Journal cover Journal topic
Atmospheric Measurement Techniques An interactive open-access journal of the European Geosciences Union
Journal topic

Journal metrics

Journal metrics

  • IF value: 3.668 IF 3.668
  • IF 5-year value: 3.707 IF 5-year
  • CiteScore value: 6.3 CiteScore
  • SNIP value: 1.383 SNIP 1.383
  • IPP value: 3.75 IPP 3.75
  • SJR value: 1.525 SJR 1.525
  • Scimago H <br class='hide-on-tablet hide-on-mobile'>index value: 77 Scimago H
    index 77
  • h5-index value: 49 h5-index 49
© Author(s) 2020. This work is distributed under
the Creative Commons Attribution 4.0 License.
© Author(s) 2020. This work is distributed under
the Creative Commons Attribution 4.0 License.

Submitted as: research article 02 Jun 2020

Submitted as: research article | 02 Jun 2020

Review status
This preprint is currently under review for the journal AMT.

XCO2 estimates from the OCO-2 measurements using a neural network approach

Leslie David, Francois-Marie Bréon, and Frédéric Chevallier Leslie David et al.
  • Laboratoire des Sciences du Climat et de l’Environnement/IPSL, CEA-CNRS-UVSQ, Université Paris-Saclay, 91198 Gif-sur-Yvette, France

Abstract. The OCO-2 instrument measures high-resolution spectra of the sun radiance reflected at the Earth surface or scattered in the atmosphere. These spectra are used to estimate the column integrated CO2 dry air mole fraction (XCO2) and the surface pressure. The official retrieval algorithm (NASA’s Atmospheric CO2 Observations from Space retrievals – ACOS) uses a full physics algorithm and has been extensively evaluated. Here we propose an alternative approach based on an artificial neural network (NN) technique. For the training and evaluation, we use as a reference estimate the surface pressures from a numerical weather model and the XCO2 derived from an atmospheric transport simulation constrained by surface air-sample measurements of CO2. The NN is trained here using real measurements acquired in nadir mode on cloud-free scenes during even months and is then evaluated against similar observations of odd months. The evaluation indicates that the NN retrieves the surface pressure with a root-mean-square error better than 3 hPa and XCO2 with a precision of 0.7 ppm. The statistics indicate that the NN, that has been trained with a representative set of data, allows excellent accuracy, slightly better than that of the full physics algorithm. An evaluation against reference sunphotometer XCO2 retrievals indicates similar accuracy for the NN and ACOS estimates, with a skill that varies among the various stations. The NN-model differences show spatio-temporal structures that indicate a potential for improving our knowledge of CO2 fluxes. We finally discuss the pros and cons of using this NN approach for the processing of OCO-2 data.

Leslie David et al.

Interactive discussion

Status: open (until 28 Jul 2020)
Status: open (until 28 Jul 2020)
AC: Author comment | RC: Referee comment | SC: Short comment | EC: Editor comment
[Subscribe to comment alert] Printer-friendly Version - Printer-friendly version Supplement - Supplement

Leslie David et al.

Leslie David et al.


Total article views: 208 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
135 69 4 208 0 3
  • HTML: 135
  • PDF: 69
  • XML: 4
  • Total: 208
  • BibTeX: 0
  • EndNote: 3
Views and downloads (calculated since 02 Jun 2020)
Cumulative views and downloads (calculated since 02 Jun 2020)

Viewed (geographical distribution)

Total article views: 131 (including HTML, PDF, and XML) Thereof 131 with geography defined and 0 with unknown origin.
Country # Views %
  • 1



No saved metrics found.


No discussed metrics found.
Latest update: 10 Jul 2020
Publications Copernicus
Short summary
This paper shows that a Neural Network approach can be used to process spaceborne observations from the OCO-2 satellite and retrieve both the surface pressure and the atmospheric CO2 content. The accuracy evaluation indicates that the retrievals have an accuracy that is at least as good as those of the operational approach that relies on complex algorithms and that is very computer intensive. The approach is therefore a very promising alternative for the processing of CO2-monitoring missions.
This paper shows that a Neural Network approach can be used to process spaceborne observations...