Source apportionment of PM10 particles in the urban atmosphere using PMF and LPO-XGBoost

Atmospheric particulate matter (PM), as a leading part of air pollution, affects health in many ways. Thus, identifying and quantifying the contribution of atmospheric particulate matter sources of PM is vital for developing effective air quality management strategies. Positive Matrix Factorization...

Descripción completa

Detalles Bibliográficos
Autores: Liu, Ying, Jin, Bowen, Zhang, Xun, Liu, Xiansheng, Wang, Tao, Thuy Dinh, Vy Ngoc, Jaffrezo, Jean-Luc, Uzu, Gaëlle, Dominutti, Pamela, Darfeuil, Sophie, Favez, Olivier, Conil, Sébastien, Marchand, Nicolas, Castillo, Sonia, de la Rosa, Jesús D., Grange, Stuart, Hueglin, Christoph, Eleftheriadis, Konstantinos, Diapouli, Evangelia, Manousakas, Manousos-Ioannis, Gini, Maria, Calzolai, Giulia, Alves, Célia, Monge, Marta, Reche, Cristina, Harrison, Roy M., Hopke, Philip K, Alastuey, Andrés, Querol, Xavier
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2025
País:España
Institución:Consejo Superior de Investigaciones Científicas (CSIC)
Repositorio:DIGITAL.CSIC. Repositorio Institucional del CSIC
OAI Identifier:oai:digital.csic.es:10261/388098
Acceso en línea:http://hdl.handle.net/10261/388098
https://api.elsevier.com/content/abstract/scopus_id/105003212578
Access Level:acceso abierto
Palabra clave:Source apportionment
Air pollution
LPO-XGBoost
Machine learning
PMF
http://metadata.un.org/sdg/9
http://metadata.un.org/sdg/3
http://metadata.un.org/sdg/11
Ensure healthy lives and promote well-being for all at all ages
Build resilient infrastructure, promote inclusive and sustainable industrialization and foster innovation
Make cities and human settlements inclusive, safe, resilient and sustainable
id ES_fa4e3d3a403371dd1b0775ed2b4af3b6
oai_identifier_str oai:digital.csic.es:10261/388098
network_acronym_str ES
network_name_str España
repository_id_str
dc.title.none.fl_str_mv Source apportionment of PM10 particles in the urban atmosphere using PMF and LPO-XGBoost
title Source apportionment of PM10 particles in the urban atmosphere using PMF and LPO-XGBoost
spellingShingle Source apportionment of PM10 particles in the urban atmosphere using PMF and LPO-XGBoost
Liu, Ying
Source apportionment
Air pollution
LPO-XGBoost
Machine learning
PMF
http://metadata.un.org/sdg/9
http://metadata.un.org/sdg/3
http://metadata.un.org/sdg/11
Ensure healthy lives and promote well-being for all at all ages
Build resilient infrastructure, promote inclusive and sustainable industrialization and foster innovation
Make cities and human settlements inclusive, safe, resilient and sustainable
title_short Source apportionment of PM10 particles in the urban atmosphere using PMF and LPO-XGBoost
title_full Source apportionment of PM10 particles in the urban atmosphere using PMF and LPO-XGBoost
title_fullStr Source apportionment of PM10 particles in the urban atmosphere using PMF and LPO-XGBoost
title_full_unstemmed Source apportionment of PM10 particles in the urban atmosphere using PMF and LPO-XGBoost
title_sort Source apportionment of PM10 particles in the urban atmosphere using PMF and LPO-XGBoost
dc.creator.none.fl_str_mv Liu, Ying
Jin, Bowen
Zhang, Xun
Liu, Xiansheng
Wang, Tao
Thuy Dinh, Vy Ngoc
Jaffrezo, Jean-Luc
Uzu, Gaëlle
Dominutti, Pamela
Darfeuil, Sophie
Favez, Olivier
Conil, Sébastien
Marchand, Nicolas
Castillo, Sonia
de la Rosa, Jesús D.
