Groundwater is a valuable resource supporting various sectors worldwide, but it is being overexploited and its quality is deteriorating due to population growth, agriculture expansion, and increasing food demands. Sustainable development of groundwater is a global challenge due to limited freshwater resources. Water quality datasets are often imbalanced across large areas, making field-based measurements expensive and time-consuming for accurate predictions. In this chapter firstly describe about some traditional methods like geomorphological method, geological method, well-inventory, geophysical method, and electrical resistivity method, and photogeology. This Chapter provides the use of machine learning to map groundwater quality. To address this, focus on three effective methods: Artificial Neural Networks (ANNs), Support Vector Machines (SVM), and Extreme Gradient Boosting (XGBOOST). ANNs mimic biological neural networks, processing data through layers of interconnected neurons. Sensitivity to initial weights, biases, and activation functions. Small changes in input or model parameters can result in significant output variations. SVM uses optimal margins to separate different data classes, handling non-linear problems by projecting data into higher dimensions. SVMs generalize well and are suitable for low-data scenarios. Less sensitive to noise in data compared to ANNs. The choice of kernel function and its parameters can impact decision boundaries and classification outcomes. XGBOOST is a recently developed gradient-boosted tree technique with built-in regularization, efficient resource usage, and model interpretability. Fuzzy method and regression models also use for groundwater prediction. Grace satellite data set is used for storage of groundwater prediction. FEFLOW, MODFLOW, and MIKE SHE are used for groundwater quality and quantity assessment. These findings contribute to the advancement of water quality assessment and provide valuable insights for future research and practical applications. This book chapter will be helpful for students and researchers in the major fields of water resources management, agriculture, and environmental engineering as well as policymakers, particularly in developing countries.