Characteristics prediction of hydrothermal biochar using data enhanced interpretable machine learning. (June 2023)

• Record Type: Journal Article
• Authors: Chen, Chao; Wang, Zhi; Ge, Yadong; Liang, Rui; Hou, Donghao; Tao, Junyu; Yan, Beibei; Zheng, Wandong; Velichkova, Rositsa; Chen, Guanyi
• Is Part Of: Bioresource technology. Volume 377(2023)
• Publication Date: 2023-06
• Subjects: Hydrothermal carbonization -- Random forest -- Correlation analysis -- Feature analysis; Biomass -- Periodicals; Biomass energy -- Periodicals; Bioremediation -- Periodicals; Agricultural wastes -- Periodicals; Factory and trade waste -- Periodicals; Organic wastes -- Periodicals; Bioénergie -- Périodiques; Déchets agricoles -- Périodiques; Déchets industriels -- Périodiques; Déchets organiques -- Périodiques; Déchets (Combustible) -- Périodiques; 662.88
• DOI: 10.1016/j.biortech.2023.128893
• Languages: English
• ISSNs: 0960-8524

Abstract

Graphical abstract: Highlights: Data enhanced interpretable machine learning was used to predict biochar property. Data enhancement improved model accuracies in average from 5.8% to 15.8%. The optimal RF model showed Accuracy average of 94.89%, outperforming SVM and ANN. Sensitivity analysis provided informative insights for the predicting mechanism. The results could enhance the design of hydrothermal biochar production systems. Abstract: Hydrothermal biochar is a promising sustainable soil remediation agent for plant growth. Demands for biochar properties differ due to the diversity of soil environment. In order to achieve accurate biochar properties prediction and overcome the interpretability bottleneck of machine learning models, this study established a series of data-enhanced machine learning models and conducted relevant sensitivity analysis. Compared with traditional support vector machine, artificial neural network, and random forest models, the accuracy after data enhancement increased in average from 5.8% to 15.8%, where the optimal random forest model showed the average of accuracy was 94.89%. According to sensitivity analysis results, the essential factors influencing the predicting results of the models were reaction temperature, reaction pressure, and specific element of biomass feedstock. As a result, data-enhanced interpretable machine learning proved promising for the characteristics prediction of hydrothermal biochar.