Preprints
https://doi.org/10.5194/gmd-2023-142
https://doi.org/10.5194/gmd-2023-142
Submitted as: model description paper
 | 
26 Jul 2023
Submitted as: model description paper |  | 26 Jul 2023
Status: this preprint is currently under review for the journal GMD.

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

Abstract. The quantification of emissions of greenhouse gases and air pollutants through the inversion of plumes in satellite images remains a complex problem that current methods can only assess with significant uncertainties. The anticipated launch of the CO2M satellite constellation in 2026 is expected to provide high-resolution images of CO2 column-averaged mole fractions (XCO2), opening up new possibilities. However, the inversion of future CO2 plumes from CO2M will encounter various obstacles. A challenge is the CO2 plume low signal-to-noise ratio, due to the variability of the background and instrumental errors in satellite measurements. Moreover, uncertainties in the transport and dispersion processes further complicate the inversion task.

To address these challenges, deep learning techniques, such as neural networks, offer promising solutions for retrieving emissions from plumes in XCO2 images. Deep learning models can be trained to identify emissions from plume dynamics simulated using a transport model. It then becomes possible to extract relevant information from new plumes and predict their emissions.

In this paper, we employ convolutional neural networks (CNN) to estimate the emission fluxes from a plume in a pseudo XCO2 image. Our dataset used to train and test such methods includes pseudo images based on simulations of hourly XCO2, NO2 and wind fields near various power plants in Eastern Germany, tracing plumes from anthropogenic and biogenic sources. CNN models are trained to predict emissions from three power plants that exhibit diverse characteristics. The power plants used to assess the deep learning model's performance are not used to train the model. We find that the CNN model outperforms state of the art plume inversion approaches, achieving highly accurate results with an absolute error about half of that of the cross-sectional flux method. Furthermore, we show that our estimations are only slightly affected by the absence of NO2 fields or a detection mechanism as additional information. Finally, interpretability techniques applied to our models confirm that the CNN automatically learns to identify the XCO2 plume and to assess emissions from the plume concentrations. These promising results suggest a high potential of CNNs in estimating local CO2 emissions from satellite images.

Joffrey Dumont Le Brazidec et al.

Status: final response (author comments only)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'A useful exploratory paper that would benefit from more caveats', Evan D. Sherwin, 23 Aug 2023
  • RC2: 'Comment on gmd-2023-142', Anonymous Referee #2, 26 Aug 2023

Joffrey Dumont Le Brazidec et al.

Joffrey Dumont Le Brazidec et al.

Viewed

Total article views: 375 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
248 115 12 375 6 5
  • HTML: 248
  • PDF: 115
  • XML: 12
  • Total: 375
  • BibTeX: 6
  • EndNote: 5
Views and downloads (calculated since 26 Jul 2023)
Cumulative views and downloads (calculated since 26 Jul 2023)

Viewed (geographical distribution)

Total article views: 364 (including HTML, PDF, and XML) Thereof 364 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 03 Oct 2023
Download
Short summary
Our research presents an innovative approach to estimate 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.