Machine-Learning-Driven Reconstruction of Organic Aerosol Sources across Dense Monitoring Networks in Europe

Fine particulate matter (PM) poses a major threat to public health, with organic aerosol (OA) being a key component. Major OA sources, hydrocarbon-like OA (HOA), biomass burning OA (BBOA), and oxygenated OA (OOA), have distinct health and environmental impacts. However, OA source apportionment via positive matrix factorization (PMF) applied to aerosol mass spectrometry (AMS) or aerosol chemical speciation monitoring (ACSM) data is costly and limited to a few supersites, leaving over 80% of OA data uncategorized in global monitoring networks. To address this gap, we trained machine learning models to predict HOA, BBOA, and OOA using limited OA source apportionment data and widely available organic carbon (OC) measurements across Europe (2010-2019). Our best performing model expanded the OA source data set 4-fold, yielding 85 000 daily apportionment values across 180 sites. Results show that HOA and BBOA peak in winter, particularly in urban areas, while OOA, consistently the dominant fraction, is more regionally distributed with less seasonal variability. This study provides a significantly expanded OA source data set, enabling better identification of pollution hotspots and supporting high-resolution exposure assessments.

Authors

Institutions

Publication Details

Journal
Environmental Science & Technology Letters
Published
2025-10-20
DOI
https://doi.org/10.1021/acs.estlett.5c00771
Citations
2
Primary Topic
Air Quality Monitoring and Forecasting
Type
article
Field-Weighted Citation Impact
1.60
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Machine-Learning-Driven Reconstruction of Organic Aerosol Sources across Dense Monitoring Networks in Europe

Hannes Keernik, Aude Bourin, A. Vasanits-Zsigrai, Petra Pokorná et al.
2 citations
Environmental Science & Technology Letters
Air Quality Monitoring and Forecasting
1.60
article

Machine-Learning-Driven Reconstruction of Organic Aerosol Sources across Dense Monitoring Networks in Europe

Hannes Keernik, Aude Bourin, A. Vasanits-Zsigrai, Petra Pokorná, Petr Vodička, Hartmut Herrmann, Andrê S. H. Prévôt, Olivier Favez, Wenche Aas, Samira Atabakhsh, Benjamin Chazeau, Sébastien Conil, Varun Kumar, Petros Vasilakos, Stephen M. Platt, Julija Pauraitė, Ana M. Sánchez de la Campa, Yulia Sosedova, Christoph Hueglin, Mikael Ehn, Laurent Poulain, Minna Aurela, Maria I. Gini, Jay G. Slowik, Anna Font, Hasna Chebaicheb, Michael Pikridas, Aniss Aiman Medbouhi, Nicole M Probst-Hensch, Liine Heikkinen, Radek Lhotka, Andrés Alástuey, Jaroslav Schwarz, Ekaterina Krymova, Karl Espen Yttri, Livio Belegante, Claudio A. Belis, Matteo Rinaldi, David C. Green, Gang Chen, Vanes Poluzzi, Céline Voiron, Stefania Gilardoni, Daniel Sánchez-Rodas, María Cruz Minguillón, Sonia Castillo, Véronique Riffault, Marta Via, Aikaterini Bougiatioti, H. Flentje, Jean‐Eudes Petit, Gaëlle Uzu, Evelyn Freney, Kees de Hoogh, Iasonas Stavroulas, Hilkka Timonen, Eleonora Cuccia, Dario Massabò, Xavier Querol, Benjamin Flueckiger, Imre Salma, Marco Paglione, Jean‐Luc Jaffrezo, Cristina Reche, Jianhui Jiang, Marek Maasikmets, Benjamin Bergmans, Stuart K. Grange, Nicolas Marchand, Konstantinos Eleftheriadis, Anna Tobler, Manousos-Ioannis Manousakas, Hugo Denier van der Gon, Olga Zografou, Jesús de la Rosa, Francesco Canonaco, Imad El Haddad, Jurgita Ovadnevaitė, Danielle Vienneau, Cristina Colombi, Chunshui Lin, Célia Alves, Fabio Giardi, Yun Cheng, Jarosław Nęcki, Abhishek Upadhyay, Jeni Vasilescu, Jean Sciare, Kaspar R. Daellenbach, Andrea Schemmel, Daniel Trejo Banos, Adrien Jouanny
article en
2 citations

