analysis and evaluation of the drop in the groundwater level of khorram abad plain

In recent years, the indiscriminate extraction of underground water has caused a sharp drop in the level of underground water; which has resulted in dangers such as land subsidence. therefore, it is important to reliably predict the level of underground water for the management of these resources. in this research, in order to simulate the underground water level of khorramabad plain, the performance of hybrid models of support vector regression-wavelet, support vector regression-bat, support vector regression-gray wolf for four piezometric wells using parameters of temperature, precipitation and withdrawal from aquifers during the period the statistics of 1382-1402 were examined. the criteria of correlation coefficient, root mean square error, average absolute value of error and nash sutcliffe coefficient were used to evaluate and compare the performance of the models. the results showed that the combined structure provides better performance than other structures in all investigated models. also, the results showed that the support vector-wavelet regression model has a favorable ability compared to other models.