Biochar-Augmented Anaerobic Digestion System: Insights from an Interpretable Stacking Ensemble Deep Learning

Muzammil Khan; K C Surendra; Sachita Baniya; Jay H Rhymer; Samir Kumar Khanal

doi:10.1021/acs.est.5c05051

Back

Biochar-Augmented Anaerobic Digestion System: Insights from an Interpretable Stacking Ensemble Deep Learning

Journal article

Open access

Peer reviewed

Biochar-Augmented Anaerobic Digestion System: Insights from an Interpretable Stacking Ensemble Deep Learning

Muzammil Khan, K C Surendra, Sachita Baniya, Jay H Rhymer and Samir Kumar Khanal

Environmental science & technology, Vol.59(29), pp.15236-15250

2025

DOI: https://doi.org/10.1021/acs.est.5c05051

PMID: 40676947

Files and links (1)

pdf

Published10.03 MBDownload View

CC BY V4.0, Open Access

Abstract

memetic algorithm

optimization

waste management

resource recovery

artificial intelligence

This study presents a comprehensive approach for optimizing biochar-augmented anaerobic digestion (AD) system through an interpretable stacking ensemble deep learning model. Extensive experimental data were compiled, incorporating feedstock characteristics, operational conditions, and biochar properties, alongside stability indicators such as pH, volatile fatty acid concentrations, alkalinity, and total ammonia nitrogen levels. The proposed model integrates different configurations of convolutional neural networks and long short-term memory networks within a stacking ensemble framework, effectively capturing complex interdependencies within the AD process and improving methane yield predictions. Optimized through advanced hyperparameter tuning, the model achieved high internal predictive accuracy (mean R2 of 0.91-0.94 and root-mean-square error of 60.85 mL CH4/g volatile solids) and demonstrated strong generalization with an R2 of 0.68 on external independent lab-scale datasets, outperforming all individual models. Post-hoc interpretability analysis using permutation importance and Shapley Additive Explanations (SHAP) identified critical factors influencing methane production and stability indicators. A model-based global optimization framework was implemented to tailor optimal operational conditions for real-world scenarios, ensuring high methane yield while maintaining process stability. Additionally, a user-friendly graphical interface was developed to facilitate the practical implementation of the predictive model. This work provides a robust framework for optimizing the AD process with biochar augmentation, enhancing resource recovery and waste management.

Details

Title: Biochar-Augmented Anaerobic Digestion System: Insights from an Interpretable Stacking Ensemble Deep Learning
Authors/Creators: Muzammil Khan - University of Hawaiʻi at Mānoa
K C Surendra - University of Hawaiʻi at Mānoa
Sachita Baniya - University of Hawaiʻi at Mānoa
Jay H Rhymer - Punahou School, 1601 Punahou St, Honolulu, Hawaii 96822, United States
Samir Kumar Khanal - Hong Kong University of Science and Technology
Publication Details: Environmental science & technology, Vol.59(29), pp.15236-15250
Publisher: ACS Publications
Number of pages: 15
Identifiers: 991005796260607891
Copyright: © 2025 The Authors.
Murdoch Affiliation: School of Engineering and Energy
Language: English
Resource Type: Journal article

UN Sustainable Development Goals (SDGs)

This output has contributed to the advancement of the following goals:

Source: InCites

Metrics

329 File views/ downloads

13 Record Views

5 Times Cited - Web of Science

InCites Highlights

These are selected metrics from InCites Benchmarking & Analytics tool, related to this output

Collaboration types: Domestic collaboration; International collaboration
Citation topics: 3 Agriculture, Environment & Ecology; 3.83 Bioengineering; 3.83.416 Anaerobic Digestion
Web Of Science research areas: Engineering, Environmental; Environmental Sciences
ESI research areas: Environment/Ecology