Related references
Note: Only part of the references are listed.
Article
Environmental Sciences
Johannes Sappl et al.
Summary: In this study, a novel Temporal Fusion Transformer model was calibrated based on six years of data to predict biogas production in wastewater treatment plants. The model provides accurate and stable forecasts, making it a valuable tool for operational management.
SCIENCE OF THE TOTAL ENVIRONMENT
(2023)
Article
Engineering, Environmental
Ikechukwu Offie et al.
Summary: This paper presents an artificial intelligence-based framework for predicting and optimizing biogas generated from a micro-AD plant. The framework improves biogas production efficiency and identifies the optimal feeding pattern. Results demonstrate increased biogas productivity and reduced operational costs.
Review
Agricultural Engineering
Muzammil Khan et al.
Summary: Anaerobic co-digestion (AcoD) offers various advantages in terms of better digestibility, process stability, and increased methane yield. However, the efficient operation of an AcoD system requires a comprehensive understanding of important operational parameters and monitoring processes can be tedious. Artificial intelligence (AI) has emerged as an innovative approach to optimize and control the AcoD process. This review discusses the applications of AI in AcoD process optimization, control, prediction, and real-time monitoring, as well as the comparison of different AI algorithms.
BIORESOURCE TECHNOLOGY
(2023)
Review
Agricultural Engineering
Rohit Gupta et al.
Summary: Anaerobic digestion is a promising technology for sustainable waste management by recovering value-added resources from organic waste. The performance of anaerobic digestion is influenced by various factors, necessitating the development of suitable modeling and optimization tools, such as machine learning approaches. This review highlights the latest progress in black-box machine learning methods for anaerobic digestion modeling, focusing on interpretability metrics and discussing various applications of machine learning in this field.
BIORESOURCE TECHNOLOGY
(2023)
Article
Agricultural Engineering
Anuchit Sonwai et al.
Summary: In this study, machine learning was used to predict the specific methane yields (SMY) using 14 features from lignocellulosic biomass (LB) characteristics and operating conditions in completely mixed reactors. The random forest (RF) model performed the best with a coefficient of determination (R2) of 0.85 and root mean square error (RMSE) of 0.06. Biomass compositions, particularly cellulose, had a significant influence on SMYs from LB. The RF model was also used to assess the impact of LB to manure ratio and determine the optimum ratio of 1:1 under typical organic loading rates (OLR). Experimental results confirmed the influential factors identified by the RF model and achieved a highest SMY of 79.2% of the predicted value. This work demonstrates the successful application of machine learning for anaerobic digestion modeling and optimization specifically for LB.
BIORESOURCE TECHNOLOGY
(2023)
Article
Environmental Sciences
Oznur Yildirim et al.
Review
Agricultural Engineering
Zhengxin Wang et al.
Summary: The development and application of bioenergy and biofuels conversion technology are crucial for producing renewable and sustainable energy sources in the future. However, due to the complexity of bioenergy systems and human limitations in understanding, machine learning provides new opportunities. The latest advances in machine learning assisted bioenergy technology show great potential in driving the development of a new generation of bioenergy and biofuels conversion technologies in the future.
BIORESOURCE TECHNOLOGY
(2022)
Article
Engineering, Environmental
Zeinab Masalegooyan et al.
Summary: This paper presents a new framework for evaluating the risk probability of major fires in landfills using fuzzy fault tree analysis, and demonstrates its effectiveness through a real-world case study.
PROCESS SAFETY AND ENVIRONMENTAL PROTECTION
(2022)
Review
Energy & Fuels
Moses Oluwatobi Fajobi et al.
Summary: Energy is crucial for domestic and industrial activities, but its reliance on conventional sources leads to environmental issues. This study explores the use of alternative energy sources like biogas and analyzes the effects of different biomass on biogas production. The study also evaluates the application of artificial intelligence in modeling and optimizing the anaerobic digestion process. The results show that pre-treatment methods can significantly affect biogas yield, and AI models have high accuracy in predicting biogas production.
ENERGY SOURCES PART A-RECOVERY UTILIZATION AND ENVIRONMENTAL EFFECTS
(2022)
Article
Agricultural Engineering
Ru Jia et al.
Summary: The study investigates the use of deep learning models to predict the state and performance variables of anaerobic digestion, with the combined model of CNN and bidirectional LSTM showing robust predictive ability and generalization.
BIORESOURCE TECHNOLOGY
(2022)
Article
Engineering, Environmental
Pezhman Kazemi et al.
Summary: This study proposes a practical data-driven framework for fault detection in anaerobic digestion process, based on predicting VFA concentration and validated using advanced techniques. The results demonstrate the good performance and feasibility of the framework in terms of fault detection.
PROCESS SAFETY AND ENVIRONMENTAL PROTECTION
(2021)
Article
Engineering, Environmental
Weichao Xu et al.
Summary: The study evaluates three machine learning algorithms for predicting the performance of ZVI-based AD reactors and finds XGBoost to have the highest accuracy. Parameters like total solid of feedstock, sCOD, ZVI dosage, and particle size were identified as dominant factors affecting methane production. Deep learning outperformed XGBoost and random forest with the lowest root mean squared errors for predicting cumulative methane production.
Review
Agricultural Engineering
Ianny A. Cruz et al.
Summary: Anaerobic digestion is a traditional process for managing organic waste and generating renewable energy, but it is vulnerable to microbial community interactions and process disturbances. Real-time monitoring is crucial for stable processes and high yields, although cost remains a limiting factor in its industrial application.
BIOSYSTEMS ENGINEERING
(2021)
Review
Engineering, Chemical
Pengfei Yan et al.
Summary: Anaerobic digestion process requires real-time monitoring of key variables to improve efficiency and stability. However, the current market real-time monitoring equipment has limitations, leading to the necessity of soft sensor modeling as a solution.
Article
Agricultural Engineering
Luguang Wang et al.
BIORESOURCE TECHNOLOGY
(2020)
Article
Environmental Sciences
Djavan De Clercq et al.
SCIENCE OF THE TOTAL ENVIRONMENT
(2020)
Article
Energy & Fuels
Fares Almomani
Article
Environmental Sciences
V Orzi et al.
SCIENCE OF THE TOTAL ENVIRONMENT
(2018)
