Articles | Volume 23, issue 9
https://doi.org/10.5194/acp-23-5317-2023
© Author(s) 2023. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/acp-23-5317-2023
© Author(s) 2023. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Technical note: Improving the European air quality forecast of the Copernicus Atmosphere Monitoring Service using machine learning techniques
Jean-Maxime Bertrand
Institut National de l'Environnement Industriel et des Risques (INERIS), Parc Alata, BP2, 60550 Verneuil-en-Halatte, France
Frédérik Meleux
CORRESPONDING AUTHOR
Institut National de l'Environnement Industriel et des Risques (INERIS), Parc Alata, BP2, 60550 Verneuil-en-Halatte, France
Anthony Ung
Institut National de l'Environnement Industriel et des Risques (INERIS), Parc Alata, BP2, 60550 Verneuil-en-Halatte, France
Gaël Descombes
Institut National de l'Environnement Industriel et des Risques (INERIS), Parc Alata, BP2, 60550 Verneuil-en-Halatte, France
Augustin Colette
Institut National de l'Environnement Industriel et des Risques (INERIS), Parc Alata, BP2, 60550 Verneuil-en-Halatte, France
Related authors
No articles found.
Marc Guevara, Augustin Colette, Antoine Guion, Valentin Petiot, Mario Adani, Joaquim Arteta, Anna Benedictow, Robert Bergström, Andrea Bolignano, Paula Camps, Ana C. Carvalho, Jesper Heile Christensen, Florian Couvidat, Ilia D’Elia, Hugo Denier van der Gon, Gaël Descombes, John Douros, Hilde Fagerli, Yalda Fatahi, Elmar Friese, Lise Frohn, Michael Gauss, Camilla Geels, Risto Hänninen, Kaj Hansen, Oriol Jorba, Jacek W. Kaminski, Rostislav Kouznetsov, Richard Kranenburg, Jeroen Kuenen, Victor Lannuque, Frédérik Meleux, Agnes Nyíri, Yuliia Palamarchuk, Carlos Pérez García-Pando, Lennard Robertson, Felicita Russo, Arjo Segers, Mikhail Sofiev, Joanna Struzewska, Renske Timmermans, Andreas Uppstu, Alvaro Valdebenito, and Zhuyun Ye
EGUsphere, https://doi.org/10.5194/egusphere-2025-1287, https://doi.org/10.5194/egusphere-2025-1287, 2025
Short summary
Short summary
Air quality models require hourly emissions to accurately represent dispersion and physico-chemical processes in the atmosphere. Since emission inventories are typically provided at the annual level, emissions are downscaled to a refined temporal resolution using temporal profiles. This study quantifies the impact of using new anthropogenic temporal profiles on the performance of an European air quality multi-model ensemble. Overall, the findings indicate an improvement of the modelling results.
Antoine Guion, Florian Couvidat, Marc Guevara, and Augustin Colette
Atmos. Chem. Phys., 25, 2807–2827, https://doi.org/10.5194/acp-25-2807-2025, https://doi.org/10.5194/acp-25-2807-2025, 2025
Short summary
Short summary
The residential sector can cause high background levels of pollutants and pollution peaks in winter. Its emissions are dominated by space heating and show strong daily variations linked to changes in outside temperature. Using heating degree days, we provide country- and species-dependent parameters for the distribution of these emissions, improving the performance of the CHIMERE air quality model. This also allows annual residential emissions to be projected before official publications.
