[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118281-en":3,"doc-seo-118281-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},118281,7971461740886,"Theodore","https://ap-avatar.wpscdn.com/davatar_3d24733baf745e90a7e4bdd5f77d97b2",8,"Research & Report","Similarity-Based Analysis of Atmospheric Organic Compounds for Machine Learning Applications","Aerosol particle formation in the atmosphere influences air quality and climate change, yet many involved organic molecules remain unidentified. Machine learning can support faster analysis of molecular properties and detection characteristics, but progress is limited by the lack of curated datasets covering atmospheric compounds and their associated properties. The work proposes a similarity-based method linking atmospheric compounds to large molecular datasets used in machine learning development. Results show a small overlap for standard representations, with the out-of-domain nature tied to distinct functional groups and atomic composition.","arXiv:2406.18171v1 [[physics. ao-ph](physics. ao-ph)] 26 Jun 2024  \nSimilarity-Based Analysis of Atmospheric Organic Compounds for Machine Learning Applications  \nHilda Sandström 1 and Patrick Rinke 1,2,3  \n1Department of Applied Physics, Aalto University, P.O. Box 11000, FI-00076 Aalto, Espoo, Finland,  \n2Physics Department, TUM School of Natural Sciences, Technical University of Munich, Garching, Germany  \n3Munich Data Science Institute, Technical University of Munich, Garching, Germany Correspondence: Patrick Rinke ([patrick.rinke@aalto.fi](patrick.rinke@aalto.fi))  \nAbstract. The formation of aerosol particles in the atmosphere impacts air quality and climate change, but many of the organic molecules involved remain unknown. Machine learning could aid in identifying these compounds through accelerated analysis of molecular properties and detection characteristics. However, such progress is hindered by the current lack of curated datasets for atmospheric molecules and their associated properties. To tackle this challenge, we propose a similarity analysis that connects atmospheric compounds to existing large molecular datasets used for machine learning development. We find a small overlap between atmospheric and non-atmospheric molecules using standard molecular representations in machine learning applications. The identified out-of-domain character of atmospheric compounds is related to their distinct functional groups and atomic composition. Our investigation underscores the need for collaborative efforts to gather and share more molecularlevel atmospheric chemistry data. The presented similarity based analysis can be used for future dataset curation for machine learning development in the atmospheric sciences.  \n1 Introduction  \nAerosol particles influence our climate by sunlight reflection and absorption, and by serving as nuclei for cloud condensation (Pörtner et al., 2022) . Beyond climate impact, aerosol particles affect air quality, causing adverse effects on human health (Pozzer et al., 2023; Khomenko et al., 2021; Lelieveld et al., 2020) . However, the underlying molecular-level processes involving organic molecules remain poorly understood, due to the vast number of organic compounds participating in atmospheric chemistry. This existing gap in knowledge hampers a comprehensive understanding of particle formation and growth in different environments (Masson-Delmotte et al., 2021; Elm et al., 2020) . In this paper, we take an initial step to evaluate the potential of filling this void using machine learning. We propose a molecular similarity-based analysis to measure the overlap between atmospheric compounds and common molecular datasets used in machine learning development. By doing so, we can provide a tool to tailor machine learning models for studies of aerosol particle formation and the effects human-based activities, like industry and agriculture, on the formation process. Ultimately, such insights can lead to more informed decisions regarding air quality and climate change mitigation.  \nOrganic aerosol particle formation is affected by atmospheric composition and molecular emissions into the atmosphere. Emitted molecules can transform in reactions initiated by sunlight, to a diverse array of compounds with numerous functional  \ngroups (Bianchi et al., 2019) . These reactions are estimated to produce between hundreds of thousands to millions of atmospherically relevant molecules (Goldstein and Galbally, 2007; Nozière et al., 2015) . Out of this plethora, an unknown number can form or grow aerosol particles by interacting with inorganic emissions (Schobesberger et al., 2013; Riccobono et al., 2014; Ehn et al., 2014), or by themselves (Kirkby et al., 2016) . Details of aerosol particle formation can be uncovered through identification of relevant atmospheric reactions (e.g.,(Peräkylä et al., 2020; Iyer et al., 2023)), aerosol forming compounds (e.g.(Franklin et al., 2022; Worton et al., 2017; Hamilton et al., 20","cbCaiaL5K3JrTbie","https://ap.wps.com/l/cbCaiaL5K3JrTbie","pdf",21744354,1,28,"English","en",105,"# Introduction\n## Aerosol impacts on climate and air quality\n## Limits of molecular-level understanding\n## Molecular similarity-based ML as a solution\n## Experimental challenges in identifying atmospheric compounds","[{\"question\":\"Why are curated datasets important for applying machine learning to atmospheric molecules?\",\"answer\":\"Machine learning progress relies on training data, but atmospheric organic compounds and their properties lack curated, structure-annotated reference datasets. This gap hinders identification and model development.\"},{\"question\":\"What does the proposed similarity analysis connect?\",\"answer\":\"The method links atmospheric compounds to existing large molecular datasets used for machine learning development. It evaluates overlap using standard molecular representations.\"},{\"question\":\"What do the findings suggest about atmospheric compounds compared with non-atmospheric molecules?\",\"answer\":\"The study finds a small overlap between atmospheric and non-atmospheric molecules using standard representations. The out-of-domain character is attributed to distinct functional groups and atomic composition.\"}]","Similarity-Based Analysis of Atmospheric Organic Compounds for Machine Learning Applications | PDF",1785682788,71,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"similarity-based-analysis-of-atmospheric-organic-compounds-for-machine-learning-applications","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/similarity-based-analysis-of-atmospheric-organic-compounds-for-machine-learning-applications/118281/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-02",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why are curated datasets important for applying machine learning to atmospheric molecules?","Question",{"text":75,"@type":76},"Machine learning progress relies on training data, but atmospheric organic compounds and their properties lack curated, structure-annotated reference datasets. This gap hinders identification and model development.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What does the proposed similarity analysis connect?",{"text":80,"@type":76},"The method links atmospheric compounds to existing large molecular datasets used for machine learning development. It evaluates overlap using standard molecular representations.",{"name":82,"@type":73,"acceptedAnswer":83},"What do the findings suggest about atmospheric compounds compared with non-atmospheric molecules?",{"text":84,"@type":76},"The study finds a small overlap between atmospheric and non-atmospheric molecules using standard representations. The out-of-domain character is attributed to distinct functional groups and atomic composition.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]