Modeling of groundwater quality based on water quality index using M5P decision tree method

Abstract

Groundwater is recognized as one of the most important sources of fresh water for agricultural and drinking purposes in the world. About one-third of the world's population needs groundwater to supply drinking water. Therefore, groundwater plays an important role in providing water for consumption in various sectors such as industry, agriculture and drinking. In the present study, first the WQI index was calculated using data related to water quality parameters of 23 wells in Qazvin plain from 2015 to 2018. Then the performance of M5P tree model in estimating groundwater quality in Qazvin plain was evaluated based on WQI index. The results of the model were compared with the indices of Correlation Coefficient (R), Root Mean Square Error (RMSE) and Mean Absolute Error (MAE). The results showed that the third scenario including TDS, EC, TH with RMSE= 5.2198, MAE= 3.7747 and R= 0.9817 was selected as the best scenario. The mean values of WQI index showed that most of the area of Qazvin plain is allocated to poor quality class.