Loading…
A novel method for multi-pollutant monitoring in water supply systems using chemical machine vision
Drinking water is vital for human health and life, but detecting multiple contaminants in it is challenging. Traditional testing methods are both time-consuming and labor-intensive, lacking the ability to capture abrupt changes in water quality over brief intervals. This paper proposes a direct anal...
Saved in:
| Published in: | Environmental science and pollution research international 2024-04, Vol.31 (18), p.26555-26566 |
|---|---|
| Main Authors: | , , , , , , , , |
| Format: | Article |
| Language: | English |
| Subjects: | |
| Citations: | Items that this one cites |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| cited_by | |
|---|---|
| cites | cdi_FETCH-LOGICAL-c326t-94872390c912223ea9cdfb5d6e0c2bc6921b27ba56a71499063dcc283705380d3 |
| container_end_page | 26566 |
| container_issue | 18 |
| container_start_page | 26555 |
| container_title | Environmental science and pollution research international |
| container_volume | 31 |
| creator | Yan, Jiacong Lee, Jianchao Liu, Lu Duan, Qiannan Lei, Jingzheng Fu, Zhizhi Zhou, Chi Wu, WeiDong Wang, Fei |
| description | Drinking water is vital for human health and life, but detecting multiple contaminants in it is challenging. Traditional testing methods are both time-consuming and labor-intensive, lacking the ability to capture abrupt changes in water quality over brief intervals. This paper proposes a direct analysis and rapid detection method of three indicators of arsenic, cadmium, and selenium in complex drinking water systems by combining a novel long-path spectral imager with machine learning models. Our technique can obtain multiple parameters in about 1 s. The experiment involved setting up samples from various drinking water backgrounds and mixed groups, totaling 9360 injections. A raw visible light source ranging from 380 to 780 nm was utilized, uniformly dispersing light into the sample cell through a filter. The residual beam was captured by a high-definition camera, forming a distinctive spectrum. Three deep learning models—ResNet-50, SqueezeNet V1.1, and GoogLeNet Inception V1—were employed. Datasets were divided into training, validation, and test sets in a 6:2:2 ratio, and prediction performance across different datasets was assessed using the coefficient of determination and root mean square error. The experimental results show that a well-trained machine learning model can extract a lot of feature image information and quickly predict multi-dimensional drinking water indicators with almost no preprocessing. The model’s prediction performance is stable under different background drinking water systems. The method is accurate, efficient, and real-time and can be widely used in actual water supply systems. This study can improve the efficiency of water quality monitoring and treatment in water supply systems, and the method’s potential for environmental monitoring, food safety, industrial testing, and other fields can be further explored in the future. |
| doi_str_mv | 10.1007/s11356-024-32791-3 |
| format | article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_2942185725</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>3046977062</sourcerecordid><originalsourceid>FETCH-LOGICAL-c326t-94872390c912223ea9cdfb5d6e0c2bc6921b27ba56a71499063dcc283705380d3</originalsourceid><addsrcrecordid>eNp9kU1P3DAQhi1UxC4ff6CHyhIXLin2OLHj4wq1FGmlXuBsOY6XNUrsYDug_ff1srRFPfQ0I80z73y8CH2m5CslRFwnSlnDKwJ1xUBIWrEjtKSc1pWopfz0IV-g05SeCAEiQZygBWvruhVcLpFZYR9e7IBHm7ehx5sQ8TgP2VVTGIY5a5_xGLzLITr_iJ3HrzrbiNM8TcMOp13Kdkx4Tvuq2drRGV3EtNk6b_GLSy74c3S80UOyF-_xDD18_3Z_86Na_7y9u1mtK8OA50qWlYBJYiQFAGa1NP2ma3puiYHOcAm0A9HphmtBy1GEs94YaJkgDWtJz87Q1UF3iuF5timr0SVjh0F7G-akQNZA20ZAU9DLf9CnMEdftlOM1FwKQTgUCg6UiSGlaDdqim7UcacoUXsL1MECVSxQbxYoVpq-vEvP3Wj7Py2_f14AdgDStP-pjX9n_0f2Fz6ZkZA</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3046977062</pqid></control><display><type>article</type><title>A novel method for multi-pollutant monitoring in water supply systems using chemical machine vision</title><source>Springer Link</source><creator>Yan, Jiacong ; Lee, Jianchao ; Liu, Lu ; Duan, Qiannan ; Lei, Jingzheng ; Fu, Zhizhi ; Zhou, Chi ; Wu, WeiDong ; Wang, Fei</creator><creatorcontrib>Yan, Jiacong ; Lee, Jianchao ; Liu, Lu ; Duan, Qiannan ; Lei, Jingzheng ; Fu, Zhizhi ; Zhou, Chi ; Wu, WeiDong ; Wang, Fei</creatorcontrib><description>Drinking water is vital for human health and life, but detecting multiple contaminants in it is challenging. Traditional testing methods are both time-consuming and labor-intensive, lacking the ability to capture abrupt changes in water quality over brief intervals. This paper proposes a direct analysis and rapid detection method of three indicators of arsenic, cadmium, and selenium in complex drinking water systems by combining a novel long-path spectral imager with machine learning models. Our technique can obtain multiple parameters in about 1 s. The experiment involved setting up samples from various drinking water backgrounds and mixed groups, totaling 9360 injections. A raw visible light source ranging from 380 to 780 nm was utilized, uniformly dispersing light into the sample cell through a filter. The residual beam was captured by a high-definition camera, forming a distinctive spectrum. Three deep learning models—ResNet-50, SqueezeNet V1.1, and GoogLeNet Inception V1—were employed. Datasets were divided into training, validation, and test sets in a 6:2:2 ratio, and prediction performance across different datasets was assessed using the coefficient of determination and root mean square error. The experimental results show that a well-trained machine learning model can extract a lot of feature image information and quickly predict multi-dimensional drinking water indicators with almost no preprocessing. The model’s prediction performance is stable under different background drinking water systems. The method is accurate, efficient, and real-time and can be widely used in actual water supply systems. This study can improve the efficiency of water quality monitoring and treatment in water supply systems, and the method’s potential for environmental monitoring, food safety, industrial testing, and other fields can be further explored in the future.</description><identifier>ISSN: 1614-7499</identifier><identifier>ISSN: 0944-1344</identifier><identifier>EISSN: 1614-7499</identifier><identifier>DOI: 10.1007/s11356-024-32791-3</identifier><identifier>PMID: 38448769</identifier><language>eng</language><publisher>Berlin/Heidelberg: Springer Berlin Heidelberg</publisher><subject>Aquatic Pollution ; Arsenic ; Arsenic - analysis ; Atmospheric Protection/Air Quality Control/Air Pollution ; Cadmium ; Cadmium - analysis ; Contaminants ; Datasets ; Deep learning ; Drinking water ; Drinking Water - chemistry ; Earth and Environmental Science ; Ecotoxicology ; Environment ; Environmental Chemistry ; Environmental Health ; Environmental monitoring ; Environmental Monitoring - methods ; Food industry ; Food safety ; High definition ; Indicators ; Learning algorithms ; Light sources ; Machine Learning ; Machine vision ; Performance prediction ; Pollution monitoring ; Research Article ; Selenium ; Waste Water Technology ; Water conveyance ; Water Management ; Water monitoring ; Water Pollutants, Chemical - analysis ; Water pollution ; Water Pollution Control ; Water Quality ; Water quality management ; Water Supply ; Water supply systems</subject><ispartof>Environmental science and pollution research international, 2024-04, Vol.31 (18), p.26555-26566</ispartof><rights>The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.</rights><rights>2024. The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c326t-94872390c912223ea9cdfb5d6e0c2bc6921b27ba56a71499063dcc283705380d3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>315,786,790,27957,27958</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/38448769$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Yan, Jiacong</creatorcontrib><creatorcontrib>Lee, Jianchao</creatorcontrib><creatorcontrib>Liu, Lu</creatorcontrib><creatorcontrib>Duan, Qiannan</creatorcontrib><creatorcontrib>Lei, Jingzheng</creatorcontrib><creatorcontrib>Fu, Zhizhi</creatorcontrib><creatorcontrib>Zhou, Chi</creatorcontrib><creatorcontrib>Wu, WeiDong</creatorcontrib><creatorcontrib>Wang, Fei</creatorcontrib><title>A novel method for multi-pollutant monitoring in water supply systems using chemical machine vision</title><title>Environmental science and pollution research international</title><addtitle>Environ Sci Pollut Res</addtitle><addtitle>Environ Sci Pollut