Augustin Colette, Gaëlle Collin, François Besson, Etienne Blot, Vincent Guidard, Frederik Meleux, Adrien Royer, Valentin Petiot, Claire Miller, Oihana Fermond, Alizé Jeant, Mario Adani, Joaquim Arteta, Anna Benedictow, Robert Bergström, Dene Bowdalo, Jorgen Brandt, Gino Briganti, Ana C. Carvalho, Jesper Heile Christensen, Florian Couvidat, Ilia D’Elia, Massimo D’Isidoro, Hugo Denier van der Gon, Gaël Descombes, Enza Di Tomaso, John Douros, Jeronimo Escribano, Henk Eskes, Hilde Fagerli, Yalda Fatahi, Johannes Flemming, Elmar Friese, Lise Frohn, Michael Gauss, Camilla Geels, Guido Guarnieri, Marc Guevara, Antoine Guion, Jonathan Guth, Risto Hänninen, Kaj Hansen, Ulas Im, Ruud Janssen, Marine Jeoffrion, Mathieu Joly, Luke Jones, Oriol Jorba, Evgeni Kadantsev, Michael Kahnert, Jacek W. Kaminski, Rostislav Kouznetsov, Richard Kranenburg, Jeroen Kuenen, Anne Caroline Lange, Joachim Langner, Victor Lannuque, Francesca Macchia, Astrid Manders, Mihaela Mircea, Agnes Nyiri, Miriam Olid, Carlos Pérez García-Pando, Yuliia Palamarchuk, Antonio Piersanti, Blandine Raux, Miha Razinger, Lennard Robertson, Arjo Segers, Martijn Schaap, Pilvi Siljamo, David Simpson, Mikhail Sofiev, Anders Stangel, Joanna Struzewska, Carles Tena, Renske Timmermans, Thanos Tsikerdekis, Svetlana Tsyro, Svyatoslav Tyuryakov, Anthony Ung, Andreas Uppstu, Alvaro Valdebenito, Peter van Velthoven, Lina Vitali, Zhuyun Ye, Vincent-Henri Peuch, and Laurence Rouïl
EGUsphere, https://doi.org/10.5194/egusphere-2024-3744, https://doi.org/10.5194/egusphere-2024-3744, 2024
Short summary
Short summary
The Copernicus Atmosphere Monitoring Service – Regional Production delivers daily forecasts, analyses, and reanalyses of air quality in Europe. The Service relies on a distributed modelling production by eleven leading European modelling teams following stringent requirements with an operational design which has no equivalent in the world. All the products are full, free, open and quality assured and disseminated with a high level of reliability.
Jean-Philippe Putaud, Enrico Pisoni, Alexander Mangold, Christoph Hueglin, Jean Sciare, Michael Pikridas, Chrysanthos Savvides, Jakub Ondracek, Saliou Mbengue, Alfred Wiedensohler, Kay Weinhold, Maik Merkel, Laurent Poulain, Dominik van Pinxteren, Hartmut Herrmann, Andreas Massling, Claus Nordstroem, Andrés Alastuey, Cristina Reche, Noemí Pérez, Sonia Castillo, Mar Sorribas, Jose Antonio Adame, Tuukka Petaja, Katrianne Lehtipalo, Jarkko Niemi, Véronique Riffault, Joel F. de Brito, Augustin Colette, Olivier Favez, Jean-Eudes Petit, Valérie Gros, Maria I. Gini, Stergios Vratolis, Konstantinos Eleftheriadis, Evangelia Diapouli, Hugo Denier van der Gon, Karl Espen Yttri, and Wenche Aas
Atmos. Chem. Phys., 23, 10145–10161, https://doi.org/10.5194/acp-23-10145-2023, https://doi.org/10.5194/acp-23-10145-2023, 2023
Short summary
Short summary
Many European people are still exposed to levels of air pollution that can affect their health. COVID-19 lockdowns in 2020 were used to assess the impact of the reduction in human mobility on air pollution across Europe by comparing measurement data with values that would be expected if no lockdown had occurred. We show that lockdown measures did not lead to consistent decreases in the concentrations of fine particulate matter suspended in the air, and we investigate why.
John Douros, Henk Eskes, Jos van Geffen, K. Folkert Boersma, Steven Compernolle, Gaia Pinardi, Anne-Marlene Blechschmidt, Vincent-Henri Peuch, Augustin Colette, and Pepijn Veefkind
Geosci. Model Dev., 16, 509–534, https://doi.org/10.5194/gmd-16-509-2023, https://doi.org/10.5194/gmd-16-509-2023, 2023
Short summary
Short summary
We focus on the challenges associated with comparing atmospheric composition models with satellite products such as tropospheric NO2 columns. The aim is to highlight the methodological difficulties and propose sound ways of doing such comparisons. Building on the comparisons, a new satellite product is proposed and made available, which takes advantage of higher-resolution, regional atmospheric modelling to improve estimates of troposheric NO2 columns over Europe.
