{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T16:12:03Z","timestamp":1790093523708,"version":"4.0.1"},"reference-count":22,"publisher":"American Chemical Society (ACS)","issue":"37","license":[{"start":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T00:00:00Z","timestamp":1789171200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,9,22]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>The quality and safety of gasoline are critical for energy distribution and market regulations. Consequently, rapid and nondestructive detection methods based on spectroscopy combined with intelligent algorithms have garnered significant attention. However, existing approaches often separate adulterant identification and concentration prediction, limiting their application in complex adulteration scenarios. To address these limitations, this study develops an attention-based multi-scale convolutional neural network, termed Multi-Scale Attention Fusion Convolutional Neural Network, based on Raman spectroscopy, to jointly perform adulterant classification and concentration regression within a unified framework. Four adulteration systems\u2500gasoline blended with methanol, ethanol, kerosene, and diesel\u2500were constructed, and 1200 Raman spectra were collected across adulteration ratios ranging from 5% to 30%. The performance of the model was systematically evaluated via ablation studies and comparisons with various backbone networks. Additionally, the proposed model was compared with multi-task deep learning models based on ResNet18 and LSTM architectures. The results indicate that the proposed model achieves more stable performance in both classification and regression tasks. In the ablation study, the removal of the Feature Pyramid Network module led to a 1.25% decrease in classification accuracy and a 29.21% increase in root mean square error, underscoring its critical role in multi-scale feature representation. Traditional single-task models were also evaluated for comparison. A Support Vector Machine, K-Nearest Neighbors, and Random Forest were applied to classification tasks, while Support Vector Regression (SVR) and Partial Least Squares Regression were used for regression. Even with optimal variable importance in projection wavelength selection, the best-performing SVR model achieved an R2 of only 0.9785. In contrast, the proposed model achieved a classification accuracy of 99.92% and an R2 exceeding 0.9886 in regression tasks, demonstrating superior qualitative and quantitative detection capability compared with conventional chemometric and single-task learning methods.<\/jats:p>","DOI":"10.1021\/acsomega.6c05800","type":"journal-article","created":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T19:01:48Z","timestamp":1789239708000},"page":"55980-55993","source":"Crossref","is-referenced-by-count":0,"title":["Gasoline Adulteration\nAnalysis Based on Raman Spectroscopy\nand a Multi-Scale Convolutional Neural Network"],"prefix":"10.1021","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-6875-0804","authenticated-orcid":true,"given":"Yingling","family":"Bai","sequence":"first","affiliation":[{"name":"Chongqing University of Technology - Huaxi Campus , , , ,","place":["Chongqing, China, 400054"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongjiao","family":"Yuan","sequence":"additional","affiliation":[{"name":"Chongqing University of Technology - Huaxi Campus , , , ,","place":["Chongqing, China, 400054"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hua","family":"Yang","sequence":"additional","affiliation":[{"name":"Chongqing University of Technology - Huaxi Campus , , , ,","place":["Chongqing, China, 400054"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Li","sequence":"additional","affiliation":[{"name":"Chongqing University of Technology - Huaxi Campus , , , ,","place":["Chongqing, China, 400054"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuding","family":"Zuo","sequence":"additional","affiliation":[{"name":"Chongqing University of Technology - Huaxi Campus , , , ,","place":["Chongqing, China, 400054"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenhao","family":"Xiao","sequence":"additional","affiliation":[{"name":"Chongqing University of Technology - Huaxi Campus , , , ,","place":["Chongqing, China, 400054"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ming","family":"Kang","sequence":"additional","affiliation":[{"name":"Chongqing Ceprei Industrial Technology Institute