The significance of machine learning in aquatic environment research is highlighted in this abstract, where it is used as a potent tool for data analysis, categorization, and prediction. Machine learning algorithms have emerged as a major technique for effectively resolving challenging nonlinear problems as a result of the rapid rise in data volume in the aquatic environment. This research focuses on using machine learning to evaluate water quality in diverse contexts, including drinking water, sewage, ocean, and surface and groundwater. The findings show that machine learning techniques have been successfully applied to the development, monitoring, simulation, evaluation, and optimization of various water treatment and management systems as well as to provide solutions for lowering water pollution, enhancing water quality, and managing the security of the watershed ecosystem. Finally, we provided a roadmap for future study in this field by proposing and evaluating some unique computational techniques such as ANN and Boosting algorithms (Ada boost, Xg boost) for forecasting the water quality with an accuracy score of 91%.