Our Earth surface is much occupied by water and hence it is also known as water planet. Of this fresh water is present in limited ecosystems like rivers and streams. The quality of water in our rivers is affected by various anthropogenic activities like intensive cultivation, population explosion, industrialization and the consequent urbanization. Hence river water quality has to be monitored to protect the status of these important ecosystems. As the conventional methods of river water analysis and monitoring are time consuming, tedious and cumbersome, machine learning methods come to the rescue. The ML models employed in River water quality monitoring include Support Vector Machine, Random Forest, Multilayer Perceptron, Logistic Regression Model, XG Boost, Decision Tree, CAT Boost and Model Stacking. Among them, Random Forest and Model Stacking can perform better than that of others. This paper overviews the applications of machine learning algorithms in river water quality monitoring.