Machine Learning Based-Prediction of Oily Wastewater Remediation Using Photocatalytic Membrane by Integration of Renewable Energy

The objective of this paper is to predict the oily wastewater quality index of the photocatalytic membrane technology approach based on machine learning. To achieve this goal, five machine learning techniques (k-Nearest Neighbor, Chained SVR, XGBoost, Chained Decision Tree, Decision Tree) have been used. The proposed techniques are valued in terms of the Regression coefficient, Mean Absolute Error, (Mean Square Error), Root Mean Squared Error and Relative Absolute Error. Based on these performance indicators, Chained SVR emerged as the best followed by KNN and DT respectively. These results highlight potential of using machine learning techniques in estimating the index performance of oily wastewater quality and can be rapid decision tools for photocatalytic membrane system performance tuning for oily wastewater remediation using solar energy.