{"refrec":{"BRefID":396380,"RR":"<b>Meyers, N.; De Witte, B.; Schmidt, N.; Herzke, D.; Fuda, J.-L.; Vanavermaete, D.; Janssen, C.R.; Everaert, G.</b> (2024). From microplastics to pixels: Testing the robustness of two machine learning approaches for automated, Nile red-based marine microplastic identification. <i>Environm. Sc. & Poll. Res. 31</i>: 61860–61875. <a href=\"https://dx.doi.org/10.1007/s11356-024-35289-0\" target=\"_blank\">https://dx.doi.org/10.1007/s11356-024-35289-0</a>","BEntID":394168,"PublicFlag":1,"CheckedFlag":0,"wosflag":1,"vabbflag":1,"RefStringPartII":". <i>Environm. Sc. & Poll. Res. 31</i>: 61860–61875. <a href=\"https://dx.doi.org/10.1007/s11356-024-35289-0\" target=\"_blank\">https://dx.doi.org/10.1007/s11356-024-35289-0</a>","DocTypID":8,"DocType":"Journal article","MarineFlag":1,"FreshFlag":0,"BrackishFlag":0,"TerrestrialFlag":0,"Authorstring":"Meyers, N.; De Witte, B.; Schmidt, N.; Herzke, D.; Fuda, J.-L.; Vanavermaete, D.; Janssen, C.R.; Everaert, G.","OrigTitleTranslFlag":0,"Authorstringtrunc":"Meyers, N. <i>et al.</i>","Englishabstract":"Despite the urgent need for accurate and robust observations of microplastics in the marine environment to assess current and future environmental risks, existing procedures remain labour-intensive, especially for smaller-sized microplastics. In addition to this, microplastic analysis faces challenges due to environmental weathering, impacting the reliability of research relying on pristine plastics. This study addresses these knowledge gaps by testing the robustness of two automated analysis techniques which combine machine learning algorithms with fluorescent colouration of Nile red (NR)-stained particles. Heterogeneously shaped uncoloured microplastics of various polymers—polyethylene (PE), polyethylene terephthalate (PET), polypropylene (PP), polystyrene (PS), and polyvinyl chloride (PVC)—ranging from 100 to 1000&nbsp;µm in size and weathered under semi-controlled surface and deep-sea conditions, were stained with NR and imaged using fluorescence stereomicroscopy. This study assessed and compared the accuracy of decision tree (DT) and random forest (RF) models in detecting and identifying these weathered plastics. Additionally, their analysis time and model complexity were evaluated, as well as the lower size limit (2–4&nbsp;µm) and the interoperability of the approach. Decision tree and RF models were comparably accurate in detecting and identifying pristine plastic polymers (both &gt; 90%). For the detection of weathered microplastics, both yielded sufficiently high accuracies (&gt; 77%), although only RF models were reliable for polymer identification (&gt; 70%), except for PET particles. The RF models showed an accuracy &gt; 90% for particle predictions based on 12–30 pixels, which translated to microplastics sized &lt; 10&nbsp;µm. Although the RF classifier did not produce consistent results across different labs, the inherent flexibility of the method allows for its swift adaptation and optimisation, ensuring the possibility to fine-tune the method to specific research goals