Benchmarking data-driven inversion methods for the estimation of local CO2 emissions from synthetic satellite images of XCO2 and NO2

Santaren, Diego; Hakkarainen, Janne; Kuhlmann, Gerrit; Koene, Erik; Chevallier, Frédéric; Ialongo, Iolanda; Lindqvist, Hannakaisa; Nurmela, Janne; Tamminen, Johanna; Amorós, Laia; Brunner, Dominik; Broquet, Grégoire

doi:https://doi.org/10.5194/amt-18-211-2025

Articles | Volume 18, issue 1

https://doi.org/10.5194/amt-18-211-2025

© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/amt-18-211-2025

© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 18, issue 1

Research article

|

15 Jan 2025

Research article |

| 15 Jan 2025

Benchmarking data-driven inversion methods for the estimation of local CO₂ emissions from synthetic satellite images of XCO₂ and NO₂

Diego Santaren, Janne Hakkarainen, Gerrit Kuhlmann, Erik Koene, Frédéric Chevallier, Iolanda Ialongo, Hannakaisa Lindqvist, Janne Nurmela, Johanna Tamminen, Laia Amorós, Dominik Brunner, and Grégoire Broquet

Data sets

Synthetic XCO2, CO and NO2 Observations for the CO2M and Sentinel-5 Satellites G. Kuhlmann et al. https://doi.org/10.5281/zenodo.4048227

Short summary

This study evaluates data-driven inversion methods for estimating CO₂emissions from local sources, such as power plants and cities, using meteorological data and XCO₂and NO₂satellite images rather than atmospheric transport modeling. We assess and compare the performance of five different methods using simulations of 1 year of satellite images, taken from the upcoming Copernicus CO₂ Monitoring Mission, covering 15 power plants and the city of Berlin, Germany.