Machine-learning-based correction model improves satellite-based atmospheric aerosol estimates

The method is also well suited for improving the spatial resolution of satellite-based data. More accurate data can be used to estimate air quality even at the street level.

Further information:

Researcher Antti Lipponen, Finnish Meteorological Institute, tel. +358 50 304 6374, antti.lipponen@fmi.fi

Professor Ville Kolehmainen, University of Eastern Finland, tel. +358 40 355 2054, ville.kolehmainen@uef.fi

References:

Taskinen, H., Väisänen, A., Hatakka, L., Virtanen, T. H., Lähivaara, T., Arola, A., Kolehmainen, V., and Lipponen, A.: High-Resolution Post-Process Corrected Satellite AOD, Geophysical Research Letters, 49, e2022GL099733, https://doi.org/10.1029/2022GL099733, 2022.

Lipponen, A., Reinvall, J., Väisänen, A., Taskinen, H., Lähivaara, T., Sogacheva, L., Kolmonen, P., Lehtinen K., Arola, A., and Kolehmainen, V.: Deep-learning-based post-process correction of the aerosol parameters in the high-resolution Sentinel-3 Level-2 Synergy product, Atmospheric Measurement Techniques, 15, 895-914, https://doi.org/10.5194/amt-15-895-2022, 2022.

Lipponen, A., Kolehmainen, V., Kolmonen, P., Kukkurainen, A., Mielonen, T., Sabater, N., Sogacheva, L., Virtanen, T. H., and Arola, A.: Model-enforced post-process correction of satellite aerosol retrievals, Atmospheric Measurement Techniques, 14, 2981-2992, https://doi.org/10.5194/amt-14-2981-2021, 2021.