 This study demonstrated the potential of using remote sensing imagery combined with machine learning algorithms to monitor water quality in large and remote areas. The study found that the XGB algorithm was the most accurate at predicting chlorophyll levels, while the Random Forest Regression algorithm was the most accurate at predicting total dissolved solids levels. Additionally, the study showed that stratified sampling can be used to improve the accuracy of the models. This article was authored by Elias S. Legas, Fazaka A. Zamali, Dagnanet Sultan, and others.