through customised datasets, thereby strengthening its robustness. The developed method is particularly relevant due to its ability to accurately analyse microplastics&nbsp;weathered under various marine conditions, as well as ecotoxicologically relevant microplastic sizes, making it highly applicable to real-world environmental samples.","AbstractOtherLang":null,"BibLvlCode":"AS","StandardTitle":"From microplastics to pixels: Testing the robustness of two machine learning approaches for automated, Nile red-based marine microplastic identification","OrigTitleLangCode":"en","OrigTitleLangCodeExtended":"eng","OrigTitleLangID":15,"DateLastModified":{"date":"2026-04-20 01:33:12.877691","timezone_type":1,"timezone":"+02:00"},"UserAccessRight":null,"UserAccID":null,"AuthorKeywords":"Microplastics  · Fluorescence · Nile red · Weathered plastics","OtherDescriptors":null,"Notes":null,"AnaPub":2024,"MonPub":null,"DateUpdate":"2025-12-19","DateCreate":"2024-10-23","SecASFANote":null,"ConfID":null,"PeerRev":1,"VlizCoreFlag":1,"WoScode":null,"VABBcode":null,"OpenAcc":0,"DOI":"10.1007/s11356-024-35289-0"},"refs":null,"anarec":{"AnaID":396380,"PubliDate":2024,"Pagination":"61860–61875","XtraPublOfAnaID":null,"ISBN":null,"Volume":"31","Issue":null,"BRefMon":null,"BRefMonRR":null,"BRefXtra":null,"BRefXtraRR":null,"SerBRefID":45312,"SerRR":"Environmental Science and Pollution Research. Springer: Heidelberg; Berlin.  ISSN 0944-1344; e-ISSN 1614-7499","StandardTitleSer":"Environmental Science and Pollution Research","ISSN":"0944-1344","AbbrevSer":"Environm. Sc. & Poll. Res.","StandardTitleMon":null,"StartPage":null,"Pages":null,"ToPubliDate":null,"BRefBibLvlCode":"S","SerNotes":null},"monrec":null,"serrec":null,"relations":[{"YBRefID":405725,"RefStrFull":"<b>Meyers, N.; De Witte, B.; Schmidt, N.; Herzke, D.; Fuda, J.-L.; Vanavermaete, D.; Janssen, C.; Everaert, G.</b> (2024). From microplastics to pixels: Testing the robustness of two machine learning approaches for automated, Nile red-based marine microplastic identification, <b><i>in</i></b>: <i>MICRO 2024: Plastic pollution from macro to nano. International conference, 23 -27 September 2024, Lanzarote, Spain.</i> ","RelID":4,"Relation":"Related to","StandardTitle":"From microplastics to pixels: Testing the robustness of two machine learning approaches for automated, Nile red-based marine microplastic identification"}],"relationsRev":null,"addrec":null,"othpubs":null,"ownerships":null,"authors":[{"AutName":"Meyers","Firstname":"Nelle","Initials":"N.","Affiliation":"Flanders Marine Institute (VLIZ)","Discriminator":null,"CorporateFlag":0,"BEntID":394168,"AutID":436398,"OrderNr":1,"DegrID":null,"EditorFlag":0,"CorrespFlag":0,"IllustratorFlag":0,"ReviserFlag":0,"TranslatorFlag":0,"InsAcronym":"VLIZ","InsFSN":"Vlaams Instituut voor de Zee","ORCID":"0000-0001-9205-6260","PersID":30367,"InsID":36},{"AutName":"De Witte","Firstname":"Bavo","Initials":"B.","Affiliation":"Flanders Research Institute for Agriculture, Fisheries and Food (ILVO), Marine