Svetlana Tsyro, Wenche Aas, Augustin Colette, Camilla Andersson, Bertrand Bessagnet, Giancarlo Ciarelli, Florian Couvidat, Kees Cuvelier, Astrid Manders, Kathleen Mar, Mihaela Mircea, Noelia Otero, Maria-Teresa Pay, Valentin Raffort, Yelva Roustan, Mark R. Theobald, Marta G. Vivanco, Hilde Fagerli, Peter Wind, Gino Briganti, Andrea Cappelletti, Massimo D'Isidoro, and Mario Adani
Atmos. Chem. Phys., 22, 7207–7257, https://doi.org/10.5194/acp-22-7207-2022, https://doi.org/10.5194/acp-22-7207-2022, 2022
Short summary
Short summary
Particulate matter (PM) air pollution causes adverse health effects. In Europe, the emissions caused by anthropogenic activities have been reduced in the last decades. To assess the efficiency of emission reductions in improving air quality, we have studied the evolution of PM pollution in Europe. Simulations with six air quality models and observational data indicate a decrease in PM concentrations by 10 % to 30 % across Europe from 2000 to 2010, which is mainly a result of emission reductions.
Elsa Real, Florian Couvidat, Anthony Ung, Laure Malherbe, Blandine Raux, Alicia Gressent, and Augustin Colette
Earth Syst. Sci. Data, 14, 2419–2443, https://doi.org/10.5194/essd-14-2419-2022, https://doi.org/10.5194/essd-14-2419-2022, 2022
Short summary
Short summary
This paper describes a 16-year (2000–2015) dataset of air pollution concentrations and air quality indicators over France combining background measurements and modeling. Hourly concentrations and regulatory indicators of NO2, O3, PM10 and PM2.5 are produced with 4 km spatial resolution. The overall dataset has been cross-validated and showed overall very good results. We hope that this open-access publication will facilitate further studies on the impacts of air pollution.
Augustin Colette, Laurence Rouïl, Frédérik Meleux, Vincent Lemaire, and Blandine Raux
Geosci. Model Dev., 15, 1441–1465, https://doi.org/10.5194/gmd-15-1441-2022, https://doi.org/10.5194/gmd-15-1441-2022, 2022
Short summary
Short summary
We introduce the first toolbox that allows exploration of the benefits of air pollution mitigation scenarios in the every-day air quality forecasts through a web interface. The toolbox relies on the joint use of chemistry-transport models (CTMs) and surrogate modelling techniques.
Jean-Philippe Putaud, Luca Pozzoli, Enrico Pisoni, Sebastiao Martins Dos Santos, Friedrich Lagler, Guido Lanzani, Umberto Dal Santo, and Augustin Colette
Atmos. Chem. Phys., 21, 7597–7609, https://doi.org/10.5194/acp-21-7597-2021, https://doi.org/10.5194/acp-21-7597-2021, 2021
Short summary
Short summary
To determine the impact of the COVID lockdown on air quality in northern Italy, measurements of atmospheric pollutants (NO2, PM10, O3, NO, SO2 ) were compared to the output of a model ignoring the lockdown. We found that NO2 decreased on average by −30 % to −40 %. Unlike NO2, PM10 was not significantly affected due to the compensation of decreased emissions from traffic by increased emissions from domestic heating and/or by changes in atmospheric chemistry enhancing secondary aerosol formation.
