Using Machine Learning Models for Predicting the Water Quality Index in the La Buong River, Vietnam

For effective management of water quantity and quality, it is absolutely essential to estimate the pollution level existing surface water. This case study aims evaluate performance twelve machine learning (ML) models, including five boosting-based algorithms (adaptive boosting, gradient histogram-based light extreme boosting), three decision tree-based (decision tree, extra trees, random forest), four ANN-based (multilayer perceptron, radial basis function, deep feed-forward neural network, convolutional network), in estimating quality La Buong River Vietnam. Water data at monitoring stations alongside for period 2010–2017 were utilized calculate index (WQI). Prediction ML models was evaluated by using two efficiency statistics (i.e., R2 RMSE). The results indicated that all have good predicting WQI but boosting (XGBoost) has best with highest accuracy (R2 = 0.989 RMSE 0.107). findings strengthen argument especially XGBoost, may be employed prediction a high accuracy, which will further improve management.