skip to main content
Language:
Search Limited to: Search Limited to: Resource type Show Results with: Show Results with: Search type Index

On the potential of a neural-network-based approach for estimating XCO.sub.2 from OCO-2 measurements

Atmospheric measurement techniques, 2022-09, Vol.15 (18), p.5219 [Peer Reviewed Journal]

COPYRIGHT 2022 Copernicus GmbH ;ISSN: 1867-1381 ;EISSN: 1867-8548

Full text available

Citations Cited by
  • Title:
    On the potential of a neural-network-based approach for estimating XCO.sub.2 from OCO-2 measurements
  • Author: Bréon, François-Marie ; David, Leslie ; Chatelanaz, Pierre ; Chevallier, Frédéric
  • Subjects: Analysis ; Methods ; Neural networks ; Physical instruments
  • Is Part Of: Atmospheric measurement techniques, 2022-09, Vol.15 (18), p.5219
  • Description: In David et al. (2021), we introduced a neural network (NN) approach for estimating the column-averaged dry-air mole fraction of CO.sub.2 (XCO.sub.2) and the surface pressure from the reflected solar spectra acquired by the OCO-2 instrument. The results indicated great potential for the technique as the comparison against both model estimates and independent TCCON measurements showed an accuracy and precision similar to or better than that of the operational ACOS (NASA's Atmospheric CO.sub.2 Observations from Space retrievals - ACOS) algorithm. Yet, subsequent analysis showed that the neural network estimate often mimics the training dataset and is unable to retrieve small-scale features such as CO.sub.2 plumes from industrial sites. Importantly, we found that, with the same inputs as those used to estimate XCO.sub.2 and surface pressure, the NN technique is able to estimate latitude and date with unexpected skill, i.e., with an error whose standard deviation is only 7.sup." and 61 d, respectively. The information about the date mainly comes from the weak CO.sub.2 band, which is influenced by the well-mixed and increasing concentrations of CO.sub.2 in the stratosphere. The availability of such information in the measured spectrum may therefore allow the NN to exploit it rather than the direct CO.sub.2 imprint in the spectrum to estimate XCO.sub.2 . Thus, our first version of the NN performed well mostly because the XCO.sub.2 fields used for the training were remarkably accurate, but it did not bring any added value. Further to this analysis, we designed a second version of the NN, excluding the weak CO.sub.2 band from the input. This new version has a different behavior as it does retrieve XCO.sub.2 enhancements downwind of emission hotspots, i.e., a feature that is not in the training dataset. The comparison against the reference Total Carbon Column Observing Network (TCCON) and the surface-air-sample-driven inversion of the Copernicus Atmosphere Monitoring Service (CAMS) remains very good, as in the first version of the NN. In addition, the difference with the CAMS model (also called innovation in a data assimilation context) for NASA Atmospheric CO.sub.2 Observations from Space (ACOS) and the NN estimates is correlated. These results confirm the potential of the NN approach for an operational processing of satellite observations aiming at the monitoring of CO.sub.2 concentrations and fluxes. The true information content of the neural network product remains to be properly evaluated, in particular regarding the respective input of the measured spectrum and the training dataset.
  • Publisher: Copernicus GmbH
  • Language: English
  • Identifier: ISSN: 1867-1381
    EISSN: 1867-8548
  • Source: ProQuest Central
    DOAJ Directory of Open Access Journals
Back to results list
INSPIRE LIBRARY - TON DUC THANG UNIVERSITY (84-028) 37 755 057 Feedback
19 Nguyen Huu Tho St. Dist.7, HCM thuvien@tdtu.edu.vn

Copyright © 2017 INSPIRE LIBRARY - TON DUC THANG UNIVERSITY

Searching Remote Databases, Please Wait