Co., Ltd. , , ,","place":["Chongqing, China, 401332"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bin","family":"Tang","sequence":"additional","affiliation":[{"name":"Chongqing University of Technology - Huaxi Campus , , , ,","place":["Chongqing, China, 400054"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"316","published-online":{"date-parts":[[2026,9,12]]},"reference":[{"key":"2026092211035899900_cit1","doi-asserted-by":"publisher","DOI":"10.1016\/j.saa.2024.124049","article-title":"Fuel forensics:\nrecent advancements in profiling of adulterated fuels by ATR-FTIR\nspectroscopy and chemometric approaches","volume":"312","author":"Babu","year":"2024","journal-title":"Spectrochimica\nActa Part A: Molecular and Biomolecular Spectroscopy"},{"key":"2026092211035899900_cit2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.trac.2017.04.011","article-title":"Monitoring petroleum\nfuel adulteration: A review of\nanalytical methods","volume":"92","author":"Vempatapu","year":"2017","journal-title":"TrAC Trends in Analytical\nChemistry"},{"issue":"38","key":"2026092211035899900_cit3","doi-asserted-by":"publisher","first-page":"34012","DOI":"10.1021\/acsomega.2c03207","article-title":"Analysis of the influence of gasoline\nadulteration on lubricant degradation and internal combustion engine\nperformance","volume":"7","author":"Gonc\u0327alves","year":"2022","journal-title":"ACS omega"},{"issue":"7","key":"2026092211035899900_cit4","doi-asserted-by":"publisher","first-page":"1508","DOI":"10.1002\/jssc.201601174","article-title":"Ultrafast gas chromatography method\nwith direct injection\nfor the quantitative determination of benzene, toluene, ethylbenzene,\nand xylenes in commercial gasoline","volume":"40","author":"Miranda","year":"2017","journal-title":"J. Sep.\nSci."},{"key":"2026092211035899900_cit5","doi-asserted-by":"publisher","first-page":"730","DOI":"10.1016\/j.foodchem.2016.06.048","article-title":"Characterisation\nof minor components in vegetable oil by comprehensive gas chromatography\nwith dual detection","volume":"212","author":"Purcaro","year":"2016","journal-title":"Food Chemistry"},{"issue":"10","key":"2026092211035899900_cit6","doi-asserted-by":"publisher","first-page":"10556","DOI":"10.1021\/acs.energyfuels.8b02368","article-title":"Gasoline\nquality assessment using\nfast gas chromatography and partial least-squares regression for the\ndetection of adulterated gasoline","volume":"32","author":"Lee","year":"2018","journal-title":"Energy Fuels"},{"issue":"11","key":"2026092211035899900_cit7","doi-asserted-by":"publisher","first-page":"2301","DOI":"10.1007\/s00216-019-01671-y","article-title":"Advances in chemometric control of\ncommercial diesel adulteration by kerosene using IR spectroscopy","volume":"411","author":"Moura","year":"2019","journal-title":"Anal. Bioanal. Chem."},{"key":"2026092211035899900_cit8","doi-asserted-by":"publisher","DOI":"10.1016\/j.infrared.2024.105119","article-title":"Detection and estimation\nof adulterated gasoline fuel in India using FTIR-ATR spectroscopy\nwith chemometric methods","volume":"137","author":"Lalbiaktluanga","year":"2024","journal-title":"Infrared Physics Technology"},{"key":"2026092211035899900_cit9","doi-asserted-by":"publisher","first-page":"260","DOI":"10.1016\/j.saa.2018.11.012","article-title":"Determination\nof adulterated gasoline using fluorescence emission-excitation matrices\nand multivariate calibration","volume":"210","author":"Wang","year":"2019","journal-title":"Spectrochimica\nActa Part A: Molecular and Biomolecular Spectroscopy"},{"key":"2026092211035899900_cit10","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1016\/j.microc.2018.03.041","article-title":"Time domain nuclear\nmagnetic resonance (TD-NMR): A new methodology to quantify adulteration\nof gasoline","volume":"140","author":"Romanel","year":"2018","journal-title":"Microchemical Journal"},{"issue":"43","key":"2026092211035899900_cit11","doi-asserted-by":"publisher","first-page":"19651","DOI":"10.1021\/jacs.2c05359","article-title":"Raman spectroscopy\nfor chemical biology\nresearch","volume":"144","author":"Dodo","year":"2022","journal-title":"J. Am. Chem. Soc."