Grange, Stuart
Hueglin, Christoph
Eleftheriadis, Konstantinos
Diapouli, Evangelia
Manousakas, Manousos-Ioannis
Gini, Maria
Calzolai, Giulia
Alves, Célia
Monge, Marta
Reche, Cristina
Harrison, Roy M.
Hopke, Philip K
Alastuey, Andrés
Querol, Xavier
author Liu, Ying
author_facet Liu, Ying
Jin, Bowen
Zhang, Xun
Liu, Xiansheng
Wang, Tao
Thuy Dinh, Vy Ngoc
Jaffrezo, Jean-Luc
Uzu, Gaëlle
Dominutti, Pamela
Darfeuil, Sophie
Favez, Olivier
Conil, Sébastien
Marchand, Nicolas
Castillo, Sonia
de la Rosa, Jesús D.
Grange, Stuart
Hueglin, Christoph
Eleftheriadis, Konstantinos
Diapouli, Evangelia
Manousakas, Manousos-Ioannis
Gini, Maria
Calzolai, Giulia
Alves, Célia
Monge, Marta
Reche, Cristina
Harrison, Roy M.
Hopke, Philip K
Alastuey, Andrés
Querol, Xavier
author_role author
author2 Jin, Bowen
Zhang, Xun
Liu, Xiansheng
Wang, Tao
Thuy Dinh, Vy Ngoc
Jaffrezo, Jean-Luc
Uzu, Gaëlle
Dominutti, Pamela
Darfeuil, Sophie
Favez, Olivier
Conil, Sébastien
Marchand, Nicolas
Castillo, Sonia
de la Rosa, Jesús D.
Grange, Stuart
Hueglin, Christoph
Eleftheriadis, Konstantinos
Diapouli, Evangelia
Manousakas, Manousos-Ioannis
Gini, Maria
Calzolai, Giulia
Alves, Célia
Monge, Marta
Reche, Cristina
Harrison, Roy M.
Hopke, Philip K
Alastuey, Andrés
Querol, Xavier
author2_role author
author
author
author
author
author
author
author
author
author
author
author
author
author
author
author
author
author
author
author
author
author
author
author
author
author
author
author
dc.contributor.none.fl_str_mv European Commission
0000-0002-0228-5551
0000-0001-5685-0993
0000-0002-9876-6383
0000-0003-3307-2548
0000-0001-7760-3350
0000-0003-2265-4905
0000-0002-8244-2018
0000-0002-9476-1470
0000-0003-3231-3186
0000-0002-2684-5226
0000-0003-2367-9661
Consejo Superior de Investigaciones Científicas [https://ror.org/02gfc7t72]
dc.subject.none.fl_str_mv Source apportionment
Air pollution
LPO-XGBoost
Machine learning
PMF
http://metadata.un.org/sdg/9
http://metadata.un.org/sdg/3
http://metadata.un.org/sdg/11
Ensure healthy lives and promote well-being for all at all ages
Build resilient infrastructure, promote inclusive and sustainable industrialization and foster innovation
Make cities and human settlements inclusive, safe, resilient and sustainable
topic Source apportionment
Air pollution
LPO-XGBoost
Machine learning
PMF
http://metadata.un.org/sdg/9
http://metadata.un.org/sdg/3
http://metadata.un.org/sdg/11
Ensure healthy lives and promote well-being for all at all ages
Build resilient infrastructure, promote inclusive and sustainable industrialization and foster innovation
Make cities and human settlements inclusive, safe, resilient and sustainable
description Atmospheric particulate matter (PM), as a leading part of air pollution, affects health in many ways. Thus, identifying and quantifying the contribution of atmospheric particulate matter sources of PM is vital for developing effective air quality management strategies. Positive Matrix Factorization (PMF) is one of the most common methods for source apportionment. However, PMF has some limitations, particularly its assumption that each source contributes linearly. In reality, some sources may exhibit nonlinear behaviors, which can compromise the accuracy of source apportionment. This study introduces a Lung Performance Optimization-based XGBoost (LPO-XGBoost) model, which leverages adaptive optimization principles inspired by lung function to enhance classic PM source apportionment. We demonstrate the potential for efficient, real-time application of the LPO-XGBoost model across 21 monitoring sites in 6 European countries. Trained and validated on extensive environmental datasets, the model is capable of predicting major pollution sources, including road traffic, biomass burning, crustal, industrial, nitrate-rich particles, sulfate-rich particles, heavy fuel oil, and sea salt. It outperforms other machine learning models with an overall predictive coefficient of determination (r2 = 0.88). Notably, the model performs exceptionally well in predicting sources such as sea salt (r2 = 0.97) and biomass burning (r2 = 0.89), but shows lower accuracy for the sulfate-rich particles source (r2 = 0.75). Comparative analyses with models including Random Forest (RF), Support Vector Machine (SVM), and their LPO-enhanced variants confirm that LPO-XGBoost provides the most reliable performance in estimating pollution source contributions, offering scalability and robustness ideal for high-time-resolution observational data. This model has significant potential to support targeted air quality management strategies. Future research should focus on expanding key species measurements at monitoring sites, ensuring consistent temporal coverage, and optimizing the model for improved mixed-source predictions to strengthen its applicability in comprehensive urban air quality assessments.
