Performance prediction of ZVI-based anaerobic digestion reactor using machine learning algorithms. (15th February 2021)

• Record Type: Journal Article
• Authors: Xu, Weichao; Long, Fei; Zhao, He; Zhang, Yaobin; Liang, Dawei; Wang, Luguang; Lesnik, Keaton Larson; Cao, Hongbin; Zhang, Yuxiu; Liu, Hong
• Is Part Of: Waste management. Volume 121(2021)
• Page Start: 59
• Page End: 66
• Publication Date: 2021-02-15
• Subjects: Anaerobic digestion -- Zero-valent iron -- Machine learning -- Methane production -- Prediction; Hazardous wastes -- Periodicals; Refuse and refuse disposal -- Periodicals; 363.728
• DOI: 10.1016/j.wasman.2020.12.003
• Languages: English
• ISSNs: 0956-053X

Abstract

Graphical abstract: Highlights: Models using 3 ML algorithms were developed to predict performance of ZVI-based AD. Algorithm XGBoost achieved the highest accuracy in predicting total CH4 production. DL showed the lowest RMSE in predicting cumulative CH4 production curve. TSf, sCOD, ZVI dosage and particle size are key parameters affecting the CH4 yield. Abstract: The use of zero-valent iron (ZVI) to enhance anaerobic digestion (AD) systems is widely advocated as it improves methane production and system stability. Accurate modeling of ZVI-based AD reactor is conducive to predicting methane production potential, optimizing operational strategy, and gathering reference information for industrial design in place of time-consuming and laborious tests. In this study, three machine learning (ML) algorithms, namely random forest (RF), extreme gradient boosting (XGBoost), and deep learning (DL), were evaluated for their feasibility of predicting the performance of ZVI-based AD reactors based on the operating parameters collected in 9 published articles. XGBoost demonstrated the highest accuracy in predicting total methane production, with a root mean squared error (RMSE) of 21.09, compared to 26.03 and 27.35 of RF and DL, respectively. The accuracy represented by mean absolute percentage error also showed the same trend, with 14.26%, 15.14% and 17.82% for XGBoost, RF and DL, respectively. Through the feature importance generated by XGBoost, the parameters of total solid of feedstock (TSf ), sCOD, ZVI dosage and particle size were identified as the dominant parameters that affect the methane production, with feature importance weights of 0.339, 0.238, 0.158, and 0.116, respectively. The digestion time was further introduced into the above-established model to predict the cumulative methane production. With the expansion of training dataset, DL outperformed XGBoost and RF to show the lowest RMSEs of 11.83 and 5.82 in the control and ZVI-added reactors, respectively. This study demonstrates the potential of using ML algorithms to model ZVI-based AD reactors.