Experimenting Two Machine Learning Methods in Classifying River Water Quality

Water is very important to human life. It is a vital aspect of human and ecosystem survival and health. As it affects human lives individually, the quality of water is a universal concern across the globe. When the quality of water deteriorates, the problem of water scarcity will follow. Water quality is highly dependent on various factors such as the increase of population, the rapid development of economic expansion, as well as environmental pollution. The objective of this study is to build a classification model for water quality. Two classification models are built by the WEKA data mining tool, which are the Random Forest algorithm and Random Tree algorithm. The performance of the model is measured based on accuracy, precision, and recall. The results showed that Random Forest gives a higher performance across all three evaluation metrics as compared to Random Tree algorithm. The results are hoped to assist the classification of water quality categories in different states and river locations across the world.