Jérôme Barré, Hervé Petetin, Augustin Colette, Marc Guevara, Vincent-Henri Peuch, Laurence Rouil, Richard Engelen, Antje Inness, Johannes Flemming, Carlos Pérez García-Pando, Dene Bowdalo, Frederik Meleux, Camilla Geels, Jesper H. Christensen, Michael Gauss, Anna Benedictow, Svetlana Tsyro, Elmar Friese, Joanna Struzewska, Jacek W. Kaminski, John Douros, Renske Timmermans, Lennart Robertson, Mario Adani, Oriol Jorba, Mathieu Joly, and Rostislav Kouznetsov
Atmos. Chem. Phys., 21, 7373–7394, https://doi.org/10.5194/acp-21-7373-2021, https://doi.org/10.5194/acp-21-7373-2021, 2021
Short summary
Short summary
This study provides a comprehensive assessment of air quality changes across the main European urban areas induced by the COVID-19 lockdown using satellite observations, surface site measurements, and the forecasting system from the Copernicus Atmospheric Monitoring Service (CAMS). We demonstrate the importance of accounting for weather and seasonal variability when calculating such estimates.
Cited articles
Badia, A. and Jorba, O.: Gas-phase evaluation of the online NMMB/BSC-CTM model over Europe for 2010 in the framework of the AQMEII-Phase2 project, Atmos. Environ., 115, 657–669, https://doi.org/10.1016/j.atmosenv.2014.05.055, 2015.
Breiman, L.: Random Forests, Mach. Learn., 45, 5–32, 2001.
Breiman, L., Friedman, J. H., Ohlsen, R. A., and Stone C. J.: Classification and Regression Trees, Chapman and Hall/CRC, ISBN 13:978-0412048418, 1984.
Christensen, J. H.: The Danish Eulerian hemispheric model – A three-dimensional air pollution model used for the Arctic, Atmos. Environ., 31, 4169–4191, 1997.
Delle Monache, L. and Stull, R. B.: An ensemble air quality forecast over western Europe during an ozone episode, Atmos. Environ., 37, 3469–3474, 2003.
Delle Monache, L., Nipen, T., Deng, X., Zhou, Y., and Stull, R.: Ozone ensemble forecasts: 2. A Kalman filter predictor bias correction, J. Geophys. Res., 111, D05308, https://doi.org/10.1029/2005JD006311, 2006.
Djalalova, I., Delle Monache, L., and Wilczak, J.: PM2.5 analog forecast and Kalman filter post-processing for the Community Multiscale Air Quality (CMAQ) model, Atmos. Environ., 108, 76–87, 2015.
Freund, Y. and Schapire, R.: Experiments with a new boosting algorithm, Machine Learning, in: Proceedings of the Thirteenth International Conference, Morgan Kauffman, San Francisco, 148–156, ISBN 10:1-55860-419-7, 1996.
Friedman, J., Hastie, T., and Tibshirani, R.: Regularization Paths for Generalized Linear Models via Coordinate Descent, J. Stat. Softw., 33, 1–22, 2010.
Friedman, J. H.: Greedy Function Approximation: a Gradient Boosting Machine, Ann. Stat., 29, 1189–1232, https://doi.org/10.1214/aos/1013203451, 2001.
Grange, S. K., Carslaw, D. C., Lewis, A. C., Boleti, E., and Hueglin, C.: Random forest meteorological normalisation models for Swiss PM10 trend analysis, Atmos. Chem. Phys., 18, 6223–6239, https://doi.org/10.5194/acp-18-6223-2018, 2018.
Greenwell, B., Boehmke, B., Cunningham, J., and GBM Developers: Generalized Boosted Regression Models, r package version 2.1.5, http://CRAN.R-project.org/package=gbm (last access: 13 April 2023), 2019.
Guth, J., Josse, B., Marécal, V., Joly, M., and Hamer, P.: First implementation of secondary inorganic aerosols in the MOCAGE version R2.15.0 chemistry transport model, Geosci. Model Dev., 9, 137–160, https://doi.org/10.5194/gmd-9-137-2016, 2016.
Hass, H., Jakobs, H. J., and Memmesheimer, M.: Analysis of a regional model (EURAD) near surface gas concentration predictions using observations from networks, Meteorol. Atmos. Phys., 57, 173–200, https://doi.org/10.1007/BF01044160, 1995.
Hoerl, A. and Kennard, R.: Ridge Regression: Biased Estimation for Nonorthogonal Problems, Technometrics, 12, 55–67, https://doi.org/10.1080/00401706.1970.10488634, 1970.
