Volume 14, issue 23 | Copyright
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

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 discussion
Status: closed
Status: closed
AC: Author comment | RC: Referee comment | SC: Short comment | EC: Editor comment
Printer-friendly Version - Printer-friendly version Supplement - 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
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...
Citation
Share