1
|
Ganeshan P, Bose A, Lee J, Barathi S, Rajendran K. Machine learning for high solid anaerobic digestion: Performance prediction and optimization. BIORESOURCE TECHNOLOGY 2024; 400:130665. [PMID: 38582235 DOI: 10.1016/j.biortech.2024.130665] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 01/20/2024] [Revised: 04/02/2024] [Accepted: 04/04/2024] [Indexed: 04/08/2024]
Abstract
Biogas production through anaerobic digestion (AD) is one of the complex non-linear biological processes, wherein understanding its dynamics plays a crucial role towards process control and optimization. In this work, a machine learning based biogas predictive model was developed for high solid systems using algorithms, including SVM, ET, DT, GPR, and KNN and two different datasets (Dataset-1:10, Dataset-2:5 inputs). Support Vector Machine had the highest accuracy (R2) of all the algorithms at 91 % (Dataset-1) and 87 % (Dataset-2), respectively. The statistical analysis showed that there was no significant difference (p = 0.377) across the datasets, wherein with less inputs, accurate results could be predicted. In case of biogas yield, the critical factors which affect the model predictions include loading rate and retention time. The developed high solid machine learning model shows the possibility of integrating Artificial Intelligence to optimize and control AD process, thus contributing to a generic model for enhancing the overall performance of the biogas plant.
Collapse
Affiliation(s)
- Prabakaran Ganeshan
- Department of Environmental Science and Engineering, School of Engineering and Sciences, SRM University-AP, Amaravati, Andhra Pradesh 522240, India
| | - Archishman Bose
- Process and Chemical Engineering, School of Engineering and Architecture, University College Cork, Cork, Ireland; Environmental Research Institute, MaREI Centre, University College Cork, Cork, Ireland
| | - Jintae Lee
- School of Chemical Engineering, Yeungnam University, Gyeongsan, Gyeongbuk 38541, Republic of Korea
| | - Selvaraj Barathi
- School of Chemical Engineering, Yeungnam University, Gyeongsan, Gyeongbuk 38541, Republic of Korea.
| | - Karthik Rajendran
- Department of Environmental Science and Engineering, School of Engineering and Sciences, SRM University-AP, Amaravati, Andhra Pradesh 522240, India.
| |
Collapse
|
2
|
Esteves AF, Gonçalves AL, Vilar VJ, Pires JCM. Comparative assessment of microalgal growth kinetic models based on light intensity and biomass concentration. BIORESOURCE TECHNOLOGY 2024; 394:130167. [PMID: 38101550 DOI: 10.1016/j.biortech.2023.130167] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 11/06/2023] [Revised: 12/05/2023] [Accepted: 12/05/2023] [Indexed: 12/17/2023]
Abstract
The comprehensive evaluation and validation of mathematical models for microalgal growth dynamics are essential for improving cultivation efficiency and optimising photobioreactor design. A considerable gap in comprehending the relation between microalgal growth, light intensity and biomass concentration arises since many studies focus solely on associating one of these factors. This paper compares microalgal growth kinetic models, specifically focusing on the combined impact of light intensity and biomass concentration. Considering a dataset (experimental results and literature values) concerning Chlorella vulgaris, nine kinetic models were assessed. Bannister and Grima models presented the best fitting performance to experimental data (RMSE ≤ 0.050 d-1; R2≥0.804; d2≥0.943). Cultivation conditions conducting photoinhibition were identified in some kinetic models. After testing these models on independent datasets, Bannister and Grima models presented superior predictive performance (RMSE = 0.022-0.023 d-1; R2 = 0.878-0.884; d2: 0.976-0.975). The models provide valuable tools for predicting microalgal growth and optimising operational parameters, reducing the need for time-consuming and costly experiments.
