Articles | Volume 18, issue 20
https://doi.org/10.5194/amt-18-5763-2025
https://doi.org/10.5194/amt-18-5763-2025
Research article
 | 
24 Oct 2025
Research article |  | 24 Oct 2025

Machine learning-based downscaling of aerosol size distributions from a global climate model

Antti Vartiainen, Santtu Mikkonen, Ville Leinonen, Tuukka Petäjä, Alfred Wiedensohler, Thomas Kühn, and Tuuli Miinalainen

Related authors

A process-evaluation of the impact of precipitation on aerosol particle number size distributions in three Earth System Models
Sara M. Blichner, Theodore Khadir, Sini Talvinen, Paulo Artaxo, Liine Heikkinen, Harri Kokkola, Radovan Krejci, Muhammed Irfan, Twan van Noije, Tuukka Petäjä, Christopher Pöhlker, Øyvind Seland, Carl Svenhag, Antti Vartiainen, and Ilona Riipinen
EGUsphere, https://doi.org/10.5194/egusphere-2025-2559,https://doi.org/10.5194/egusphere-2025-2559, 2025
Short summary

Cited articles

Aas, K., Jullum, M., and Løland, A.: Explaining individual predictions when features are dependent: More accurate approximations to Shapley values, Artificial Intelligence, 298, 103502, https://doi.org/10.1016/j.artint.2021.103502, 2021. a
Akiba, T., Sano, S., Yanase, T., Ohta, T., and Koyama, M.: Optuna: A Next-Generation Hyperparameter Optimization Framework, in: The 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2623–2631, https://doi.org/10.1145/3292500.3330701, 2019. a
Alpaydin, E.: Introduction to Machine Learning, MIT Press, Cambridge, MA, 3rd edn., ISBN 978-0-262-02818-9, 2014. a, b, c
Amini, H., Bergmann, M. L., Taghavi Shahri, S. M., Tayebi, S., Cole-Hunter, T., Kerckhoffs, J., Khan, J., Meliefste, K., Lim, Y.-H., Mortensen, L. H., Hertel, O., Reeh, R., Gaarde Nielsen, C., Loft, S., Vermeulen, R., Andersen, Z. J., and Schwartz, J.: Harnessing AI to unmask Copenhagen's invisible air pollutants: A study on three ultrafine particle metrics, Environmental Pollution, 346, 123664, https://doi.org/10.1016/j.envpol.2024.123664, 2024. a
Bai, L., Chen, H., Hatzopoulou, M., Jerrett, M., Kwong, J., Burnett, R., Donkelaar, A., Copes, R., Martin, R., Van Ryswyk, K., Lu, H., Kopp, A., and Weichenthal, S.: Exposure to Ambient Ultrafine Particles and Nitrogen Dioxide and Incident Hypertension and Diabetes, Epidemiology, 29, 1, https://doi.org/10.1097/EDE.0000000000000798, 2018. a
Download
Short summary
Global climate models, commonly used for climate predictions, struggle at capturing local-scale variations in air quality. We have used measurements of ultrafine particles (UFPs), a less understood air pollutant with potentially significant health implications, for training machine learning models that can substantially reduce the inaccuracy in UFP concentrations predicted by a climate model. This approach could aid epidemiological studies of ultrafine particles by extending exposure records.
Share