Viability and implicactions of Artificial Intelligence for air quality estimation in Spain
DOI:
https://doi.org/10.59192/mapping.492Keywords:
Artificial intelligence, NO2, TROPOMI, machine learning, air qualityAbstract
This study examines the potential of artificial intelligence (AI) to enhance air-quality estimation in Spain, focusing on nitrogen dioxide (NO2), a pollutant closely linked to urban mobility and adverse health impacts. The research is conducted in the Community of Madrid, which hosts the country’s most comprehensive air-quality monitoring network and provides an ideal setting to assess machine-learning-based modeling. TROPOMI (Sentinel-5P) satellite observations are combined with meteorological variables derived from surface stations and ERA5-Land reanalysis. Several spatial configurations and two model families are evaluated: tree-based algorithms (Random Forest and XGBoost) and artificial neural networks. The best performance is achieved by neural networks trained on environmentally coherent spatial clusters, yielding accuracy metrics that surpass most previous studies and demonstrating AI’s ability to capture the complex spatiotemporal behavior of NO₂, even in heterogeneous environments. Results show that, when supported by a rigorous methodological design, AI can effectively complement traditional monitoring networks, provide reliable estimates in areas with limited infrastructure, and support new regulatory requirements aimed at reducing pollutant exposure. The study highlights AI as a strategic tool for improving air-quality assessment in Spain and for facilitating the transition toward more flexible, scalable, and data-integrated monitoring systems.
Downloads
References
Balamurugan, V., Chen, J., Wenzel, A., Keutsch, F.N., 2023. Spatiotemporal modeling of air pollutant concentrations in Germany using machine learning. Atmos. Chem. Phys 23, 10267–10285. https://doi.org/10.5194/acp-23-10267-2023
Breiman, L., 2001. Random forests. Mach. Learn. 45, 5–32. https://doi.org/10.1023/A:1010933404324/METRICS
Cao, E.L., 2023. National ground-level NO2 predictions via satellite imagery driven convolutional neural networks. Front. Environ. Sci. 11, 1285471. https://doi.org/10.3389/FENVS.2023.1285471/BIBTEX
Cedeno Jimenez, J.R., Pugliese Viloria, A. de J., Brovelli, M.A., 2023. Estimating Daily NO2 Ground Level Concentrations Using Sentinel-5P and Ground Sensor Meteorological Measurements. ISPRS Int. J. Geo-Information 12, 107. https://doi.org/10.3390/ijgi12030107
Chan, K.L., Khorsandi, E., Liu, S., Baier, F., Valks, P., 2021. Estimation of Surface NO2 Concentrations over Germany from TROPOMI Satellite Observations Using a Machine Learning Method. Remote Sens. 2021, Vol. 13, Page 969 13, 969. https://doi.org/10.3390/RS13050969
Chen, T., Guestrin, C., 2016. XGBoost: A scalable tree boosting system. Proc. ACM SIGKDD Int. Conf. Knowl. Discov. Data Min. 13-17-August-2016, 785–794. https://doi.org/10.1145/2939672.2939785;CSUBTYPE:STRING:CONFERENCE
City of Madrid, 2025a. Hourly air quality data since 2001 [WWW Document]. URL https://datos.madrid.es/portal/site/egob/menuitem.c05c1f754a33a9fbe4b2e4b284f1a5a0/?vgnextoid=f3c0f7d512273410VgnVCM2000000c205a0aRCRD&vgnextchannel=374512b9ace9f310VgnVCM100000171f5a0aRCRD&vgnextfmt=default (accessed 11.20.25).
City of Madrid, 2025b. Hourly meteorological data since 2019 [WWW Document]. URL https://datos.madrid.es/sites/v/index.jsp?vgnextoid=fa8357cec5efa610VgnVCM1000001d4a900aRCRD&vgnextchannel=374512b9ace9f310VgnVCM100000171f5a0aRCRD (accessed 11.20.25).