Res Int</addtitle><description>Drinking water is vital for human health and life, but detecting multiple contaminants in it is challenging. Traditional testing methods are both time-consuming and labor-intensive, lacking the ability to capture abrupt changes in water quality over brief intervals. This paper proposes a direct analysis and rapid detection method of three indicators of arsenic, cadmium, and selenium in complex drinking water systems by combining a novel long-path spectral imager with machine learning models. Our technique can obtain multiple parameters in about 1 s. The experiment involved setting up samples from various drinking water backgrounds and mixed groups, totaling 9360 injections. A raw visible light source ranging from 380 to 780 nm was utilized, uniformly dispersing light into the sample cell through a filter. The residual beam was captured by a high-definition camera, forming a distinctive spectrum. Three deep learning models—ResNet-50, SqueezeNet V1.1, and GoogLeNet Inception V1—were employed. Datasets were divided into training, validation, and test sets in a 6:2:2 ratio, and prediction performance across different datasets was assessed using the coefficient of determination and root mean square error. The experimental results show that a well-trained machine learning model can extract a lot of feature image information and quickly predict multi-dimensional drinking water indicators with almost no preprocessing. The model’s prediction performance is stable under different background drinking water systems. The method is accurate, efficient, and real-time and can be widely used in actual water supply systems. This study can improve the efficiency of water quality monitoring and treatment in water supply systems, and the method’s potential for environmental monitoring, food safety, industrial testing, and other fields can be further explored in the future.</description><subject>Aquatic Pollution</subject><subject>Arsenic</subject><subject>Arsenic - analysis</subject><subject>Atmospheric Protection/Air Quality Control/Air Pollution</subject><subject>Cadmium</subject><subject>Cadmium - analysis</subject><subject>Contaminants</subject><subject>Datasets</subject><subject>Deep learning</subject><subject>Drinking water</subject><subject>Drinking Water - chemistry</subject><subject>Earth and Environmental Science</subject><subject>Ecotoxicology</subject><subject>Environment</subject><subject>Environmental Chemistry</subject><subject>Environmental Health</subject><subject>Environmental monitoring</subject><subject>Environmental Monitoring - methods</subject><subject>Food industry</subject><subject>Food safety</subject><subject>High definition</subject><subject>Indicators</subject><subject>Learning algorithms</subject><subject>Light sources</subject><subject>Machine Learning</subject><subject>Machine vision</subject><subject>Performance prediction</subject><subject>Pollution monitoring</subject><subject>Research Article</subject><subject>Selenium</subject><subject>Waste Water Technology</subject><subject>Water conveyance</subject><subject>Water Management</subject><subject>Water monitoring</subject><subject>Water Pollutants, Chemical - analysis</subject><subject>Water pollution</subject><subject>Water Pollution Control</subject><subject>Water Quality</subject><subject>Water quality management</subject><subject>Water Supply</subject><subject>Water supply systems</subject><issn>1614-7499</issn><issn>0944-1344</issn><issn>1614-7499</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><recordid>eNp9kU1P3DAQhi1UxC4ff6CHyhIXLin2OLHj4wq1FGmlXuBsOY6XNUrsYDug_ff1srRFPfQ0I80z73y8CH2m5CslRFwnSlnDKwJ1xUBIWrEjtKSc1pWopfz0IV-g05SeCAEiQZygBWvruhVcLpFZYR9e7IBHm7ehx5sQ8TgP2VVTGIY5a5_xGLzLITr_iJ3HrzrbiNM8TcMOp13Kdkx4Tvuq2drRGV3EtNk6b_GLSy74c3S80UOyF-_xDD18_3Z_86Na_7y9u1mtK8OA50qWlYBJYiQFAGa1NP2ma3puiYHOcAm0A9HphmtBy1GEs94YaJkgDWtJz87Q1UF3iuF5timr0SVjh0F7G-akQNZA20ZAU9DLf9CnMEdftlOM1FwKQTgUCg6UiSGlaDdqim7UcacoUXsL1MECVSxQbxYoVpq-vEvP3Wj7Py2_f14AdgDStP-pjX9n_0f2Fz6ZkZA</recordid><startdate>20240401</startdate><enddate>20240401</enddate><creator>Yan, Jiacong</creator><creator>Lee, Jianchao</creator><creator>Liu, Lu</creator><creator>Duan, Qiannan</creator><creator>Lei, Jingzheng</creator><creator>Fu, Zhizhi</creator><creator>Zhou, Chi</creator><creator>Wu, WeiDong</creator><creator>Wang, Fei</creator><general>Springer Berlin Heidelberg</general><general>Springer Nature B.V</general><scope>CGR</scope><scope>CUY</scope><scope>CVF</scope><scope>ECM</scope><scope>EIF</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7QL</scope><scope>7SN</scope><scope>7T7</scope><scope>7TV</scope><scope>7U7</scope><scope>8FD</scope><scope>C1K</scope><scope>FR3</scope><scope>K9.