Automated machine learning-based prediction of microplastics induced impacts on methane production in anaerobic digestion. (1st September 2022)

• Record Type: Journal Article
• Authors: Xu, Run-Ze; Cao, Jia-Shun; Ye, Tian; Wang, Su-Na; Luo, Jing-Yang; Ni, Bing-Jie; Fang, Fang
• Is Part Of: Water research. Volume 223(2022)
• Publication Date: 2022-09-01
• Subjects: Microplastics -- Automated machine learning -- Anaerobic digestion -- Methane production -- Explainable analysis; AutoML automated machine learning -- EDA exploratory data analysis -- GAMA genetic automated machine learning assistant -- GBM gradient boosting machines -- MAE mean absolute error -- MSE mean squared error -- PDP partial dependence plots -- PPMC Pearson product-moment correlation coefficient -- RMSE root mean squared error -- ROS reactive oxygen species -- SHAP Shapley additive explanations -- TPOT tree-based pipeline optimization tool -- WAS waste activated sludge; Water -- Pollution -- Research -- Periodicals; 363.7394
• DOI: 10.1016/j.watres.2022.118975
• Languages: English
• ISSNs: 0043-1354

Abstract

Highlights: Methane production was predicted by AutoML algorithms based on microplastic dataset. GBM-based models showed better prediction performance than neural networks. The order of variable importance was determined by integrated explainable methods. The variable of microplastic types dominated the prediction of methane production. Increasing microplastic diameter and concentration inhibited methane production. Abstract: Microplastics as emerging pollutants have been heavily accumulated in the waste activated sludge (WAS) during biological wastewater treatment, which showed significantly diverse impacts on the subsequent anaerobic sludge digestion for methane production. However, a robust modeling approach for predicting and unveiling the complex effects of accumulated microplastics within WAS on methane production is still missing. In this study, four automated machine learning (AutoML) approach was applied to model the effects of microplastics on anaerobic digestion processes, and integrated explainable analysis was explored to reveal the relationships between key variables ( e.g., concentration, type, and size of microplastics) and methane production. The results showed that the gradient boosting machine had better prediction performance (mean squared error (MSE) = 17.0) than common neural networks models (MSE = 58.0), demonstrating that the AutoML algorithms succeeded in predicting the methane production and could select the best machine learning model without human intervention. Explainable analysis results indicated that the variable of microplastic types was more important than the variable of microplastic diameter and concentration. The existence of polystyrene was associated with higher methane production, whereas increasing microplastic diameter and concentration both inhibited methane production. This work also provided a novel modeling approach for comprehensively understanding the complex effects of microplastics on methane production, which revealed the dependence relationships between methane production and key variables and may be served as a reference for optimizing operational adjustments in anaerobic digestion processes. Graphical abstract: Image, graphical abstract