Evaluation of Accuracy of Hybrid Model of Gene Expression Planning - Fuzzy Logic in Estimation of Land Subsidence Risk

Land subsidence is a nonlinear and complex process that data-driven computational intelligence models can model it. In this study, the accuracy and efficiency of hybrid fuzzy logic gene expression planning hybrid model in estimating land subsidence risk and its factors in Varamin aquifer standardized. For this purpose, after selecting and gathering information from 15 factors affecting the subsidence event based on research records in the GIS environment, they were first standardized by fuzzy membership functions and then gene expression programming method was used to integrate the layers. Finally, using seven important statistical benchmarks based on radar image data, the model was validated in 4 different scenarios in input data and operators. The results showed scenario 1 with input parameters of bedrock level, Debi of pumping wells, groundwater drawdown, geology and operators, +, - ×, ÷, sqr, exp, Ln, ^ 2, ^ 3,3Rt, sin, cos, Atan, is the best model in training and testing. Accordingly, the groundwater drawdown parameter had the highest effect on land subsidence in the study area.