publishDate 2025
dc.date.none.fl_str_mv 2025
2025
2025
dc.type.none.fl_str_mv info:eu-repo/semantics/article
http://purl.org/coar/resource_type/c_6501
Publisher's version
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/10261/388098
https://api.elsevier.com/content/abstract/scopus_id/105003212578
url http://hdl.handle.net/10261/388098
https://api.elsevier.com/content/abstract/scopus_id/105003212578
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv #PLACEHOLDER_PARENT_METADATA_VALUE#
info:eu-repo/grantAgreement/EC/H2020/101036245
Environmental research
https://doi.org/10.1016/j.envres.2025.121659

dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.publisher.none.fl_str_mv Elsevier
publisher.none.fl_str_mv Elsevier
dc.source.none.fl_str_mv reponame:DIGITAL.CSIC. Repositorio Institucional del CSIC
instname:Consejo Superior de Investigaciones Científicas (CSIC)
instname_str Consejo Superior de Investigaciones Científicas (CSIC)
reponame_str DIGITAL.CSIC. Repositorio Institucional del CSIC
collection DIGITAL.CSIC. Repositorio Institucional del CSIC
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869425172474232832
spelling Source apportionment of PM10 particles in the urban atmosphere using PMF and LPO-XGBoostLiu, YingJin, BowenZhang, XunLiu, XianshengWang, TaoThuy Dinh, Vy NgocJaffrezo, Jean-LucUzu, GaëlleDominutti, PamelaDarfeuil, SophieFavez, OlivierConil, SébastienMarchand, NicolasCastillo, Soniade la Rosa, Jesús D.Grange, StuartHueglin, ChristophEleftheriadis, KonstantinosDiapouli, EvangeliaManousakas, Manousos-IoannisGini, MariaCalzolai, GiuliaAlves, CéliaMonge, MartaReche, CristinaHarrison, Roy M.Hopke, Philip KAlastuey, AndrésQuerol, XavierSource apportionmentAir pollutionLPO-XGBoostMachine learningPMFhttp://metadata.un.org/sdg/9http://metadata.un.org/sdg/3http://metadata.un.org/sdg/11Ensure healthy lives and promote well-being for all at all agesBuild resilient infrastructure, promote inclusive and sustainable industrialization and foster innovationMake cities and human settlements inclusive, safe, resilient and sustainableAtmospheric particulate matter (PM), as a leading part of air pollution, affects health in many ways. Thus, identifying and quantifying the contribution of atmospheric particulate matter sources of PM is vital for developing effective air quality management strategies. Positive Matrix Factorization (PMF) is one of the most common methods for source apportionment. However, PMF has some limitations, particularly its assumption that each source contributes linearly. In reality, some sources may exhibit nonlinear behaviors, which can compromise the accuracy of source apportionment. This study introduces a Lung Performance Optimization-based XGBoost (LPO-XGBoost) model, which leverages adaptive optimization principles inspired by lung function to enhance classic PM source apportionment. We demonstrate the potential for efficient, real-time application of the LPO-XGBoost model across 21 monitoring sites in 6 European countries. Trained and validated on extensive environmental datasets, the model is capable of predicting major pollution sources, including road traffic, biomass burning, crustal, industrial, nitrate-rich particles, sulfate-rich particles, heavy fuel oil, and sea salt. It outperforms other machine learning models with an overall predictive coefficient of determination (r2 = 0.88). Notably, the model performs exceptionally well in predicting sources such as sea salt (r2 = 0.97) and biomass burning (r2 = 0.89), but shows lower