Honoré, C., Rouïl, L., Vautard, R., Beeckmann, M., Bessagnet, B., Dufour, A., Elichegaray, C., Flaud, J.-M., Malherbe, L., Meleux, F., Menut, L., Martin, D., Peuch, A., Peuch, V.-H., and Poisson, N.: Predictability of European air quality: Assessment of 3 years of operational forecasts and analyses by the PREV'AIR system, J. Geophys. Res., 113, D04301, https://doi.org/10.1029/2007JD008761, 2008.
Kaminski, J. W., Neary, L., Struzewska, J., McConnell, J. C., Lupu, A., Jarosz, J., Toyota, K., Gong, S. L., Côté, J., Liu, X., Chance, K., and Richter, A.: GEM-AQ, an on-line global multiscale chemical weather modelling system: model description and evaluation of gas phase chemistry processes, Atmos. Chem. Phys., 8, 3255–3281, https://doi.org/10.5194/acp-8-3255-2008, 2008.
Kang, D., Mathur, R., Rao, S. T., and Yu, S.: Bias adjustment techniques for improving ozone air quality forecasts, J. Geophys. Res., 113, D23308, https://doi.org/10.1029/2008JD010151, 2008.
Kuhn, M.: Building predictive models in R using the caret package, J. Stat. Softw., 28, 1–26, https://doi.org/10.18637/jss.v028.i05, 2008.
Liaw, A. and Wiener, M.: Classification and Regression by random forest, R News, 2, 18–22, 2002.
Mailler, S., Menut, L., Khvorostyanov, D., Valari, M., Couvidat, F., Siour, G., Turquety, S., Briant, R., Tuccella, P., Bessagnet, B., Colette, A., Létinois, L., Markakis, K., and Meleux, F.: CHIMERE-2017: from urban to hemispheric chemistry-transport modeling, Geosci. Model Dev., 10, 2397–2423, https://doi.org/10.5194/gmd-10-2397-2017, 2017.
Marécal, V., Peuch, V.-H., Andersson, C., Andersson, S., Arteta, J., Beekmann, M., Benedictow, A., Bergström, R., Bessagnet, B., Cansado, A., Chéroux, F., Colette, A., Coman, A., Curier, R. L., Denier van der Gon, H. A. C., Drouin, A., Elbern, H., Emili, E., Engelen, R. J., Eskes, H. J., Foret, G., Friese, E., Gauss, M., Giannaros, C., Guth, J., Joly, M., Jaumouillé, E., Josse, B., Kadygrov, N., Kaiser, J. W., Krajsek, K., Kuenen, J., Kumar, U., Liora, N., Lopez, E., Malherbe, L., Martinez, I., Melas, D., Meleux, F., Menut, L., Moinat, P., Morales, T., Parmentier, J., Piacentini, A., Plu, M., Poupkou, A., Queguiner, S., Robertson, L., Rouïl, L., Schaap, M., Segers, A., Sofiev, M., Tarasson, L., Thomas, M., Timmermans, R., Valdebenito, Á., van Velthoven, P., van Versendaal, R., Vira, J., and Ung, A.: A regional air quality forecasting system over Europe: the MACC-II daily ensemble production, Geosci. Model Dev., 8, 2777–2813, https://doi.org/10.5194/gmd-8-2777-2015, 2015.
Mircea, M., Ciancarella, L., Briganti, G., Calori, G., Cappelletti, A., Cionni, I., Costa, M., Cremona, G., D'Isidoro, M., Finardi, S., Pace, G., Piersanti, A., Righini, G., Silibello, C., Vitali, L. and Zanini, G.: Assessment of the AMS-MINNI system capabilities to simulate air quality over Italy for the calendar year 2005, Atmos. Environ., 84, 178–188, 2014.
Petetin, H., Bowdalo, D., Soret, A., Guevara, M., Jorba, O., Serradell, K., and Pérez García-Pando, C.: Meteorology-normalized impact of the COVID-19 lockdown upon NO2 pollution in Spain, Atmos. Chem. Phys., 20, 11119–11141, https://doi.org/10.5194/acp-20-11119-2020, 2020.
