Preprints
https://doi.org/10.5194/essd-2022-71
https://doi.org/10.5194/essd-2022-71
 
11 Mar 2022
11 Mar 2022
Status: this discussion paper is a preprint. It has been under review for the journal Earth System Science Data (ESSD). The manuscript was not accepted for further review after discussion.

A new estimate of oceanic CO2 fluxes by machine learning reveals the impact of CO2 trends in different methods

Jiye Zeng, Tsuneo Matsunaga, and Tomoko Shirai Jiye Zeng et al.
  • National Institute for Environmental Studies, Tsukuba, 305-8506, Japan

Abstract. Global oceans have absorbed a substantial portion of the anthropogenic carbon dioxide (CO2) emitted into the atmosphere. Data-based machine learning (DML) estimates for the oceanic CO2 sink have become an import part of the Global Carbon Budget in recent years. Although DML models are considered objective as they impose very few subjective conditions in optimizing model parameters, they face the challenge of data scarcity problem when applied to mapping ocean CO2 concentrations, from which air-sea CO2 fluxes can be computed. Data scarcity forces DML models to pool multiple years’ data for model training. When the time span extends to a few decades, the result could be largely affected by how ocean CO2 trends are obtained. This study extracted the trends using a new method and reconstructed monthly surface ocean CO2 concentrations and air-sea fluxes in 1980–2020 with a spatial resolution of 1×1 degree. Comparing with six other products, our results show a smaller oceanic sink and the sink in early and late year of the modelled period could be overestimated if ocean CO2 trends were not well processed by models. We estimated that the oceanic sink has increased from 1.79 PgC yr-1 in 1980s to 2.58 PgC yr-1 in 2010s with a mean acceleration of 0.027 PgC yr-2.

Jiye Zeng et al.

Status: closed

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on essd-2022-71', Anonymous Referee #1, 18 Mar 2022
    • AC1: 'Reply on RC1', J. Zeng, 20 Mar 2022
      • RC2: 'Reply on AC1', Anonymous Referee #1, 20 Mar 2022
        • AC2: 'Reply on RC2', J. Zeng, 08 Apr 2022
  • RC3: 'Comment on essd-2022-71', Anonymous Referee #2, 13 Apr 2022
    • AC3: 'Reply on RC3', J. Zeng, 18 Apr 2022
  • RC4: 'Comment on essd-2022-71', Anonymous Referee #3, 28 Apr 2022
    • AC4: 'Reply on RC4', J. Zeng, 02 May 2022

Status: closed

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on essd-2022-71', Anonymous Referee #1, 18 Mar 2022
    • AC1: 'Reply on RC1', J. Zeng, 20 Mar 2022
      • RC2: 'Reply on AC1', Anonymous Referee #1, 20 Mar 2022
        • AC2: 'Reply on RC2', J. Zeng, 08 Apr 2022
  • RC3: 'Comment on essd-2022-71', Anonymous Referee #2, 13 Apr 2022
    • AC3: 'Reply on RC3', J. Zeng, 18 Apr 2022
  • RC4: 'Comment on essd-2022-71', Anonymous Referee #3, 28 Apr 2022
    • AC4: 'Reply on RC4', J. Zeng, 02 May 2022

Jiye Zeng et al.

Data sets

NIES-ML3 ensemble product of surface ocean CO2 concentrations and air-sea CO2 fluxes reconstructed by using three machine learning models with new CO2 trends Jiye Zeng https://db.cger.nies.go.jp/DL/10.17595/20220311.001.html.en

Jiye Zeng et al.

Viewed

Total article views: 742 (including HTML, PDF, and XML)
HTML PDF XML Total Supplement BibTeX EndNote
529 186 27 742 37 8 11
  • HTML: 529
  • PDF: 186
  • XML: 27
  • Total: 742
  • Supplement: 37
  • BibTeX: 8
  • EndNote: 11
Views and downloads (calculated since 11 Mar 2022)
Cumulative views and downloads (calculated since 11 Mar 2022)

Viewed (geographical distribution)

Total article views: 661 (including HTML, PDF, and XML) Thereof 661 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 27 Nov 2022
Download
Short summary
We have extracted the increase rates of ocean CO2 with three types of machine learning models. The results are new and important because scarce data made it difficult to use machine learning models for for ocean CO2 reconstruction and oceanic CO2 sink estimate. One of the approaches is to remove the trend in CO2 data obtained in multiple-years so that the models can learn the non-linear dependence of CO2 on seawater properties better.