Machine learning modeling and analysis of biohydrogen production from wastewater by dark fermentation process.

Hosseinzadeh, A; Zhou, JL; Altaee, A; Li, D

Machine learning modeling and analysis of biohydrogen production from wastewater by dark fermentation process.

Hosseinzadeh, A Zhou, JL Altaee, A

Li, D

Permalink

Publisher:: Elsevier BV
Publication Type:: Journal Article
Citation:: Bioresource technology, 2021, pp. 126111
Issue Date:: 2021-10-11

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

The embargo period expires on 1 Oct 2023

Adobe PDF

Download Accepted Manuscript VersionAdobe PDF (1.02 MB)

View on publisher's site

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Hosseinzadeh, A
dc.contributor.author	Zhou, JL
dc.contributor.author	Altaee, A https://orcid.org/0000-0001-9764-3974
dc.contributor.author	Li, D
dc.date.accessioned	2021-10-16T22:18:15Z
dc.date.available	2021-10-07
dc.date.available	2021-10-16T22:18:15Z
dc.date.issued	2021-10-11
dc.identifier.citation	Bioresource technology, 2021, pp. 126111
dc.identifier.issn	0960-8524
dc.identifier.issn	1873-2976
dc.identifier.uri	http://hdl.handle.net/10453/151116
dc.description.abstract	Dark fermentation process for simultaneous wastewater treatment and H<sub>2</sub> production is gaining attention. This study aimed to use machine learning (ML) procedures to model and analyze H<sub>2</sub> production from wastewater during dark fermentation. Different ML procedures were assessed based on the mean squared error (MSE) and determination coefficient (R<sup>2</sup>) to select the most robust models for modeling the process. The research showed that gradient boosting machine (GBM), support vector machine (SVM), random forest (RF) and AdaBoost were the most appropriate models, which were optimized by grid search and deeply analyzed by permutation variable importance (PVI) to identify the relative importance of process variables. All four models demonstrated promising performances in predicting H<sub>2</sub> production with high R<sup>2</sup> values (0.893, 0.885, 0.902 and 0.889) and small MSE values (0.015, 0.015, 0.016 and 0.015). Moreover, RF-PVI demonstrated that acetate, butyrate, acetate/butyrate, ethanol, Fe and Ni were of high importance in decreasing order.
dc.format	Print-Electronic
dc.language	eng
dc.publisher	Elsevier BV
dc.relation.ispartof	Bioresource technology
dc.relation.isbasedon	10.1016/j.biortech.2021.126111
dc.rights	info:eu-repo/semantics/embargoedAccess
dc.subject.classification	Biotechnology
dc.title	Machine learning modeling and analysis of biohydrogen production from wastewater by dark fermentation process.
dc.type	Journal Article
utslib.location.activity	England
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Civil and Environmental Engineering
pubs.organisational-group	/University of Technology Sydney/Strength - CTWW - Centre for Technology in Water and Wastewater Treatment
utslib.copyright.status	open_access	*
utslib.copyright.embargo	2023-10-01T00:00:00+1000Z
dc.date.updated	2021-10-16T22:18:11Z
pubs.publication-status	Published

Abstract:

Dark fermentation process for simultaneous wastewater treatment and H₂ production is gaining attention. This study aimed to use machine learning (ML) procedures to model and analyze H₂ production from wastewater during dark fermentation. Different ML procedures were assessed based on the mean squared error (MSE) and determination coefficient (R²) to select the most robust models for modeling the process. The research showed that gradient boosting machine (GBM), support vector machine (SVM), random forest (RF) and AdaBoost were the most appropriate models, which were optimized by grid search and deeply analyzed by permutation variable importance (PVI) to identify the relative importance of process variables. All four models demonstrated promising performances in predicting H₂ production with high R² values (0.893, 0.885, 0.902 and 0.889) and small MSE values (0.015, 0.015, 0.016 and 0.015). Moreover, RF-PVI demonstrated that acetate, butyrate, acetate/butyrate, ethanol, Fe and Ni were of high importance in decreasing order.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/151116