Collapse
Affiliation(s)
- Ana F Esteves
- LEPABE - Laboratory for Process Engineering, Environment, Biotechnology and Energy, Faculty of Engineering, University of Porto, Rua Dr. Roberto Frias, 4200-465 Porto, Portugal; ALiCE - Associate Laboratory in Chemical Engineering, Faculty of Engineering, University of Porto, Rua Dr. Roberto Frias, 4200-465 Porto, Portugal; LSRE-LCM - Laboratory of Separation and Reaction Engineering - Laboratory of Catalysis and Materials, Faculty of Engineering, University of Porto, Rua Dr. Roberto Frias, 4200-465 Porto, Portugal.
| | - Ana L Gonçalves
- LEPABE - Laboratory for Process Engineering, Environment, Biotechnology and Energy, Faculty of Engineering, University of Porto, Rua Dr. Roberto Frias, 4200-465 Porto, Portugal; ALiCE - Associate Laboratory in Chemical Engineering, Faculty of Engineering, University of Porto, Rua Dr. Roberto Frias, 4200-465 Porto, Portugal; CITEVE - Technological Centre for the Textile and Clothing Industries of Portugal, Rua Fernando Mesquita, 2785, 4760-034 Vila Nova de Famalicão, Portugal
| | - Vítor J Vilar
- ALiCE - Associate Laboratory in Chemical Engineering, Faculty of Engineering, University of Porto, Rua Dr. Roberto Frias, 4200-465 Porto, Portugal; LSRE-LCM - Laboratory of Separation and Reaction Engineering - Laboratory of Catalysis and Materials, Faculty of Engineering, University of Porto, Rua Dr. Roberto Frias, 4200-465 Porto, Portugal
| | - José C M Pires
- LEPABE - Laboratory for Process Engineering, Environment, Biotechnology and Energy, Faculty of Engineering, University of Porto, Rua Dr. Roberto Frias, 4200-465 Porto, Portugal; ALiCE - Associate Laboratory in Chemical Engineering, Faculty of Engineering, University of Porto, Rua Dr. Roberto Frias, 4200-465 Porto, Portugal.
| |
Collapse
|
3
|
Ghazizade Fard M, Koupaie EH. Machine learning assisted modelling of anaerobic digestion of waste activated sludge coupled with hydrothermal pre-treatment. BIORESOURCE TECHNOLOGY 2024; 394:130255. [PMID: 38145767 DOI: 10.1016/j.biortech.2023.130255] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 10/21/2023] [Revised: 12/05/2023] [Accepted: 12/23/2023] [Indexed: 12/27/2023]
Abstract
This study utilizes decision-tree-based models, including Random Forest, XGBoost, artificial neural networks (ANNs), support vector machine regressors, and K nearest neighbors algorithms, to predict sludge solubilization and methane yield in hydrothermal pretreatment (HTP) coupled with anaerobic digestion (AD) processes. Analyzing two decades of published research, we find that ANN models exhibit superior fitting accuracy for solubilization prediction, while decision-tree models excel in methane yield prediction. Pretreatment temperature is identified as pivotal among various variables, and heating time surprisingly emerges as equally significant as holding time for solubilization and surpasses it for methane yield. Contrary to prior expectations, the HTP method's impact on sludge solubilization and AD performance is minimal. This study underscores data-driven models' potential as resource-efficient tools for optimizing advanced AD processes with HTP. Notably, our research spans nearly two decades of lab, pilot, and full-scale studies, offering novel insights not previously explored.
Collapse
Affiliation(s)
- Maryam Ghazizade Fard
- Waste & Wastewater Biorefinery Lab (WWBL), Department of Chemical Engineering, Queen's University, 19 Division Street, Kingston, ON K7L 2N9, Canada
| | - Ehssan H Koupaie
- Waste & Wastewater Biorefinery Lab (WWBL), Department of Chemical Engineering, Queen's University, 19 Division Street, Kingston, ON K7L 2N9, Canada.
| |
Collapse
|
4
|
Piadeh F, Offie I, Behzadian K, Bywater A, Campos LC. Real-time operation of municipal anaerobic digestion using an ensemble data mining framework. BIORESOURCE TECHNOLOGY 2024; 392:130017. [PMID: 37967795 DOI: 10.1016/j.biortech.2023.130017] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 08/23/2023] [Revised: 11/05/2023] [Accepted: 11/10/2023] [Indexed: 11/17/2023]
Abstract
This study presents a novel approach for real-time operation of anaerobic digestion using an ensemble decision-making framework composed of weak learner data mining models. The framework utilises simple but practical features such as waste composition, added water and feeding volume to predict biogas yield and to generate an optimised weekly operation pattern to maximise biogas production and minimise operational costs. The effectiveness of this framework is validated through a real-world case study conducted in the UK. Comparative analysis with benchmark models demonstrates a significant improvement in prediction accuracy, increasing from the range of 50-80% with benchmark models to 91% with the proposed framework. The results also show the efficacy of the weekly operation pattern, which leads to a substantial 78% increase in biogas generation during the testing period. Moreover, the pattern contributes to a reduction of 71% in total days required for feeding and 30% in total days required for pre-feeding.