Research","Discriminator":null,"CorporateFlag":0,"BEntID":394168,"AutID":573906,"OrderNr":2,"DegrID":null,"EditorFlag":0,"CorrespFlag":0,"IllustratorFlag":0,"ReviserFlag":0,"TranslatorFlag":0,"InsAcronym":"ILVO","InsFSN":"Instituut voor Landbouw-, Visserij- en Voedingsonderzoek","ORCID":"0000-0002-4982-6351","PersID":11997,"InsID":5442},{"AutName":"Schmidt","Firstname":"Natascha","Initials":"N.","Affiliation":null,"Discriminator":null,"CorporateFlag":0,"BEntID":394168,"AutID":362820,"OrderNr":3,"DegrID":null,"EditorFlag":0,"CorrespFlag":0,"IllustratorFlag":0,"ReviserFlag":0,"TranslatorFlag":0,"InsAcronym":null,"InsFSN":null,"ORCID":null,"PersID":null,"InsID":null},{"AutName":"Herzke","Firstname":null,"Initials":"D.","Affiliation":"Norwegian Inst Air Res, Dept Environm Pollutants, Tromso, Norway.","Discriminator":null,"CorporateFlag":0,"BEntID":394168,"AutID":223699,"OrderNr":4,"DegrID":null,"EditorFlag":0,"CorrespFlag":0,"IllustratorFlag":0,"ReviserFlag":0,"TranslatorFlag":0,"InsAcronym":null,"InsFSN":null,"ORCID":null,"PersID":null,"InsID":null},{"AutName":"Fuda","Firstname":"Jean-Luc","Initials":"J.-L.","Affiliation":null,"Discriminator":null,"CorporateFlag":0,"BEntID":394168,"AutID":73290,"OrderNr":5,"DegrID":null,"EditorFlag":0,"CorrespFlag":0,"IllustratorFlag":0,"ReviserFlag":0,"TranslatorFlag":0,"InsAcronym":null,"InsFSN":null,"ORCID":null,"PersID":null,"InsID":null},{"AutName":"Vanavermaete","Firstname":"David","Initials":"D.","Affiliation":"Flanders Research Institute for Agriculture, Fisheries and Food (ILVO), Marine Research","Discriminator":null,"CorporateFlag":0,"BEntID":394168,"AutID":573907,"OrderNr":6,"DegrID":null,"EditorFlag":0,"CorrespFlag":0,"IllustratorFlag":0,"ReviserFlag":0,"TranslatorFlag":0,"InsAcronym":"ILVO","InsFSN":"Instituut voor Landbouw-, Visserij- en Voedingsonderzoek","ORCID":"0000-0002-2087-9062","PersID":41852,"InsID":5442},{"AutName":"Janssen","Firstname":"Colin","Initials":"C.R.","Affiliation":"Laboratory of Environmental Toxicology and Aquatic Ecology, Faculty of Bioscience Engineering, Ghent University","Discriminator":null,"CorporateFlag":0,"BEntID":394168,"AutID":157099,"OrderNr":7,"DegrID":null,"EditorFlag":0,"CorrespFlag":0,"IllustratorFlag":0,"ReviserFlag":0,"TranslatorFlag":0,"InsAcronym":"GhEnToxLab","InsFSN":"Universiteit Gent; Faculteit Bio-ingenieurswetenschappen; Vakgroep Dierwetenschappen en Aquatische Ecologie; Laboratorium voor Milieutoxicologie","ORCID":"0000-0002-7781-6679","PersID":50,"InsID":6705},{"AutName":"Everaert","Firstname":"Gert","Initials":"G.","Affiliation":"Flanders Marine Institute (VLIZ)","Discriminator":null,"CorporateFlag":0,"BEntID":394168,"AutID":287049,"OrderNr":8,"DegrID":null,"EditorFlag":0,"CorrespFlag":0,"IllustratorFlag":0,"ReviserFlag":0,"TranslatorFlag":0,"InsAcronym":"VLIZ","InsFSN":"Vlaams Instituut voor de Zee","ORCID":"0000-0003-4305-0617","PersID":20323,"InsID":36}],"mapdetails":null,"datasets":null,"monographs":null,"monparts":null,"serparts":null,"BEntOpen":null,"BEntPrivate":null,"availability":[{"BInstID":410134,"LibID":36,"BRefID":396380,"EmbargoDate":null,"FullEmbargoDate":null,"PhysMedID":16,"hasOCRd":1,"ShelfLocCode":"410134","RFID":null,"PaidValue":null,"Medium":"Server","Description":"Interne