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

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

Publikasjonsdetaljer

Publikasjonstype: Vitenskapelig artikkel

Tidsskrift: Environmental Science and Technology Letters (ES&T Letters)

Volum: 12

Utgave: 11

Sider: 1523-1531

Original versjon/DOI: https://doi.org/10.1021/acs.estlett.5c00771

NVA: https://hdl.handle.net/11250/5318739

Sammendrag:

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.