Investigation of the performance of the Modflow concept model and the Simulator Meta model of Genetic Programming in the modeling of the hydrograph representing the aquifer (Case Study: Lour-Andimeshk Plain)

In order to apply the correct management, it is necessary to identify and model the level of groundwater in the plains for a long-term planning and use more and better than the potential of the water in the plains, is deeply felt. In this study, the monthly statistical information for the 5-year water (89-88 to 93-92) related to the 8-pisometer level of the Lour-Andimeshk plain aquifer. At first, using the Tesine method, weighted average of each piezometer was obtained and the time series of the mean plain, which represents the hydrograph of the representative aquifer of the study area, was calculated. Then, using the concept of groundwater of Modflow and the Simulator Meta model of the Genetic Programming, the hydrograph of the aquifer unit was modeled and the results were compared. The results showed that the concept model of Modflow with a coefficient of explanation of 0/7836 in the test phase compared to the transmutation of the Genetic Programming with a coefficient of explanation of 0/6310 has better performance.