accuracy for the sulfate-rich particles source (r2 = 0.75). Comparative analyses with models including Random Forest (RF), Support Vector Machine (SVM), and their LPO-enhanced variants confirm that LPO-XGBoost provides the most reliable performance in estimating pollution source contributions, offering scalability and robustness ideal for high-time-resolution observational data. This model has significant potential to support targeted air quality management strategies. Future research should focus on expanding key species measurements at monitoring sites, ensuring consistent temporal coverage, and optimizing the model for improved mixed-source predictions to strengthen its applicability in comprehensive urban air quality assessments.This study has been supported and been done by RI-URBANS project (Research Infrastructures Services Reinforcing Air Quality Monitoring Capacities in European Urban & Industrial Areas, European Union's Horizon 2020 research and innovation program, Green Deal, European Commission, contract 101036245). Furthermore, additional support has been received from State Key Laboratory of Resources and Environmental Information System, the National Natural Science Foundation of China (42407566, 42205099, 72441001), and the Chunhui Project Foundation of the Education Department of China (HZKY20220053), the Science Fund for Creative Research Groups of the National Natural Science Foundation of China (72221002) that carried out the ML implementation. Meanwhile, samples in France were collected within many research and Air Quality assessment programs, including the programs CARA (funded by the Ministry of Environment within the LCSQA), DECOMBIO, CAMERA, and QAMECS (all funded by Ademe), ACME and MIAI-Airquality (funded by University Grenoble Alpes), OPE – Andra (funded by Andra), and multiple fundings by Atmo AuRA, Atmo Sud, Atmo Grand Est, Atmo Haut de France, Atmo Normandie, for the sampling and analyses. We would like to express our deep thanks to many people in the AASQA France for the sampling of all these samples, and to people in several laboratories in France, including IGE, for the analyses of these samples. The University of Aveiro thanks the Foundation for Science and Technology (FCT) for funding CESAM (UID Centro de Estudos do Ambiente e do Mar + LAP/0094/2020). The University of Granada acknowledges the financial support of the Spanish Ministry of Science and Innovation through the project ELPIS PID2020-120015RB-I00. Samples in Switzerland were collected by the Swiss National Air Pollution Monitoring Network NABEL (BAFU/Empa).Peer reviewedElsevierEuropean Commission0000-0002-0228-55510000-0001-5685-09930000-0002-9876-63830000-0003-3307-25480000-0001-7760-33500000-0003-2265-49050000-0002-8244-20180000-0002-9476-14700000-0003-3231-31860000-0002-2684-52260000-0003-2367-9661Consejo Superior de Investigaciones Científicas [https://ror.org/02gfc7t72]202520252025info:eu-repo/semantics/articlehttp://purl.org/coar/resource_type/c_6501Publisher's versioninfo:eu-repo/semantics/publishedVersionhttp://hdl.handle.net/10261/388098https://api.elsevier.com/content/abstract/scopus_id/105003212578reponame:DIGITAL.CSIC. Repositorio Institucional del CSICinstname:Consejo Superior de Investigaciones Científicas (CSIC)Inglés#PLACEHOLDER_PARENT_METADATA_VALUE#info:eu-repo/grantAgreement/EC/H2020/101036245Environmental researchhttps://doi.org/10.1016/j.envres.2025.121659Síinfo:eu-repo/semantics/openAccessoai:digital.csic.es:10261/3880982026-05-22T06:33:51Z
score 15.811543