Journal cover Journal topic
Biogeosciences An interactive open-access journal of the European Geosciences Union
Biogeosciences, 14, 5551-5569, 2017
https://doi.org/10.5194/bg-14-5551-2017
© Author(s) 2017. This work is distributed under
the Creative Commons Attribution 3.0 License.
Research article
08 Dec 2017
Empirical methods for the estimation of Southern Ocean CO2: support vector and random forest regression
Luke Gregor et al.
Download
Interactive discussionStatus: closed
AC: Author comment | RC: Referee comment | SC: Short comment | EC: Editor comment
Printer-friendly Version - Printer-friendly version      Supplement - Supplement
 
RC1: 'Review of Gregor et al: Empirical methods for the estimation of Southern Ocean CO2: Support Vector and Random Forest Regression', Anonymous Referee #1, 18 Jun 2017 Printer-friendly Version Supplement 
 
RC2: 'Important and novel contribution, but requires a more thorough analysis and discussion', Nicolas GRUBER, 29 Jul 2017 Printer-friendly Version 
 
AC1: 'Corrections to manuscript', Luke Gregor, 13 Sep 2017 Printer-friendly Version Supplement 
Peer review completion
AR: Author's response | RR: Referee report | ED: Editor decision
ED: Reconsider after major revisions (01 Oct 2017) by Laurent Bopp  
AR by Anna Wenzel on behalf of the Authors (06 Oct 2017)  Author's response
ED: Referee Nomination & Report Request started (20 Oct 2017) by Laurent Bopp
RR by Anonymous Referee #1 (24 Oct 2017)  
ED: Publish subject to technical corrections (05 Nov 2017) by Laurent Bopp  
AR by Luke Gregor on behalf of the Authors (06 Nov 2017)  Author's response  Manuscript
CC BY 4.0
Publications Copernicus
Download
Short summary
We use machine learning to extrapolate ship measurements of CO2 using satellite data. We present two ML methods new to this field. These methods perform well in the context of previous work and reproduce the decadal trends of previous estimates. To test the methods, we simulate the exact observed setup in biogeochemical ocean model output. We show that the new methods perform well in synthetic data. Lastly, we show that there is only a weak bias due to undersampling in the SOCAT v3 dataset.
We use machine learning to extrapolate ship measurements of CO2 using satellite data. We present...
Share