Collapse
Affiliation(s)
- Farzad Piadeh
- School of Computing and Engineering, University of West London, London W5 5RF, United Kingdom; School of Physics, Engineering and Computer Science, University of Hertfordshire, Hatfield AL10 9AB, United Kingdom
| | - Ikechukwu Offie
- School of Computing and Engineering, University of West London, London W5 5RF, United Kingdom
| | - Kourosh Behzadian
- School of Computing and Engineering, University of West London, London W5 5RF, United Kingdom; Centre for Urban Sustainability and Resilience, Department of Civil, Environmental and Geomatic Engineering, University College London, London WC1E6BT, United Kingdom.
| | - Angela Bywater
- Water and Environmental Engineering Group, Faculty of Engineering and Physical Sciences, University of Southampton, Southampton, SO17 1BJ, UK
| | - Luiza C Campos
- Centre for Urban Sustainability and Resilience, Department of Civil, Environmental and Geomatic Engineering, University College London, London WC1E6BT, United Kingdom
| |
Collapse
|
5
|
Sharma V, Sharma D, Tsai ML, Ortizo RGG, Yadav A, Nargotra P, Chen CW, Sun PP, Dong CD. Insights into the recent advances of agro-industrial waste valorization for sustainable biogas production. BIORESOURCE TECHNOLOGY 2023; 390:129829. [PMID: 37839650 DOI: 10.1016/j.biortech.2023.129829] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 08/12/2023] [Revised: 10/03/2023] [Accepted: 10/03/2023] [Indexed: 10/17/2023]
Abstract
Recent years have seen a transition to a sustainable circular economy model that uses agro-industrial waste biomass waste to produce energy while reducing trash and greenhouse gas emissions. Biogas production from lignocellulosic biomass (LCB) is an alternative option in the hunt for clean and renewable fuels. Different approaches are employed to transform the LCB to biogas, including pretreatment, anaerobic digestion (AD), and biogas upgradation to biomethane. To maintain process stability and improve AD performance, machine learning (ML) tools are being applied in real-time monitoring, predicting, and optimizing the biogas production process. An environmental life cycle assessment approach for biogas production systems is essential to calculate greenhouse gas emissions. The current review presents a detailed overview of the utilization of agro-waste for sustainable biogas production. Different methods of waste biomass processing and valorization are discussed that contribute towards developing an efficient agro-waste to biogas-based circular economy.
Collapse
Affiliation(s)
- Vishal Sharma
- Department of Seafood Science, National Kaohsiung University of Science and Technology, Kaohsiung City, Taiwan; Department of Marine Environmental Engineering, National Kaohsiung University of Science and Technology, Kaohsiung City, Taiwan
| | - Diksha Sharma
- Department of Seafood Science, National Kaohsiung University of Science and Technology, Kaohsiung City, Taiwan
| | - Mei-Ling Tsai
- Department of Seafood Science, National Kaohsiung University of Science and Technology, Kaohsiung City, Taiwan
| | - Rhessa Grace Guanga Ortizo
- Department of Seafood Science, National Kaohsiung University of Science and Technology, Kaohsiung City, Taiwan
| | - Aditya Yadav
- Department of Seafood Science, National Kaohsiung University of Science and Technology, Kaohsiung City, Taiwan
| | - Parushi Nargotra
- Department of Seafood Science, National Kaohsiung University of Science and Technology, Kaohsiung City, Taiwan
| | - Chiu-Wen Chen
- Department of Marine Environmental Engineering, National Kaohsiung University of Science and Technology, Kaohsiung City, Taiwan; Institute of Aquatic Science and Technology, National Kaohsiung University of Science and Technology, Kaohsiung City, Taiwan
| | - Pei-Pei Sun
- Department of Seafood Science, National Kaohsiung University of Science and Technology, Kaohsiung City, Taiwan
| | - Cheng-Di Dong
- Department of Marine Environmental Engineering, National Kaohsiung University of Science and Technology, Kaohsiung City, Taiwan; Institute of Aquatic Science and Technology, National Kaohsiung University of Science and Technology, Kaohsiung City, Taiwan.
| |
Collapse
|