated a correlation between the ANN and SVM, and subsidence analyzed by D-InSAR, indicated by correlation coefficients of 0.69 and 0.90, respectively. The LS prediction maps offer a means to manage groundwater resources to prevent excessive subsidence in potentially affected regions.