Machine learning techniques for chemical and type analysis of ocean oil samples via handheld spectrophotometer device SCOPUS

DC Field Value Language
dc.contributor.author Sosnowski, Katelyn -
dc.contributor.author Loh, Andrew -
dc.contributor.author Zubler, Alanna V. -
dc.contributor.author Shir, Hasina -
dc.contributor.author Ha, Sung Yong -
dc.contributor.author Yim, Un Hyuk -
dc.contributor.author Yoon, Jeong-Yeol -
dc.date.accessioned 2022-03-29T02:30:02Z -
dc.date.available 2022-03-29T02:30:02Z -
dc.date.created 2022-03-28 -
dc.date.issued 2022-05 -
dc.identifier.issn 2590-1370 -
dc.identifier.uri https://sciwatch.kiost.ac.kr/handle/2020.kiost/42412 -
dc.description.abstract We designed and constructed a handheld, sturdy fluorescence spectrometry device for identifying samples from ocean oil spills. Two large training databases of autofluorescence spectra from raw oil samples (538 samples/1614 spectra and 767 samples/2301 spectra) were cross validated using support vector machine (SVM) to identify oil type and SARA (saturate, aromatic, resin, and asphaltene) contents. The device's performance was then validated on an independent set of 79 ocean oil samples, which were added to and then collected from ocean water during outdoor exposure to hot, humid weather to represent an actual oil spill. It successfully classified oil types with 92%–100% sensitivity and specificity and F1 scores of 85.7–100%. Further classification of light fuel oils into marine gas oil (MGO)-like and Bunker A (BA)-like categories was successful with the training set (raw oil samples), while less successful with the independent validation set (ocean oil samples). SARA content classification models performed well in training for the saturate (80.8% accuracy) and asphaltene (90.7%) contents. The developed training model was validated using ocean oil samples, and the resulting accuracies were 62.0% (saturate) and 93.7% (asphaltene). These results indicate the difficulties in classifying volatile light fuel oils with a low molecular weight that have experienced weathering effects, while high molecular weight compounds and general oil type can be analyzed. -
dc.description.uri 3 -
dc.language English -
dc.publisher Elsevier Ltd -
dc.title Machine learning techniques for chemical and type analysis of ocean oil samples via handheld spectrophotometer device -
dc.type Article -
dc.citation.title Biosensors and Bioelectronics: X -
dc.citation.volume 10 -
dc.contributor.alternativeName Andrew -
dc.contributor.alternativeName 하성용 -
dc.contributor.alternativeName 임운혁 -
dc.identifier.bibliographicCitation Biosensors and Bioelectronics: X, v.10 -
dc.identifier.doi 10.1016/j.biosx.2022.100128 -
dc.identifier.scopusid 2-s2.0-85126991876 -
dc.description.journalClass 3 -
dc.description.isOpenAccess N -
dc.subject.keywordAuthor Asphaltene -
dc.subject.keywordAuthor Fluorescence spectroscopy -
dc.subject.keywordAuthor Oil spill -
dc.subject.keywordAuthor Saturate -
dc.subject.keywordAuthor Support vector machine -
dc.description.journalRegisteredClass scopus -
Appears in Collections:
South Sea Research Institute > Risk Assessment Research Center > 1. Journal Articles
Files in This Item:
There are no files associated with this item.

qrcode

Items in ScienceWatch@KIOST are protected by copyright, with all rights reserved, unless otherwise indicated.

Browse