Community of Madrid, 2025a. Hourly air quality data since 2005 [WWW Document]. URL https://datos.comunidad.madrid/dataset/calidad_aire_datos_historico (accessed 11.20.25).
Community of Madrid, 2025b. Hourly meteorological data since 2020 [WWW Document]. URL https://datos.comunidad.madrid/catalogos/#/dataset/calidad_aire_datos_meteo_historico/?view=info (accessed 11.20.25).
Das, B.P., Pathan, M.S., Lee, Y.H., Dev, S., 2021. Estimating Ground-level Nitrogen Dioxide Concentration from Satellite Data. Prog. Electromagn. Res. Symp. 2021-November, 1176–1182. https://doi.org/10.1109/PIERS53385.2021.9694752
Earth Engine Data Catalog, 2024. Sentinel-5P OFFL NO2: Offline Nitrogen Dioxide [WWW Document]. URL https://developers.google.com/earth-engine/datasets/catalog/COPERNICUS_S5P_OFFL_L3_NO2#description (accessed 4.17.23).
Friedman, J.H., 2001. Greedy function approximation: A gradient boosting machine. https://doi.org/10.1214/aos/1013203451 29, 1189–1232. https://doi.org/10.1214/AOS/1013203451
Khomenko, S., Cirach, M., Pereira-Barboza, E., Mueller, N., Barrera-Gómez, J., Rojas-Rueda, D., de Hoogh, K., Hoek, G., Nieuwenhuijsen, M., 2021. Premature mortality due to air pollution in European cities: a health impact assessment. Lancet Planet. Heal. 5, e121–e134. https://doi.org/10.1016/S2542-5196(20)30272-2
Morillas, C., Álvarez, S., Pires, J.C.M., García, A.J., Martínez, S., 2025. Linking Satellite and Ground Observations of NO2 in Spanish Cities: Influence of Meteorology and O3. Nitrogen (Switzerland) 6, 32. https://doi.org/10.3390/NITROGEN6020032/S1
Morillas, C., Alvarez, S., Serio, C., Masiello, G., Martinez, S., 2024. TROPOMI NO2 Sentinel-5P data in the Community of Madrid: A detailed consistency analysis with in situ surface observations. Remote Sens. Appl. Soc. Environ. 33, 101083. https://doi.org/10.1016/J.RSASE.2023.101083
Muñoz Sabater, J., 2019. ERA5-Land hourly data from 1950 to present. https://doi.org/10.24381/cds.e2161bac
Van Geffen, J.H.G.M., Eskes, H.J., Boersma, K.F., Maasakkers, J.D., Veefkind, J.P., 2019. TROPOMI ATBD of the total and tropospheric NO2 data products.
Veefkind, J.P., Aben, I., McMullan, K., Förster, H., de Vries, J., Otter, G., Claas, J., Eskes, H.J., de Haan, J.F., Kleipool, Q., van Weele, M., Hasekamp, O., Hoogeveen, R., Landgraf, J., Snel, R., Tol, P., Ingmann, P., Voors, R., Kruizinga, B., Vink, R., Visser, H., Levelt, P.F., 2012. TROPOMI on the ESA Sentinel-5 Precursor: A GMES mission for global observations of the atmospheric composition for climate, air quality and ozone layer applications. Remote Sens. Environ. 120, 70–83. https://doi.org/10.1016/J.RSE.2011.09.027
World Health Organization (WHO), 2021. WHO global air quality guidelines, Particulate matter (PM2.5 and PM10), ozone, nitrogen dioxide, sulfur dioxide and carbon monoxide.
Xing, J., Baek, B.H., Li, S., Wang, C.T., Song, G., Ma, S., Zheng, S., Liu, C., Tong, D., Woo, J.H., Liu, T.Y., Fu, J.S., 2024. A Physically Constrained Deep-Learning Fusion Method for Estimating Surface NO2 Concentration from Satellite and Ground Monitors. Environ. Sci. Technol. 58, 21218–21228. https://doi.org/10.1021/ACS.EST.4C07341
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Revista MAPPING
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