},{"key":"2026092211035899900_cit12","doi-asserted-by":"publisher","DOI":"10.1016\/j.saa.2025.127076","article-title":"Detailed\ndescription of Raman spectra of carotenoids: experiment and DFT calculations\nof all-trans-isomers","volume":"348","author":"Vasimov","year":"2026","journal-title":"Spectrochimica Acta Part\nA: Molecular and Biomolecular Spectroscopy"},{"key":"2026092211035899900_cit13","doi-asserted-by":"publisher","DOI":"10.1016\/j.saa.2025.127220","article-title":"Identification of green\ntea varieties and origins based on fused surface enhanced Raman spectra\nfrom different extraction solvent","volume":"348","author":"Dai","year":"2026","journal-title":"Spectrochimica\nActa Part A: Molecular and Biomolecular Spectroscopy"},{"key":"2026092211035899900_cit14","doi-asserted-by":"publisher","DOI":"10.1016\/j.trac.2024.117578","article-title":"Recent progress\nand applications of Raman spectrum denoising algorithms in chemical\nand biological analyses: A review","volume":"172","author":"Fang","year":"2024","journal-title":"TrAC Trends\nin Analytical Chemistry"},{"issue":"21","key":"2026092211035899900_cit15","doi-asserted-by":"publisher","first-page":"21251","DOI":"10.1021\/acsnano.3c05510","article-title":"Identifying surface-enhanced raman\nspectra with a raman library using machine learning","volume":"17","author":"Ju","year":"2023","journal-title":"ACS Nano"},{"key":"2026092211035899900_cit16","doi-asserted-by":"publisher","DOI":"10.1016\/j.saa.2021.119712","article-title":"Potential\nof Raman spectroscopic techniques to study\nproteins","volume":"258","author":"Kuhar","year":"2021","journal-title":"Spectrochimica Acta Part A: Molecular\nand Biomolecular Spectroscopy"},{"key":"2026092211035899900_cit17","doi-asserted-by":"publisher","first-page":"116","DOI":"10.1016\/j.chemolab.2017.04.002","article-title":"MCR-ALS with correlation\nconstraint and Raman spectroscopy for identification and quantification\nof biofuels and adulterants in petroleum diesel","volume":"169","author":"Cordeiro Dantas","year":"2017","journal-title":"Chemometrics and Intelligent Laboratory Systems"},{"key":"2026092211035899900_cit18","doi-asserted-by":"publisher","DOI":"10.1016\/j.molstruc.2020.127760","article-title":"Determination\nand quantification of kerosene in gasoline by mid-infrared and Raman\nspectroscopy","volume":"1210","author":"Li","year":"2020","journal-title":"Journal of Molecular Structure"},{"key":"2026092211035899900_cit19","doi-asserted-by":"publisher","DOI":"10.1016\/j.saa.2021.119430","article-title":"Hybrid variable selection\nstrategy coupled with random forest (RF)\nfor quantitative analysis of methanol in methanol-gasoline via Raman\nspectroscopy","volume":"251","author":"Li","year":"2021","journal-title":"Spectrochimica Acta Part A: Molecular\nand Biomolecular Spectroscopy"},{"issue":"3","key":"2026092211035899900_cit20","doi-asserted-by":"publisher","first-page":"287","DOI":"10.3390\/analytica3030020","article-title":"Deep learning for Raman spectroscopy:\nA review","volume":"3","author":"Luo","year":"2022","journal-title":"Analytica"},{"issue":"3","key":"2026092211035899900_cit21","doi-asserted-by":"publisher","first-page":"385","DOI":"10.1007\/s12161-024-02728-0","article-title":"Qualitative\nIdentification and Adulteration\nQuantification of Extra Virgin Olive Oil Based on Raman Spectroscopy\nCombined with Multi-task Deep Learning Model","volume":"18","author":"Liang","year":"2025","journal-title":"Food Analytical Methods"},{"key":"2026092211035899900_cit22","doi-asserted-by":"publisher","DOI":"10.1016\/j.talo.2024.100333","article-title":"Rapid screening of designer fuel frauds by Raman spectroscopy","volume":"9","author":"Picardi","year":"2024","journal-title":"Talanta Open"}],"container-title":["ACS Omega"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.acs.org\/doi\/pdf\/10.1021\/acsomega.6c05800","content-type":"application\/pdf","content-version":"vor","intended-application":"unspecified"},{"URL":"https:\/\/pubs.acs.org\/acsodf\/article-pdf\/11\/37\/55980\/68492800\/acsomega.6c05800.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/pubs.acs.org\/acsodf\/article-pdf\/11\/37\/55980\/68492800\/acsomega.6c05800.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T15:49:07Z","timestamp":1790092147000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.acs.org\/acsodf\/article\/11\/37\/55980\/5428956\/Gasoline-Adulteration-Analysis-Based-on-Raman"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,12]]},"references-count":22,"journal-issue":{"issue":"37","published-online":{"date-parts":[[2026,9,12]]},"published-print":{"date-parts":[[2026,9,22]]}},"URL":"https:\/\/doi.org\/10.1021\/acsomega.6c05800","relation":{},"ISSN":["2470-1343"],"issn-type":[{"value":"2470-1343","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,12]]}}}