</scope><scope>M7N</scope><scope>P64</scope><scope>7X8</scope></search><sort><creationdate>20240401</creationdate><title>A novel method for multi-pollutant monitoring in water supply systems using chemical machine vision</title><author>Yan, Jiacong ; Lee, Jianchao ; Liu, Lu ; Duan, Qiannan ; Lei, Jingzheng ; Fu, Zhizhi ; Zhou, Chi ; Wu, WeiDong ; Wang, Fei</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c326t-94872390c912223ea9cdfb5d6e0c2bc6921b27ba56a71499063dcc283705380d3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Aquatic Pollution</topic><topic>Arsenic</topic><topic>Arsenic - analysis</topic><topic>Atmospheric Protection/Air Quality Control/Air Pollution</topic><topic>Cadmium</topic><topic>Cadmium - analysis</topic><topic>Contaminants</topic><topic>Datasets</topic><topic>Deep learning</topic><topic>Drinking water</topic><topic>Drinking Water - chemistry</topic><topic>Earth and Environmental Science</topic><topic>Ecotoxicology</topic><topic>Environment</topic><topic>Environmental Chemistry</topic><topic>Environmental Health</topic><topic>Environmental monitoring</topic><topic>Environmental Monitoring - methods</topic><topic>Food industry</topic><topic>Food safety</topic><topic>High definition</topic><topic>Indicators</topic><topic>Learning algorithms</topic><topic>Light sources</topic><topic>Machine Learning</topic><topic>Machine vision</topic><topic>Performance prediction</topic><topic>Pollution monitoring</topic><topic>Research Article</topic><topic>Selenium</topic><topic>Waste Water Technology</topic><topic>Water conveyance</topic><topic>Water Management</topic><topic>Water monitoring</topic><topic>Water Pollutants, Chemical - analysis</topic><topic>Water pollution</topic><topic>Water Pollution Control</topic><topic>Water Quality</topic><topic>Water quality management</topic><topic>Water Supply</topic><topic>Water supply systems</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Yan, Jiacong</creatorcontrib><creatorcontrib>Lee, Jianchao</creatorcontrib><creatorcontrib>Liu, Lu</creatorcontrib><creatorcontrib>Duan, Qiannan</creatorcontrib><creatorcontrib>Lei, Jingzheng</creatorcontrib><creatorcontrib>Fu, Zhizhi</creatorcontrib><creatorcontrib>Zhou, Chi</creatorcontrib><creatorcontrib>Wu, WeiDong</creatorcontrib><creatorcontrib>Wang, Fei</creatorcontrib><collection>Medline</collection><collection>MEDLINE</collection><collection>MEDLINE (Ovid)</collection><collection>MEDLINE</collection><collection>MEDLINE</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>Bacteriology Abstracts (Microbiology B)</collection><collection>Ecology Abstracts</collection><collection>Industrial and Applied Microbiology Abstracts (Microbiology A)</collection><collection>Pollution Abstracts</collection><collection>Toxicology Abstracts</collection><collection>Technology Research Database</collection><collection>Environmental Sciences and Pollution Management</collection><collection>Engineering Research Database</collection><collection>ProQuest Health & Medical Complete (Alumni)</collection><collection>Algology Mycology and Protozoology Abstracts (Microbiology C)</collection><collection>Biotechnology and BioEngineering Abstracts</collection><collection>MEDLINE - Academic</collection><jtitle>Environmental science and pollution research international</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Yan, Jiacong</au><au>Lee, Jianchao</au><au>Liu, Lu</au><au>Duan, Qiannan</au><au>Lei, Jingzheng</au><au>Fu, Zhizhi</au><au>Zhou, Chi</au><au>Wu, WeiDong</au><au>Wang, Fei</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>A novel method for multi-pollutant monitoring in water supply systems using chemical machine vision</atitle><jtitle>Environmental science and pollution research international</jtitle><stitle>Environ Sci Pollut Res</stitle><addtitle>Environ Sci Pollut Res