Vitus Besel , Milica Todorović , Theo Kurtén , Hanna Vehkamäki , Patrick Rinke
{"title":"在分子数据集中寻找稀疏数据:应用主动学习识别极低挥发性有机化合物","authors":"Vitus Besel , Milica Todorović , Theo Kurtén , Hanna Vehkamäki , Patrick Rinke","doi":"10.1016/j.jaerosci.2024.106375","DOIUrl":null,"url":null,"abstract":"<div><p>The formation of aerosol particles in the atmosphere is driven by the gas to particle conversion of <em>extremely low volatile organic compounds</em> (ELVOC), organic compounds with a particularly low saturation vapor pressure (<span><math><msub><mrow><mi>p</mi></mrow><mrow><mi>Sat</mi></mrow></msub></math></span>). Identifying ELVOCs and their chemical structures is both experimentally and theoretically challenging: Measuring the very low <span><math><msub><mrow><mi>p</mi></mrow><mrow><mi>Sat</mi></mrow></msub></math></span> of ELVOCs is extremely difficult, and computing <span><math><msub><mrow><mi>p</mi></mrow><mrow><mi>Sat</mi></mrow></msub></math></span> for these often large molecules is computationally costly. Moreover, ELVOCs are underrepresented in available datasets of atmospheric organic species, which reduces the value of statistical models built on such data. We propose an active learning (AL) approach to efficiently identify ELVOCs in a data pool of atmospheric organic species with initially unknown <span><math><msub><mrow><mi>p</mi></mrow><mrow><mi>Sat</mi></mrow></msub></math></span>. We assess the performance of our AL approach by comparing it to traditional machine learning regression methods, as well as ELVOC classification based on molecular properties. AL proves to be a highly efficient method for ELVOC identification with limitations on the type of ELVOC it can identify. We also show that traditional machine learning or molecular property-based methods can be adequate tools depending on the available data and desired degree of efficiency.</p></div>","PeriodicalId":14880,"journal":{"name":"Journal of Aerosol Science","volume":null,"pages":null},"PeriodicalIF":3.9000,"publicationDate":"2024-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0021850224000429/pdfft?md5=37c98b723eebcb80f08de6db27508c46&pid=1-s2.0-S0021850224000429-main.pdf","citationCount":"0","resultStr":"{\"title\":\"The search for sparse data in molecular datasets: Application of active learning to identify extremely low volatile organic compounds\",\"authors\":\"Vitus Besel , Milica Todorović , Theo Kurtén , Hanna Vehkamäki , Patrick Rinke\",\"doi\":\"10.1016/j.jaerosci.2024.106375\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>The formation of aerosol particles in the atmosphere is driven by the gas to particle conversion of <em>extremely low volatile organic compounds</em> (ELVOC), organic compounds with a particularly low saturation vapor pressure (<span><math><msub><mrow><mi>p</mi></mrow><mrow><mi>Sat</mi></mrow></msub></math></span>). Identifying ELVOCs and their chemical structures is both experimentally and theoretically challenging: Measuring the very low <span><math><msub><mrow><mi>p</mi></mrow><mrow><mi>Sat</mi></mrow></msub></math></span> of ELVOCs is extremely difficult, and computing <span><math><msub><mrow><mi>p</mi></mrow><mrow><mi>Sat</mi></mrow></msub></math></span> for these often large molecules is computationally costly. Moreover, ELVOCs are underrepresented in available datasets of atmospheric organic species, which reduces the value of statistical models built on such data. We propose an active learning (AL) approach to efficiently identify ELVOCs in a data pool of atmospheric organic species with initially unknown <span><math><msub><mrow><mi>p</mi></mrow><mrow><mi>Sat</mi></mrow></msub></math></span>. We assess the performance of our AL approach by comparing it to traditional machine learning regression methods, as well as ELVOC classification based on molecular properties. AL proves to be a highly efficient method for ELVOC identification with limitations on the type of ELVOC it can identify. We also show that traditional machine learning or molecular property-based methods can be adequate tools depending on the available data and desired degree of efficiency.</p></div>\",\"PeriodicalId\":14880,\"journal\":{\"name\":\"Journal of Aerosol Science\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":3.9000,\"publicationDate\":\"2024-03-30\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.sciencedirect.com/science/article/pii/S0021850224000429/pdfft?md5=37c98b723eebcb80f08de6db27508c46&pid=1-s2.0-S0021850224000429-main.pdf\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Aerosol Science\",\"FirstCategoryId\":\"93\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0021850224000429\",\"RegionNum\":3,\"RegionCategory\":\"环境科学与生态学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"ENGINEERING, CHEMICAL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Aerosol Science","FirstCategoryId":"93","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0021850224000429","RegionNum":3,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENGINEERING, CHEMICAL","Score":null,"Total":0}
The search for sparse data in molecular datasets: Application of active learning to identify extremely low volatile organic compounds
The formation of aerosol particles in the atmosphere is driven by the gas to particle conversion of extremely low volatile organic compounds (ELVOC), organic compounds with a particularly low saturation vapor pressure (). Identifying ELVOCs and their chemical structures is both experimentally and theoretically challenging: Measuring the very low of ELVOCs is extremely difficult, and computing for these often large molecules is computationally costly. Moreover, ELVOCs are underrepresented in available datasets of atmospheric organic species, which reduces the value of statistical models built on such data. We propose an active learning (AL) approach to efficiently identify ELVOCs in a data pool of atmospheric organic species with initially unknown . We assess the performance of our AL approach by comparing it to traditional machine learning regression methods, as well as ELVOC classification based on molecular properties. AL proves to be a highly efficient method for ELVOC identification with limitations on the type of ELVOC it can identify. We also show that traditional machine learning or molecular property-based methods can be adequate tools depending on the available data and desired degree of efficiency.
期刊介绍:
Founded in 1970, the Journal of Aerosol Science considers itself the prime vehicle for the publication of original work as well as reviews related to fundamental and applied aerosol research, as well as aerosol instrumentation. Its content is directed at scientists working in engineering disciplines, as well as physics, chemistry, and environmental sciences.
The editors welcome submissions of papers describing recent experimental, numerical, and theoretical research related to the following topics:
1. Fundamental Aerosol Science.
2. Applied Aerosol Science.
3. Instrumentation & Measurement Methods.