This paper presents to study the performance of machine learning techniques consisting of Multivariate Adaptive Regression Spline(MARS), Multilayer Perceptron (MLP), and Decision Tree Regression (DTR) for estimating physico-chemical properties groundwater in coastal plain area in Vinhlinh and Giolinh districts of Quangtri province of Vietnam. To deploy the MLP and DTR, different types of transfer and kernel functions were tested, respectively. Determining the results of MARS, MLP and DTR showed that three models have suitable carrying out for forecasting water quality components. Comparison of outcomes of MARS model with MLP, DTR models indicates that this model has good performance for forecasting the elements of water quality, its level of accuracy is slightly more than other. To assess the accurate values of the models according to the measurement parameters indicated that order models were MARS, DTR, and MLP, respectively.