نوع مقاله : مقاله پژوهشی
نویسندگان
1 دانشکده عمران و معماری، دانشگاه شهاب دانش، قم، ایران
2 دانشکده عمران و معماری، دانشگاه شهاب دانش، قم، ایران
3 دانشجوی دکتری دانشگاه خوارزمی
چکیده
کلیدواژهها
موضوعات
عنوان مقاله [English]
نویسندگان [English]
Groundwater is considered the most important water source in the Qom plain. Therefore, predicting the groundwater level fluctuations of this plain can be a great help for planning and decision-making. The main aim of this study is to predict the groundwater level of Qom plain by the Adaptive Neuro-Fuzzy Inference System. It is easily possible to study the process of nonlinear models such as groundwater without considering the physics of the problem or knowing the characteristics of aquifer layers and complex geological information by this method. In this study nine observation wells were selected in Qom plain. Different patterns and combinations including groundwater level, well discharge, and rainfall in the earlier 12 months were used for input data and groundwater level in the current month was selected for output in the model. According to the results, the mentioned model have had suitable accuracy in predicting the groundwater level with respect to the correlation coefficient (R2) equal to 0.96 and the root mean square error equal to 0.26. The use of well discharge data in modeling improved the results in observation wells, which shows that these data have an effect on decreasing the groundwater level of this plain. Results showed that drainage from wells is the most important factor in reducing the groundwater level of this plain. The results also illustrated that the groundwater level of previous months and the amount of well drainage are suitable for predicting the groundwater level in arid and semi-arid climates such as Qom plain at the modeling entrance.
کلیدواژهها [English]