Fuel properties of hydrochar and pyrochar: Prediction and exploration with machine learning. (1st July 2020)

• Record Type: Journal Article
• Authors: Li, Jie; Pan, Lanjia; Suvarna, Manu; Tong, Yen Wah; Wang, Xiaonan
• Is Part Of: Applied energy. Volume 269(2020)
• Publication Date: 2020-07-01
• Subjects: Biochar -- Waste to energy -- Pyrolysis -- Hydrothermal carbonization -- Machine learning -- Multi-task prediction; Power (Mechanics) -- Periodicals; Energy conservation -- Periodicals; Energy conversion -- Periodicals; 621.042
• DOI: 10.1016/j.apenergy.2020.115166
• Languages: English
• ISSNs: 0306-2619

Abstract

Graphical abstract: Highlights: Datasets for hydrochar and pyrochar were compiled by systematic literature review. Machine learning models with multi-task prediction were developed and optimized. Fuel properties of chars were predicted by optimal models with R 2 of ~0.90. Feature impacts on targets were explored with model explainer based on game theory. Performance of models was further improved after feature re-examination. Abstract: Conversion of wet organic wastes into renewable energy is a promising way to substitute fossil fuels and avoid environmental deterioration. Hydrothermal carbonization and pyrolysis can convert wet organic wastes into hydrochar and pyrochar, which are potential fossil fuel alternatives due to their comparable fuel properties. Machine learning (ML) has strong prediction ability after being trained with historic dataset and facilitates good understanding of the impact of input features on output targets through a data-driven approach. In this study, ML models for multi-task prediction of fuel properties of the chars were developed and optimized based on two datasets for hydrochar and pyrochar. Feature importance and correlation were explored based on optimized ML model, and feature re-examination was conducted for model improvement. Results showed that support vector regression model with optimal hyper-parameters exhibited better generalized performance for prediction of both hydrochar and pyrochar properties with the best average R 2 of 0.90 and 0.94. ML-based feature analysis indicated that process temperature and carbon content in the feedstock were the significant features impacting fuel properties of both chars, while nitrogen content was another important input feature for hydrochar and hydrogen content for pyrochar. The accuracy (especially for pyrochar), generalization ability, and computational speed of models were further improved after feature re-examination. The intuitions obtained from feature analysis provided meaningful insights to select input features for prediction performance improvement and computational cost saving, and might guide experiments to produce chars with desired quality.