Machine-Learning-Driven Reconstruction of Organic Aerosol Sources across Dense Monitoring Networks in Europe
Environmental Science & Technology Letters · 11.11.2025 · 12 (11) · 1523-1531
DOI: 10.1021/acs.estlett.5c00771 ↗Kurz gefasst
Fachartikel in der Zeitschrift Environmental Science & Technology Letters, online erschienen am 20.10.2025. Verfasst von Adrien Jouanny und 59 weiteren Autor:innen. Beteiligte Einrichtung: PSI Center for Energy and Environmental Sciences, 5232 Villigen, Switzerland. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key Research and Development Program of China, European Regional Development Fund, Department of the Environment, Climate and Communications.
Abstract (Originalsprache)
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.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- PSI Center for Energy and Environmental Sciences, 5232 Villigen, Switzerland.
- Global Institute for Urban and Regional Sustainability, School of Ecological and Environmental Sciences, East China Normal University, Shanghai 200231, China.
- Center for Atmospheric Research, University of Nova Gorica, SI-5000 Nova Gorica, Slovenia.
- Swiss Data Science Center, EPFL and ETH Zürich, 8092 Zürich, Switzerland.
- Swiss Tropical and Public Health Institute, Kreuzstraße 2, 4123 Allschwil, Switzerland.
- University of Basel, 4001 Basel, Switzerland.
ORCID-Profile: Adrien Jouanny, Abhishek Upadhyay, Jianhui Jiang, Anna Font, Jean-Eudes Petit, Andrés Alastuey, Xavier Querol, Stefania Gilardoni, Matteo Rinaldi, Marco Paglione, Claudio Belis, Hilkka J Timonen, Minna Aurela, Mikael Ehn, Iasonas Stavroulas, Konstantinos Eleftheriadis, Gang Ian Chen, David Christopher Green, Samira Atabakhsh
Förderung
- National Key Research and Development Program of China
- European Regional Development Fund
- Department of the Environment, Climate and Communications
- Akademie Ved Cesk? Republiky
- R?gion Hauts-de-France
- National Natural Science Foundation of China
- Environmental Protection Agency
- Consell Catal? de Recerca i Innovaci?
Zitieren
APA
Jouanny, A., Upadhyay, A., Jiang, J., Vasilakos, P., Via, M., Cheng, Y., Flueckiger, B., Uzu, G., Jaffrezo, J. L., Voiron, C., Favez, O., Chebaicheb, H., Bourin, A., Font, A., Riffault, V., Freney, E., Marchand, N., Chazeau, B., Conil, S., …, & Atabakhsh, S. (2025). Machine-Learning-Driven Reconstruction of Organic Aerosol Sources across Dense Monitoring Networks in Europe. Environmental Science & Technology Letters, 12(11), 1523-1531. https://doi.org/10.1021/acs.estlett.5c00771
Vancouver
Jouanny A, Upadhyay A, Jiang J, Vasilakos P, Via M, Cheng Y, et al. Machine-Learning-Driven Reconstruction of Organic Aerosol Sources across Dense Monitoring Networks in Europe. Environmental Science & Technology Letters. 2025;12(11):1523-1531. doi:10.1021/acs.estlett.5c00771
BibTeX
@article{Jouanny2025,
author = {Jouanny, Adrien and Upadhyay, Abhishek and Jiang, Jianhui and Vasilakos, Petros and Via, Marta and Cheng, Yun and Flueckiger, Benjamin and Uzu, Gaëlle and Jaffrezo, Jean-Luc and Voiron, Céline and Favez, Olivier and Chebaicheb, Hasna and Bourin, Aude and Font, Anna and Riffault, Véronique and Freney, Evelyn and Marchand, Nicolas and Chazeau, Benjamin and Conil, Sébastien and Petit, Jean-Eudes and de la Rosa, Jesús D and de la Campa, Ana Sanchez and Navarro, Daniel Sanchez-Rodas and Castillo, Sonia and Alastuey, Andrés and Querol, Xavier and Reche, Cristina and Minguillón, María Cruz and Maasikmets, Marek and Keernik, Hannes and Giardi, Fabio and Colombi, Cristina and Cuccia, Eleonora and Gilardoni, Stefania and Rinaldi, Matteo and Paglione, Marco and Poluzzi, Vanes and Massabò, Dario and Belis, Claudio and Grange, Stuart and Hueglin, Christoph and Canonaco, Francesco and Tobler, Anna and Timonen, Hilkka J and Aurela, Minna and Ehn, Mikael and Stavroulas, Iasonas and Bougiatioti, Aikaterini and Eleftheriadis, Konstantinos and Gini, Maria I and Zografou, Olga and Manousakas, Manousos-Ioannis and Chen, Gang Ian and Green, David Christopher and Pokorná, Petra and Vodička, Petr and Lhotka, Radek and Schwarz, Jaroslav and Schemmel, Andrea and Atabakhsh, Samira},
title = {Machine-Learning-Driven Reconstruction of Organic Aerosol Sources across Dense Monitoring Networks in Europe},
journal = {Environmental Science & Technology Letters},
year = {2025},
volume = {12},
number = {11},
pages = {1523--1531},
doi = {10.1021/acs.estlett.5c00771}
}
EUVIMED