Assessing groundwater quality requires a well-equipped laboratory and various instruments and chemicals. The primary focus of this study is to construct an Artificial Neural Network (ANN) model capable of accurately predicting the groundwater quality within the specified research area. The water quality data utilized in this study was obtained from a comprehensive analysis of water quality parameters. This analysis was conducted on 35 groundwater samples collected from the study area and tested at the Delhi Technological University water laboratory. After completing a correlation analysis, the input parameters selected for the model were Electrical Conductivity, Total Dissolved Solids, and Salinity. On the other hand, Na+, Cl−, SO42−, K+, and Total Hardness (TH) were identified as the target parameters. Of the 35 samples, 25 were randomly used for training and testing the model. The remaining ten samples were reserved for prediction and assessing the accuracy of the model. The final network structure (3-10-1) was determined based on regression terms and Mean Squared Error values in the MATLAB environment. The proportion of variances is calculated to evaluate the model’s performance. The results of the ANN model for simulating Na+ concentration show an average variance of 11%. The average variances for Cl− and SO42− are 4% and − 3%, respectively. However, the average variances for K+ and TH are 259% and 45%, respectively. It can be concluded that the model is highly suitable for simulating the concentrations of Na, Cl, and SO4 in groundwater. The model serves as a supplementary tool for monitoring water quality.