[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-128027-en":3,"doc-seo-128027-105":31,"detail-sidebar-cat-0-en-105":92},{"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":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},128027,962084931830,"Theodore","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","Towards Atmospheric Compound Identification in Chemical Ionization Mass Spectrometry with Pesticide Standards and Machine Learning - Technical note","Chemical ionization mass spectrometry (CIMS) is widely used in atmospheric chemistry, but limited understanding of interactions between reagent ions and target compounds makes reliable compound identification difficult. This technical note applies machine learning to a reference pesticide dataset measured in two standard solutions using an Orbitrap with a TD-MION-MS inlet in negative and positive modes. Two models are trained: random forest for detection and kernel ridge regression for predicting CIMS signal intensities, comparing several molecular representations and analyzing feature importance.","Atmos. Chem. Phys., 25, 685–704, 2025 [https://doi.org/10.5194/acp-25-685-2025](https://doi.org/10.5194/acp-25-685-2025)[ ](https://doi.org/10.5194/acp-25-685-2025)© Author(s) 2025 . This work is distributed under the Creative Commons Attribution 4 .0 License.  \nTechnical note: Towards atmospheric compound identification in chemical ionization mass spectrometry with pesticide standards and machine learning  \nFederica Bortolussi 1 , Hilda Sandström2 , Fariba Partovi3,4 , Joona Mikkilä4 , Patrick Rinke2,5,6,7 , and  \nMatti Rissanen 1,3  \n1Department of Chemistry, University of Helsinki, 00560 Helsinki, Finland  \n2Department of Applied Physics, Aalto University, Espoo, Finland  \n3Aerosol Physics Laboratory, Physics Unit, Tampere University, 33720 Tampere, Finland  \n4 Karsa Ltd., A. I. Virtasen aukio 1, 00560 Helsinki, Finland  \n5Physics Department, TUM School of Natural Sciences, Technical University of Munich, Garching, Germany  \n6Atomistic Modelling Center, Munich Data Science Institute, Technical University of Munich, Garching, Germany  \n7Munich Center for Machine Learning (MCML), Munich, Germany Correspondence: Federica Bortolussi (federica.bortolussi@helsinki.fi)  \nReceived: 17 June 2024 – Discussion started: 18 July 2024  \nRevised: 16 November 2024 – Accepted: 20 November 2024 – Published: 17 January 2025  \nAbstract. Chemical ionization mass spectrometry (CIMS) is widely used in atmospheric chemistry studies. However, due to the complex interactions between reagent ions and target compounds, chemical understanding remains limited and compound identification difficult. In this study, we apply machine learning to a reference dataset of pesticides in two standard solutions to build a model that can provide insights from CIMS analyses in atmospheric science. The CIMS measurements were performed with an Orbitrap mass spectrometer coupled to a thermal desorption multi-scheme chemical ionization inlet unit (TD-MION-MS) with both negative and positive ionization modes utilizing Br 􀀀 , O, H 3OC and (CH 3)2 COHC (AceHC ) as reagent ions. We then trained two machine learning methods on these data: (1) random forest (RF) for classifying if a pesticide can be detected with CIMS and (2) kernel ridge regression (KRR) for predicting the expected CIMS signals. We compared their performance on five different representations of the molecular structure: the topological fingerprint (TopFP), the molecular access system keys (MACCS), a custom descriptor based on standard molecular properties (RDKitPROP), the Coulomb matrix (CM) and the many-body tensor representation (MBTR) . The results indicate that MACCS outperforms the other descriptors. Our best classification model reaches a prediction accuracy of 0.85 􀀆 0.02 and a receiver operating characteristic curve area of 0.91 􀀆 0.01. Our best regression model reaches an accuracy of 0.44 􀀆 0.03 logarithmic units of the signal intensity. Subsequent feature importance analysis of the classifiers reveals that the most important sub-structures are NH and OH for the negative ionization schemesand nitrogen-containing groups for the positive ionization schemes.  \nPublished by Copernicus Publications on behalf of the European Geosciences Union.  \nTechnical note  \n686 F. Bortolussi et al.: Atmospheric compound identification in CIMS with machine learning  \n1 Introduction (Erban et al., 2019 ; Heinonen et al., 2012 ; Dührkop et al., 2015 ; Brouard et al., 2016 ; Nguyen et al., 2018, 2019) . The  \nMass spectrometry is an analytical technique for molecular compound identification and tracking in a variety of fields (e.g., biochemistry, food control, forensic science, pollution control, reaction physics and kinetics, thermodynamic parameters' determination) (Griffiths and de Hoffmann, 2007) . In atmospheric science, chemical ionization mass spectrometry (CIMS) has proliferated because it can detect gas-phase compounds at atmospheric pressures (Sipilä et al., 2016 ; Laskin et al., 2018 ; Huey, 2007 ; Eisele and Tanner, 1993 ;","cbCaiqMPa1aHqroj","https://ap.wps.com/l/cbCaiqMPa1aHqroj","pdf",2769678,2,1,20,"English","en",105,"# Abstract\n# Introduction\n## Chemical ionization mass spectrometry in atmospheric chemistry\n## Motivation and limitations of current identification workflows\n# Technical approach\n## Machine learning models for detection and signal regression\n## Molecular structure representations compared\n# Results\n## Classification performance and evaluation metrics\n## Regression performance and error in signal intensity\n## Feature importance and influential substructures\n# Conclusion","[{\"question\":\"Why is compound identification challenging in chemical ionization mass spectrometry (CIMS)?\",\"answer\":\"Complex interactions between reagent ions and target compounds limit chemical understanding, making routine identification from CIMS spectra difficult.\"},{\"question\":\"What machine learning tasks are used in the study?\",\"answer\":\"Random forest is used to classify whether a pesticide can be detected with CIMS, and kernel ridge regression predicts expected CIMS signal intensities.\"},{\"question\":\"Which molecular representation performed best for the classification model?\",\"answer\":\"The results indicate that MACCS outperforms the other compared descriptors for predicting pesticide detectability.\"}]","Towards Atmospheric Compound Identification in Chemical Ionization Mass Spectrometry with Pesticide Standards and Machine Learning - Technical note | PDF",1785944101,50,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":29},"towards-atmospheric-compound-identification-in-chemical-ionization-mass-spectrometry-with-pesticide-standards-and-machine-learning-technical-note","",{"@graph":37,"@context":86},[38,54,69],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,48,51],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":20},"https://docshare.wps.com/document/","Document",{"item":49,"name":12,"@type":44,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":44,"position":53},"https://docshare.wps.com/document/towards-atmospheric-compound-identification-in-chemical-ionization-mass-spectrometry-with-pesticide-standards-and-machine-learning-technical-note/128027/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":42,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-26","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"Why is compound identification challenging in chemical ionization mass spectrometry (CIMS)?","Question",{"text":76,"@type":77},"Complex interactions between reagent ions and target compounds limit chemical understanding, making routine identification from CIMS spectra difficult.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"What machine learning tasks are used in the study?",{"text":81,"@type":77},"Random forest is used to classify whether a pesticide can be detected with CIMS, and kernel ridge regression predicts expected CIMS signal intensities.",{"name":83,"@type":74,"acceptedAnswer":84},"Which molecular representation performed best for the classification model?",{"text":85,"@type":77},"The results indicate that MACCS outperforms the other compared descriptors for predicting pesticide detectability.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":93},[94,98,102,106,111,115,120,123,127,130,134],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":47,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":47,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":30,"slug":114},6,"Technology","technology",{"id":116,"doc_module":4,"doc_module_name":47,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":47,"category_name":125,"show_sort_weight":22,"slug":126},9,"Religion & Spirituality","religion-spirituality",{"id":22,"doc_module":4,"doc_module_name":47,"category_name":128,"show_sort_weight":22,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":47,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":47,"category_name":136,"show_sort_weight":107,"slug":137},19,"General","general"]