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 M. 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

doi:10.1021/acs.estlett.5c00771

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 PetitJesús 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 M. 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^*

^*Corresponding author for this work

School of Ecology and Environmental Sciences

Research output: Contribution to journal › Article › peer-review

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.

Original language	English
Pages (from-to)	1523-1531
Number of pages	9
Journal	Environmental Science and Technology Letters
Volume	12
Issue number	11
DOIs	https://doi.org/10.1021/acs.estlett.5c00771
State	Published - 11 Nov 2025

Keywords

air quality
deep learning
Europe data set
machine learning
organic aerosols
source apportionment
spatial−temporal analysis

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1021/acs.estlett.5c00771

Cite this

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., ... El Haddad, I. (2025). Machine-Learning-Driven Reconstruction of Organic Aerosol Sources across Dense Monitoring Networks in Europe. Environmental Science and Technology Letters, 12(11), 1523-1531. https://doi.org/10.1021/acs.estlett.5c00771

@article{a92f8921ea2d4377b5bd0454e8984899,

title = "Machine-Learning-Driven Reconstruction of Organic Aerosol Sources across Dense Monitoring Networks in Europe",

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.",

keywords = "air quality, deep learning, Europe data set, machine learning, organic aerosols, source apportionment, spatial−temporal analysis",

author = "Adrien Jouanny and Abhishek Upadhyay and Jianhui Jiang and Petros Vasilakos and Marta Via and Yun Cheng and Benjamin Flueckiger and Ga{\"e}lle Uzu and Jaffrezo, \{Jean Luc\} and C{\'e}line Voiron and Olivier Favez and Hasna Chebaicheb and Aude Bourin and Anna Font and V{\'e}ronique Riffault and Evelyn Freney and Nicolas Marchand and Benjamin Chazeau and S{\'e}bastien Conil and Petit, \{Jean Eudes\} and \{de la Rosa\}, \{Jes{\'u}s D.\} and \{de la Campa\}, \{Ana Sanchez\} and Navarro, \{Daniel Sanchez Rodas\} and Sonia Castillo and Andr{\'e}s Alastuey and Xavier Querol and Cristina Reche and Minguill{\'o}n, \{Mar{\'i}a Cruz\} and Marek Maasikmets and Hannes Keernik and Fabio Giardi and Cristina Colombi and Eleonora Cuccia and Stefania Gilardoni and Matteo Rinaldi and Marco Paglione and Vanes Poluzzi and Dario Massab{\`o} and Claudio Belis and Stuart Grange and Christoph Hueglin and Francesco Canonaco and Anna Tobler and Timonen, \{Hilkka J.\} and Minna Aurela and Mikael Ehn and Iasonas Stavroulas and Aikaterini Bougiatioti and Konstantinos Eleftheriadis and Gini, \{Maria I.\} and Olga Zografou and Manousakas, \{Manousos Ioannis\} and Chen, \{Gang Ian\} and Green, \{David Christopher\} and Petra Pokorn{\'a} and Petr Vodi{\v c}ka and Radek Lhotka and Jaroslav Schwarz and Andrea Schemmel and Samira Atabakhsh and Hartmut Herrmann and Laurent Poulain and Harald Flentje and Liine Heikkinen and Varun Kumar and \{Denier van der Gon\}, \{Hugo Anne\} and Wenche Aas and Platt, \{Stephen M.\} and Yttri, \{Karl Espen\} and Imre Salma and Anik{\'o} Vasanits and Benjamin Bergmans and Yulia Sosedova and Jaroslaw Necki and Jurgita Ovadnevaite and Chunshui Lin and Julija Pauraite and Michael Pikridas and Jean Sciare and Jeni Vasilescu and Livio Belegante and C{\'e}lia Alves and Slowik, \{Jay G.\} and Nicole Probst-Hensch and Danielle Vienneau and Pr{\'e}v{\^o}t, \{Andr{\'e} S.H.\} and Medbouhi, \{Aniss Aiman\} and Banos, \{Daniel Trejo\} and \{de Hoogh\}, Kees and Daellenbach, \{Kaspar R.\} and Ekaterina Krymova and \{El Haddad\}, Imad",

note = "Publisher Copyright: {\textcopyright} 2025 The Authors. Published by American Chemical Society",