Int</addtitle><date>2024-04-01</date><risdate>2024</risdate><volume>31</volume><issue>18</issue><spage>26555</spage><epage>26566</epage><pages>26555-26566</pages><issn>1614-7499</issn><issn>0944-1344</issn><eissn>1614-7499</eissn><notes>ObjectType-Article-1</notes><notes>SourceType-Scholarly Journals-1</notes><notes>ObjectType-Feature-2</notes><notes>content type line 23</notes><abstract>Drinking water is vital for human health and life, but detecting multiple contaminants in it is challenging. Traditional testing methods are both time-consuming and labor-intensive, lacking the ability to capture abrupt changes in water quality over brief intervals. This paper proposes a direct analysis and rapid detection method of three indicators of arsenic, cadmium, and selenium in complex drinking water systems by combining a novel long-path spectral imager with machine learning models. Our technique can obtain multiple parameters in about 1 s. The experiment involved setting up samples from various drinking water backgrounds and mixed groups, totaling 9360 injections. A raw visible light source ranging from 380 to 780 nm was utilized, uniformly dispersing light into the sample cell through a filter. The residual beam was captured by a high-definition camera, forming a distinctive spectrum. Three deep learning models—ResNet-50, SqueezeNet V1.1, and GoogLeNet Inception V1—were employed. Datasets were divided into training, validation, and test sets in a 6:2:2 ratio, and prediction performance across different datasets was assessed using the coefficient of determination and root mean square error. The experimental results show that a well-trained machine learning model can extract a lot of feature image information and quickly predict multi-dimensional drinking water indicators with almost no preprocessing. The model’s prediction performance is stable under different background drinking water systems. The method is accurate, efficient, and real-time and can be widely used in actual water supply systems. This study can improve the efficiency of water quality monitoring and treatment in water supply systems, and the method’s potential for environmental monitoring, food safety, industrial testing, and other fields can be further explored in the future.</abstract><cop>Berlin/Heidelberg</cop><pub>Springer Berlin Heidelberg</pub><pmid>38448769</pmid><doi>10.1007/s11356-024-32791-3</doi><tpages>12</tpages></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 1614-7499 |
| ispartof | Environmental science and pollution research international, 2024-04, Vol.31 (18), p.26555-26566 |
| issn | 1614-7499 0944-1344 1614-7499 |
| language | eng |
| recordid | cdi_proquest_miscellaneous_2942185725 |
| source | Springer Link |
| subjects | Aquatic Pollution Arsenic Arsenic - analysis Atmospheric Protection/Air Quality Control/Air Pollution Cadmium Cadmium - analysis Contaminants Datasets Deep learning Drinking water Drinking Water - chemistry Earth and Environmental Science Ecotoxicology Environment Environmental Chemistry Environmental Health Environmental monitoring Environmental Monitoring - methods Food industry Food safety High definition Indicators Learning algorithms Light sources Machine Learning Machine vision Performance prediction Pollution monitoring Research Article Selenium Waste Water Technology Water conveyance Water Management Water monitoring Water Pollutants, Chemical - analysis Water pollution Water Pollution Control Water Quality Water quality management Water Supply Water supply systems |
| title | A novel method for multi-pollutant monitoring in water supply systems using chemical machine vision |
| url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-09-22T21%3A16%3A42IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=A%20novel%20method%20for%20multi-pollutant%20monitoring%20in%20water%20supply%20systems%20using%20chemical%20machine%20vision&rft.jtitle=Environmental%20science%20and%20pollution%20research%20international&rft.au=Yan,%20Jiacong&rft.date=2024-04-01&rft.volume=31&rft.issue=18&rft.spage=26555&rft.epage=26566&rft.pages=26555-26566&rft.issn=1614-7499&rft.eissn=1614-7499&rft_id=info:doi/10.1007/s11356-024-32791-3&rft_dat=%3Cproquest_cross%3E3046977062%3C/proquest_cross%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c326t-94872390c912223ea9cdfb5d6e0c2bc6921b27ba56a71499063dcc283705380d3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=3046977062&rft_id=info:pmid/38448769&rfr_iscdi=true |