Fast identification of fluorescent components in three-dimensional excitation-emission matrix fluorescence spectra via deep learning

Xu, RZ; Cao, JS; Feng, G; Luo, JY; Feng, Q; Ni, BJ; Fang, F

Fast identification of fluorescent components in three-dimensional excitation-emission matrix fluorescence spectra via deep learning

Xu, RZ Cao, JS Feng, G Luo, JY Feng, Q Ni, BJ Fang, F

Permalink

Publisher:: ELSEVIER SCIENCE SA
Publication Type:: Journal Article
Citation:: Chemical Engineering Journal, 2022, 430
Issue Date:: 2022-02-15

Closed Access

	Filename	Description	Size
	Fast identification of fluorescent components in three-dimensional excitation-emission matrix fluorescence spectra via deep learning.pdf	Published version	3.66 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Xu, RZ
dc.contributor.author	Cao, JS
dc.contributor.author	Feng, G
dc.contributor.author	Luo, JY
dc.contributor.author	Feng, Q
dc.contributor.author	Ni, BJ
dc.contributor.author	Fang, F
dc.date.accessioned	2023-03-23T22:20:43Z
dc.date.available	2023-03-23T22:20:43Z
dc.date.issued	2022-02-15
dc.identifier.citation	Chemical Engineering Journal, 2022, 430
dc.identifier.issn	1385-8947
dc.identifier.issn	1873-3212
dc.identifier.uri	http://hdl.handle.net/10453/168249
dc.description.abstract	Three-dimensional excitation-emission matrix (3D-EEM) fluorescence spectroscopy has been widely applied to detect the fluorescent components in samples from natural water bodies to wastewater treatment processes. Data interpretation methods such as parallel factor analysis (PARAFAC) are required to decompose the overlapped fluorescent signals in the 3D-EEM spectra. However, strict requirements of data and complicated procedures of the PARAFAC limit the online monitoring and analysis of samples. Here we develop a fast fluorescent identification network (FFI-Net) model based on the deep learning approach to fast predict the numbers and maps of fluorescent components by simply inputting a single 3D-EEM spectrum. Two types of convolutional neural networks (CNN) are trained to classify the numbers of fluorescent components with an accuracy of 0.956 and predict the maps of fluorescent components with the min mean absolute error of 8.9 × 10-4. We demonstrate that the accuracy of the FFI-Net model will be further improved when more 3D-EEM data are available as a training dataset. Meanwhile, a user-friendly interface is designed to facilitate practical applications. Our approach gives a robust way to overcome the shortage of the PARAFAC and provides a new platform for online analysis of the fluorescent components in water samples.
dc.language	English
dc.publisher	ELSEVIER SCIENCE SA
dc.relation.ispartof	Chemical Engineering Journal
dc.relation.isbasedon	10.1016/j.cej.2021.132893
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject	0904 Chemical Engineering, 0905 Civil Engineering, 0907 Environmental Engineering
dc.subject.classification	Chemical Engineering
dc.title	Fast identification of fluorescent components in three-dimensional excitation-emission matrix fluorescence spectra via deep learning
dc.type	Journal Article
utslib.citation.volume	430
utslib.for	0904 Chemical Engineering
utslib.for	0905 Civil Engineering
utslib.for	0907 Environmental Engineering
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	closed_access	*
dc.date.updated	2023-03-23T22:20:41Z
pubs.publication-status	Published
pubs.volume	430

Abstract:

Three-dimensional excitation-emission matrix (3D-EEM) fluorescence spectroscopy has been widely applied to detect the fluorescent components in samples from natural water bodies to wastewater treatment processes. Data interpretation methods such as parallel factor analysis (PARAFAC) are required to decompose the overlapped fluorescent signals in the 3D-EEM spectra. However, strict requirements of data and complicated procedures of the PARAFAC limit the online monitoring and analysis of samples. Here we develop a fast fluorescent identification network (FFI-Net) model based on the deep learning approach to fast predict the numbers and maps of fluorescent components by simply inputting a single 3D-EEM spectrum. Two types of convolutional neural networks (CNN) are trained to classify the numbers of fluorescent components with an accuracy of 0.956 and predict the maps of fluorescent components with the min mean absolute error of 8.9 × 10-4. We demonstrate that the accuracy of the FFI-Net model will be further improved when more 3D-EEM data are available as a training dataset. Meanwhile, a user-friendly interface is designed to facilitate practical applications. Our approach gives a robust way to overcome the shortage of the PARAFAC and provides a new platform for online analysis of the fluorescent components in water samples.

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

http://hdl.handle.net/10453/168249