Modeling nutrient removal by membrane bioreactor at a sewage treatment plant using machine learning models. (April 2022)

• Record Type: Journal Article
• Authors: Yaqub, Muhammad; Lee, Wontae
• Is Part Of: Journal of water process engineering. Volume 46(2022)
• Publication Date: 2022-04
• Subjects: NH4 ammonium -- A2O-MBR anaerobic-anoxic-oxic membrane bioreactor -- ANN artificial neural network -- COD chemical oxygen demand -- R2 coefficient of determination -- DO dissolved oxygen -- MAPE mean absolute percentage error -- MAE mean absolute error -- MLSS mixed liquor suspended solids -- MLP multilayer perceptron -- ORP oxidation-reduction potential -- PVDF polyvinylidene fluoride -- RMSE root mean square error -- SS suspended solids -- TN total nitrogen -- TOC total organic carbon -- TP total phosphorous -- XGBoost extreme gradient boosting -- WWTP wastewater treatment plant; Multilayer perceptron -- Machine learning -- Nutrient removal -- Wastewater treatment -- Extreme gradient boost; Water-supply engineering -- Periodicals; Saline water conversion -- Periodicals; Seawater -- Distillation -- Periodicals; Sanitary engineering -- Periodicals; Sewage -- Purification -- Periodicals; 627
• DOI: 10.1016/j.jwpe.2021.102521
• Languages: English
• ISSNs: 2214-7144

Abstract

Abstract: This study developed machine learning (ML) models to predict nutrient removal using an anaerobic-anoxic-oxic membrane bioreactor (A 2 O-MBR). An extreme gradient boosting (XGBoost) model was applied using a grid search strategy (Grid-XGBoost) to predict the removal of nutrients, including ammonium (NH4 ), total phosphorus (TP), and total nitrogen (TN). The models were validated against a commonly used multilayer perceptron (MLP) neural network. The input parameters were divided into operating conditions, including dissolved oxygen, oxidation-reduction potential, and mixed liquor suspended solids. These conditions were also partitioned based on influent characteristics such as NH4, TN, TP, total organic content, chemical oxygen demand, and suspended solids. A total of nine models were developed for each ML technique using the operating conditions and influent characteristics as separate datasets and combining them for each target nutrient. It was observed that using only operating conditions or influent characteristics as input parameters for XGBoost and MLP yielded poor results. Moreover, a significant improvement in the predictive efficacy of the model was observed when all parameters for the target nutrient removal predictions were considered. The prediction of NH4 by the XGBoost model had the highest R 2 values of 0.763, 0.814, and 0.876 when the operating conditions, influent characteristics, and combined dataset were used as input parameters, respectively. Overall, the ensemble XGBoost model demonstrated better performance than the MLP model in all cases. However, the performance of both the models was found to be inadequate for predicting TN and TP removal in any scenario. The proposed XGBoost model is a reliable and robust ML technique for predicting NH4 removal, which may contribute to decision-making in advance to improve the efficacy of an A 2 O-MBR system. Graphical abstract: Unlabelled Image Highlights: Predicted nutrients removal by membrane bioreactor at a sewage treatment plant. Adopted and tested the feasibility of machine learning (ML) models in this study. Investigated nine different modeling scenarios based on related parameters. Developed and compared two ML models such as multilayer perceptron and Extreme Gradient Boosting models.