Iranian agriculture has not made significant progress in recent decades, and crops are grown using methods such as flood irrigation. Consumption of more than 90% of Iran’s water is related to the agricultural sector, most of which is extracted from groundwater, which causes land subsidence (LS). In this study, Isfahan LS has been measured with 30 Sentinel-1 radar images by the Interferometric synthetic aperture radar (InSAR) method from 2020 to 2021. Convolutional neural network (CNN), whale optimization algorithm (WOA) and grey wolf optimization (GWO) are used for phase unwrapping. 3 leveling points in two months of 2020 have been measured to determine and validate the root-mean-square error (RMSE) of the proposed methods. As a result of applying the three phase unwrapping algorithms in the InSAR technique, it showed CNN has best accuracy, RMSE and worst time and GWO has best time. The maximum subsidence reaches more than 170 mm/year. The average of the whole study area of Isfahan has subsidence of 110.9 mm/year. Correlation of 3 piezometric well with subsidence of Isfahan city has more than 0.9.