Geoscientific Model Development
Geoscientific Model Development
GMD
Articles | Volume 17, issue 5
Articles | Volume 17, issue 5
https://doi.org/10.5194/gmd-17-1995-2024
© Author(s) 2024. This work is distributed under
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/gmd-17-1995-2024
© Author(s) 2024. This work is distributed under
the Creative Commons Attribution 4.0 License.
Articles | Volume 17, issue 5
Model description paper
 | 
05 Mar 2024
Model description paper |  | 05 Mar 2024

Deep learning applied to CO2 power plant emissions quantification using simulated satellite images

Joffrey Dumont Le Brazidec, Pierre Vanderbecken, Alban Farchi, Grégoire Broquet, Gerrit Kuhlmann, and Marc Bocquet

Supplement

https://doi.org/10.5194/gmd-17-1995-2024-supplement

Data sets

co2-images-inv-pp: dataset Joffrey Dumont Le Brazidec https://doi.org/10.5281/zenodo.8096616

co2-images-inv-pp: inversion models weights (convolutional neural networks) Joffrey Dumont Le Brazidec et al. https://doi.org/10.5281/zenodo.8095487

Synthetic XCO2, CO and NO2 observations for the CO2M and Sentinel-5 satellites G. Kuhlmann et al. https://doi.org/10.5281/zenodo.4048228

Model code and software

cerea-daml/co2-images-inv-dl: Clean release: "Deep learning applied to CO2 power plant emissions quantification using simulated satellite images" Joffrey Dumont Le Brazidec et al. https://doi.org/10.5281/zenodo.10100338

Download
Short summary
Our research presents an innovative approach to estimating power plant CO2 emissions from satellite images of the corresponding plumes such as those from the forthcoming CO2M satellite constellation. The exploitation of these images is challenging due to noise and meteorological uncertainties. To overcome these obstacles, we use a deep learning neural network trained on simulated CO2 images. Our method outperforms alternatives, providing a positive perspective for the analysis of CO2M images.
Read more