Petetin, H., Bowdalo, D., Bretonnière, P.-A., Guevara, M., Jorba, O., Mateu Armengol, J., Samso Cabre, M., Serradell, K., Soret, A., and Pérez Garcia-Pando, C.: Model output statistics (MOS) applied to Copernicus Atmospheric Monitoring Service (CAMS) O3 forecasts: trade-offs between continuous and categorical skill scores, Atmos. Chem. Phys., 22, 11603–11630, https://doi.org/10.5194/acp-22-11603-2022, 2022.
Robertson, L., Langner, J., and Engardt, M.: An Eulerian limited-area atmospheric transport model, J. Appl. Meteorol. Clim., 38, 190–210, 1999.
Rouïl, L., Honoré, C., Vautard, R., Beeckmann, M., Bessagnet, B., Malherbe, L., Meleux, F., Dufour, A., Elichegaray, C., Flaud, J.-M., Menut, L., Martin, D., Peuch, A., Peuch, V.-H., and Poisson, N.: PREV'AIR: An operational forecasting and mapping system for air quality in Europe, B. Am. Meteorol. Soc., 90, 73–84, https://doi.org/10.1175/2008BAMS2390.1, 2009.
Schaap, M., Manders, A. M. M., Hendriks, E. C. J., Cnossen, J. M., Segers, A. J. S., Denier van der Gon, H., Jozwicka, M., Sauter, F. J., Velders, G. J. M., Matthijsen, J., and Builtjes, P. J. H.: Regional Modelling of Particulate Matter for the Netherlands Netherlands Research Program on Particulate Matter, Report 500099008, PBL Netherlands Environmental Assesment Agency, ISSN 1875-2314, 2009.
Simpson, D., Benedictow, A., Berge, H., Bergström, R., Emberson, L. D., Fagerli, H., Flechard, C. R., Hayman, G. D., Gauss, M., Jonson, J. E., Jenkin, M. E., Nyíri, A., Richter, C., Semeena, V. S., Tsyro, S., Tuovinen, J.-P., Valdebenito, Á., and Wind, P.: The EMEP MSC-W chemical transport model – technical description, Atmos. Chem. Phys., 12, 7825–7865, https://doi.org/10.5194/acp-12-7825-2012, 2012.
Sofiev, M., Vira, J., Kouznetsov, R., Prank, M., Soares, J., and Genikhovich, E.: Construction of the SILAM Eulerian atmospheric dispersion model based on the advection algorithm of Michael Galperin, Geosci. Model Dev., 8, 3497–3522, https://doi.org/10.5194/gmd-8-3497-2015, 2015.
Tibshirani, R.: Regression shrinkage and selection via the lasso, J. Roy. Stat. Soc. B Met., 58, 267–288, 1996.
Wilczak, J., McKeen, S., Djalalova, I., Grell, G., Peckham, S., Gong, W., Bouchet, V., Moffet, R., McHenry, J., McQueen, J., Lee, P., Tang, Y., and Carmichael, G. R.: Bias-corrected ensemble and probabilistic forecasts of surface ozone over eastern North America during the summer of 2004, J. Geophys. Res.-Atmos., 111, D23S28, https://doi.org/10.1029/2006jd007598, 2006.
Zhang, Y., Bocquet, M., Mallet, V., Seigneur, C., and Baklanov, A.: Real-time air quality forecasting, Part I: History, techniques, and current status, Atmos. Environ., 60, 632–655, 2012.
Short summary
Post-processing methods based on machine learning algorithms were applied to refine the forecasts of four key pollutants at monitoring sites across Europe. Performances show significant improvements compared to those of the deterministic model raw outputs. Taking advantage of the large modelling domain extension, an innovative
globalapproach is proposed to drastically reduce the period necessary to train the models and thus facilitate the implementation in an operational context.
Post-processing methods based on machine learning algorithms were applied to refine the...
Altmetrics
Final-revised paper
Preprint