VLIZ documenten","Acronym":"VLIZ","Library":"Vlaams Instituut voor de Zee","DutchTerm":"Non-open access","URL":null,"ClassifID":228,"Classification":"Non-open access","ReqLink":1,"ClassifTypID":3,"URLLocation":"https://www.vliz.be/imisdocs/publications/","SubDir":1,"InternalReq":1,"LoggedInReq":1,"Disclaimer":"Disclaimer_VLIZ_Intern","DutchDisclaimer":"<p>Deze publicatie is enkel beschikbaar voor persoonlijk gebruik binnen de Innovocean site <br />en mag op geen enkele manier verder worden verspreid.</p>","FileFormat":".pdf","FileDescr":"pdf","InsPub":1,"InsID":36,"FileFormID":6,"LendableFlag":null,"PublicFlag":1,"orderLib":"A","Notes":null,"AccConID":null,"AccessConstraint":null,"LicURL":null},{"BInstID":410135,"LibID":36,"BRefID":396380,"EmbargoDate":null,"FullEmbargoDate":null,"PhysMedID":16,"hasOCRd":1,"ShelfLocCode":"410135","RFID":null,"PaidValue":null,"Medium":"Server","Description":null,"Acronym":"VLIZ","Library":"Vlaams Instituut voor de Zee","DutchTerm":"Open Marien Archief","URL":null,"ClassifID":235,"Classification":"Open Marine Archive","ReqLink":null,"ClassifTypID":5,"URLLocation":"https://www.vliz.be/imisdocs/publications/","SubDir":0,"InternalReq":0,"LoggedInReq":0,"Disclaimer":"Disclaimer_OMA","DutchDisclaimer":null,"FileFormat":".pdf","FileDescr":"pdf","InsPub":1,"InsID":36,"FileFormID":6,"LendableFlag":null,"PublicFlag":1,"orderLib":"A","Notes":"Reprint","AccConID":null,"AccessConstraint":null,"LicURL":null}],"litstyles":null,"thespers":null,"arch2discl":null,"SERpubls":[{"PublName":"Springer","City":"Heidelberg; Berlin"}],"MONpubls":null,"pictures":[],"thestermsPath":[{"ThesaurusTerm":"Automation","ThestID":684,"Acronym":"ASFA","ThesTermPath":"Automation"},{"ThesaurusTerm":"Fluorescence","ThestID":74594,"Acronym":"CSA","ThesTermPath":"Fluorescence"},{"ThesaurusTerm":"Machine learning","ThestID":74315,"Acronym":"CSA","ThesTermPath":"Machine learning"},{"ThesaurusTerm":"Monitoring","ThestID":5312,"Acronym":"ASFA","ThesTermPath":"Monitoring"},{"ThesaurusTerm":"Marine pollution","ThestID":5015,"Acronym":"ASFA","ThesTermPath":"Pollution > Water pollution > Marine pollution"}],"thestermsASFA":[{"ThesaurusTerm":"Automation"},{"ThesaurusTerm":"Fluorescence"},{"ThesaurusTerm":"Machine learning"},{"ThesaurusTerm":"Marine pollution"},{"ThesaurusTerm":"Monitoring"}],"taxtermsASFA":null,"geotermsASFA":null,"collections":[{"Collection":"OMA - Open Marien Archief","ShortName":"OMA"},{"Collection":"VLIZ Acknowledged Publications","ShortName":"VLIZ ackn"}],"conf":null,"proj":null,"Physdatasets":null,"spcols":{"222":{"SpName":"BMB - Belgische Mariene Bibliografie","SpColID":222,"ParSpColID":null,"TopParID":null,"ShortName":"BMB","URLLocation":null,"LibID":36,"OpenRepoFlag":null,"SpTypID":null,"TopParIDNotWebsite":null,"SpColPath":"BMB"},"992":{"SpName":"FRIS (VLIZ) - Flanders Research Information Space","SpColID":992,"ParSpColID":null,"TopParID":null,"ShortName":"FRIS","URLLocation":null,"LibID":36,"OpenRepoFlag":null,"SpTypID":null,"TopParIDNotWebsite":null,"SpColPath":"FRIS"},"221":{"SpName":"OMA - Open Marien Archief","SpColID":221,"ParSpColID":null,"TopParID":null,"ShortName":"OMA","URLLocation":null,"LibID":36,"OpenRepoFlag":1,"SpTypID":null,"TopParIDNotWebsite":null,"SpColPath":"OMA"},"1064":{"SpName":"Peer reviewed VLIZ publications","SpColID":1064,"ParSpColID":null,"TopParID":null,"ShortName":"PR VLIZ pubs","URLLocation":null,"LibID":null,"OpenRepoFlag":null,"SpTypID":null,"TopParIDNotWebsite":null,"SpColPath":"PR VLIZ pubs"},"39":{"SpName":"VLIZ Acknowledged Publications","SpColID":39,"ParSpColID":null,"TopParID":null,"ShortName":"VLIZ ackn","URLLocation":null,"LibID":36,"OpenRepoFlag":null,"SpTypID":null,"TopParIDNotWebsite":null,"SpColPath":"VLIZ ackn"}},"doi":null,"publs":null,"serparttypes":null,"monauthors":null,"MParts":null,"SParts":null,"hLibs":null,"langs":[{"BEntID":394168,"AbstractFlag":0,"LangID":15,"LangCode":"en","Lang":"English","DutchTerm":"Engels","LangCodeExtended":"eng"},{"BEntID":394168,"AbstractFlag":1,"LangID":15,"LangCode":"en","Lang":"English","DutchTerm":"Engels","LangCodeExtended":"eng"}],"urls":[{"URL":"https://dx.doi.org/10.1007/s11356-024-35289-0","externalID":"10.1007/s11356-024-35289-0","URLTypeCode":"DOI","URLID":136083,"URLTypID":13,"URLType":"DOI","URLPrefix":"http://dx.doi.org/"}],"thesterms":[{"ThesaurusTerm":"Automation","ThestID":684,"Acronym":"ASFA","ThesTypID":1,"ThesType":"ASFA Thesaurus List"},{"ThesaurusTerm":"Fluorescence","ThestID":74594,"Acronym":"CSA","ThesTypID":2,"ThesType":"CSA Technology Research Database Master Thesaurus"},{"ThesaurusTerm":"Machine learning","ThestID":74315,"Acronym":"CSA","ThesTypID":2,"ThesType":"CSA Technology Research Database Master Thesaurus"},{"ThesaurusTerm":"Marine pollution","ThestID":5015,"Acronym":"ASFA","ThesTypID":1,"ThesType":"ASFA Thesaurus List"},{"ThesaurusTerm":"Monitoring","ThestID":5312,"Acronym":"ASFA","ThesTypID":1,"ThesType":"ASFA Thesaurus List"}],"taxterms":null,"geoterms":null,"othterms":null,"asfacodes":null,"asfa2codes":null,"thestermsFRIS":[{"ThesaurusTerm":"Automation","DutchTerm":null,"ThestID":684,"Acronym":"ASFA","ThesTypID":1,"ThesType":"ASFA Thesaurus List"},{"ThesaurusTerm":"Fluorescence","DutchTerm":null,"ThestID":74594,"Acronym":"CSA","ThesTypID":2,"ThesType":"CSA Technology Research Database Master Thesaurus"},{"ThesaurusTerm":"Machine learning","DutchTerm":null,"ThestID":74315,"Acronym":"CSA","ThesTypID":2,"ThesType":"CSA Technology Research Database Master Thesaurus"},{"ThesaurusTerm":"Marine pollution","DutchTerm":"Mariene vervuiling","ThestID":5015,"Acronym":"ASFA","ThesTypID":1,"ThesType":"ASFA Thesaurus List"},{"ThesaurusTerm":"Monitoring","DutchTerm":"Monitoring","ThestID":5312,"Acronym":"ASFA","ThesTypID":1,"ThesType":"ASFA Thesaurus List"}],"taxtermsFRIS":null,"geotermsFRIS":null,"othtermsFRIS":null,"resmessage":"","complete":1,"sessions":{"newSesName":"Chisala, Chilekwa, C.","newSesDate":{"date":"2024-10-23 08:59:55.077000","timezone_type":3,"timezone":"Europe/Brussels"},"updSesName":"Verheyde, Fons, F.","updSesDate":{"date":"2025-12-19 13:49:25.737000","timezone_type":3,"timezone":"Europe/Brussels"}}}