Abstract

Fine particulate matter (PM) poses a major threat to public health, with organic aerosol (OA) being a key component. Major OA sources, hydrocarbon-like OA (HOA), biomass burning OA (BBOA), and oxygenated OA (OOA), have distinct health and environmental impacts. However, OA source apportionment via positive matrix factorization (PMF) applied to aerosol mass spectrometry (AMS) or aerosol chemical speciation monitoring (ACSM) data is costly and limited to a few supersites, leaving over 80% of OA data uncategorized in global monitoring networks. To address this gap, we trained machine learning models to predict HOA, BBOA, and OOA using limited OA source apportionment data and widely available organic carbon (OC) measurements across Europe (2010-2019). Our best performing model expanded the OA source data set 4-fold, yielding 85 000 daily apportionment values across 180 sites. Results show that HOA and BBOA peak in winter, particularly in urban areas, while OOA, consistently the dominant fraction, is more regionally distributed with less seasonal variability. This study provides a significantly expanded OA source data set, enabling better identification of pollution hotspots and supporting high-resolution exposure assessments.

Environmental Science & Technology LettersVol. 12(11)
Eötvös Loránd University (HU), Institut polytechnique de Grenoble (FR), NSF National Center for Atmospheric Research (US), Agenzia Regionale per la Protezione Ambientale del Piemonte (IT), Jagiellonian University (PL), Finnish Meteorological Institute (FI), Centre National de la Recherche Scientifique (FR), University of Helsinki (FI), Netherlands Organisation for Applied Scientific Research (NL), Cyprus Institute (CY), Swiss Tropical and Public Health Institute (CH), Queensland University of Technology (AU), Stockholm University (SE), Tampere University (FI), Deutscher Wetterdienst (DE), Universidad de Granada (ES), University of Basel (CH), Ollscoil na Gaillimhe – University of Galway (IE), University of Nova Gorica (SI), Chinese Academy of Sciences (CN), Université Clermont Auvergne (FR), Peking University (CN), Czech Academy of Sciences (CZ), National Centre of Scientific Research "Demokritos" (GR), Aarhus University (DK), Institut Mines-Télécom (FR), Aix-Marseille Université (FR), European Commission (BE), Paul Scherrer Institute (CH), ETH Zurich (CH), National Institute of Polar Research (JP), Center for Physical Sciences and Technology (LT), Institut National de Recherche pour l'Agriculture, l'Alimentation et l'Environnement (FR), Kjeller Innovasjon (Norway) (NO), Sustainability Institute (ZA), Institute of Atmospheric Sciences and Climate (IT), Environment Agency Austria (AT), Laboratoire de Physico-Chimie de l'Atmosphère (FR), Institut Scientifique de Service Public (BE), Estonian Environmental Research Center (Estonia) (EE), Leibniz Institute for Tropospheric Research (DE), Joint Research Centre (IT), National Observatory of Athens (GR), Climate Centre (NL), Czech Academy of Sciences, Institute of Chemical Process Fundamentals (CZ), Institut des Géosciences de l'Environnement (FR), Swiss Data Science Center (CH), Laboratoire des Sciences du Climat et de l'Environnement (FR), Institut national de l'environnement industriel et des risques (FR), National Research Council (RO), National Institute of Research and Development for Optoelectronics (RO), Laboratoire de Météorologie Physique (FR), Institute for Sustainable Development (ET), Agence Nationale pour la Gestion des Déchets Radioactifs (FR), Centrale Méditerranée (FR), Institute of Environmental Assessment and Water Research (ES), Clermont Université (FR), Institute for Sustainability (GB), Institute of Earth Environment (CN), Bolin Centre for Climate Research (SE), Impact (CA), Data Management (Italy) (IT), Institut de Recherche pour le Développement (FR), Institute for Environmental Research, University of Florence (IT), Imperial College London (GB), University of Tartu (EE), University of Aveiro (PT), East China Normal University (CN), AGH University of Krakow (PL), Swiss Federal Laboratories for Materials Science and Technology (CH), Centre for Science and Environment (IN), Universidad de Huelva (ES), University of Genoa (IT), KTH Royal Institute of Technology (SE), Advanced Research Projects Agency - Energy (US), Université Grenoble Alpes (FR)
Openalex Percentile: Top 15%
Air Quality Monitoring and Forecasting
1.60
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.