year = "2025",

month = nov,

day = "11",

doi = "10.1021/acs.estlett.5c00771",

language = "英语",

volume = "12",

pages = "1523--1531",

journal = "Environmental Science and Technology Letters",

issn = "2328-8930",

publisher = "American Chemical Society",

number = "11",

}

Jouanny, A, Upadhyay, A, Jiang, J, Vasilakos, P, Via, M, Cheng, Y, Flueckiger, B, Uzu, G, Jaffrezo, JL, Voiron, C, Favez, O, Chebaicheb, H, Bourin, A, Font, A, Riffault, V, Freney, E, Marchand, N, Chazeau, B, Conil, S, Petit, JE, de la Rosa, JD, de la Campa, AS, Navarro, DSR, Castillo, S, Alastuey, A, Querol, X, Reche, C, Minguillón, MC, Maasikmets, M, Keernik, H, Giardi, F, Colombi, C, Cuccia, E, Gilardoni, S, Rinaldi, M, Paglione, M, Poluzzi, V, Massabò, D, Belis, C, Grange, S, Hueglin, C, Canonaco, F, Tobler, A, Timonen, HJ, Aurela, M, Ehn, M, Stavroulas, I, Bougiatioti, A, Eleftheriadis, K, Gini, MI, Zografou, O, Manousakas, MI, Chen, GI, Green, DC, Pokorná, P, Vodička, P, Lhotka, R, Schwarz, J, Schemmel, A, Atabakhsh, S, Herrmann, H, Poulain, L, Flentje, H, Heikkinen, L, Kumar, V, Denier van der Gon, HA, Aas, W, Platt, SM, Yttri, KE, Salma, I, Vasanits, A, Bergmans, B, Sosedova, Y, Necki, J, Ovadnevaite, J, Lin, C, Pauraite, J, Pikridas, M, Sciare, J, Vasilescu, J, Belegante, L, Alves, C, Slowik, JG, Probst-Hensch, N, Vienneau, D, Prévôt, ASH, Medbouhi, AA, Banos, DT, de Hoogh, K, Daellenbach, KR, Krymova, E & El Haddad, I 2025, 'Machine-Learning-Driven Reconstruction of Organic Aerosol Sources across Dense Monitoring Networks in Europe', Environmental Science and Technology Letters, vol. 12, no. 11, pp. 1523-1531. https://doi.org/10.1021/acs.estlett.5c00771

TY - JOUR

T1 - Machine-Learning-Driven Reconstruction of Organic Aerosol Sources across Dense Monitoring Networks in Europe

AU - Jouanny, Adrien

AU - Upadhyay, Abhishek

AU - Jiang, Jianhui

AU - Vasilakos, Petros

AU - Via, Marta

AU - Cheng, Yun

AU - Flueckiger, Benjamin

AU - Uzu, Gaëlle

AU - Jaffrezo, Jean Luc

AU - Voiron, Céline

AU - Favez, Olivier

AU - Chebaicheb, Hasna

AU - Bourin, Aude

AU - Font, Anna

AU - Riffault, Véronique

AU - Freney, Evelyn

AU - Marchand, Nicolas

AU - Chazeau, Benjamin

AU - Conil, Sébastien

AU - Petit, Jean Eudes

AU - de la Rosa, Jesús D.

AU - de la Campa, Ana Sanchez

AU - Navarro, Daniel Sanchez Rodas

AU - Castillo, Sonia

AU - Alastuey, Andrés

AU - Querol, Xavier

AU - Reche, Cristina

AU - Minguillón, María Cruz

AU - Maasikmets, Marek

AU - Keernik, Hannes

AU - Giardi, Fabio

AU - Colombi, Cristina

AU - Cuccia, Eleonora

AU - Gilardoni, Stefania

AU - Rinaldi, Matteo

AU - Paglione, Marco

AU - Poluzzi, Vanes

AU - Massabò, Dario

AU - Belis, Claudio

AU - Grange, Stuart

AU - Hueglin, Christoph

AU - Canonaco, Francesco

AU - Tobler, Anna

AU - Timonen, Hilkka J.

AU - Aurela, Minna

AU - Ehn, Mikael

AU - Stavroulas, Iasonas

AU - Bougiatioti, Aikaterini

AU - Eleftheriadis, Konstantinos

AU - Gini, Maria I.

AU - Zografou, Olga

AU - Manousakas, Manousos Ioannis

AU - Chen, Gang Ian

AU - Green, David Christopher

AU - Pokorná, Petra

AU - Vodička, Petr

AU - Lhotka, Radek

AU - Schwarz, Jaroslav

AU - Schemmel, Andrea

AU - Atabakhsh, Samira

AU - Herrmann, Hartmut

AU - Poulain, Laurent

AU - Flentje, Harald

AU - Heikkinen, Liine

AU - Kumar, Varun

AU - Denier van der Gon, Hugo Anne

AU - Aas, Wenche

AU - Platt, Stephen M.

AU - Yttri, Karl Espen

AU - Salma, Imre

AU - Vasanits, Anikó

AU - Bergmans, Benjamin

AU - Sosedova, Yulia

AU - Necki, Jaroslaw

AU - Ovadnevaite, Jurgita

AU - Lin, Chunshui

AU - Pauraite, Julija

AU - Pikridas, Michael

AU - Sciare, Jean

AU - Vasilescu, Jeni

AU - Belegante, Livio

AU - Alves, Célia

AU - Slowik, Jay G.

AU - Probst-Hensch, Nicole

AU - Vienneau, Danielle

AU - Prévôt, André S.H.

AU - Medbouhi, Aniss Aiman

AU - Banos, Daniel Trejo

AU - de Hoogh, Kees

AU - Daellenbach, Kaspar R.

AU - Krymova, Ekaterina

AU - El Haddad, Imad

PY - 2025/11/11

Y1 - 2025/11/11

N2 - 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.

AB - 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.

KW - air quality

KW - deep learning

KW - Europe data set

KW - machine learning

KW - organic aerosols

KW - source apportionment

KW - spatial−temporal analysis

UR - https://www.scopus.com/pages/publications/105021233032

U2 - 10.1021/acs.estlett.5c00771

DO - 10.1021/acs.estlett.5c00771

M3 - 文章

AN - SCOPUS:105021233032

SN - 2328-8930

VL - 12

SP - 1523

EP - 1531

JO - Environmental Science and Technology Letters

JF - Environmental Science and Technology Letters

IS - 11

ER -

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

Abstract

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this