Evaluation and Accuracy of Artificial Intelligence, Geostatistics and Inverse distance weighting Methods in Simulation the Groundwater Depth

Successful management of groundwater resources using numerical models requires knowledge of spatial distribution of hydraulic heads and it's fluctuation, aquifer parameters and other input data. One of the most basical issues in groundwater resources management is the estimation of water table from observation well network data. In this study, three methods of artificial intelligence, geostatistics (Kriging) and IDW with evapotranspiration, air temperature, precipitation and geographic inputs were used to simulate the depth of groundwater Salman Farsi Sugarcane Plantation. The results showed that the highest simulation accuracy of groundwater depth in Salman Farsi Sugarcane Plantation was related to the artificial neural network model with the highest R2 (0/92) index and lowest RMSE and MAE (1.25 and 1.74) values. Also, among the Kriging and IDW models used, the accuracy of the Kriging model was more than the IDW model. Due to the acceptable accuracy of the results of the presented models, the water resource planner and decision maker in this field can apply this optimum interpolated groundwater depth to monitoring the spatiotemporal fluctuation of groundwater depth in this area by updating it's data.