Articles | Volume 12, issue 12
Geosci. Model Dev., 12, 5113–5136, 2019
https://doi.org/10.5194/gmd-12-5113-2019
Geosci. Model Dev., 12, 5113–5136, 2019
https://doi.org/10.5194/gmd-12-5113-2019

Development and technical paper 10 Dec 2019

Development and technical paper | 10 Dec 2019

A comparative assessment of the uncertainties of global surface ocean CO2 estimates using a machine-learning ensemble (CSIR-ML6 version 2019a) – have we hit the wall?

Luke Gregor et al.

Data sets

Global surface-ocean partial pressure of carbon dioxide (pCO2) estimates from a machine learning ensemble: CSIR-ML6 v2019a (NCEI Accession 0206205) L. Gregor, A. D. Lebehot, S. Kok, and P. M. Scheel Monteiro https://doi.org/10.25921/z682-mn47

Model code and software

CSIR_ML6-surface_ocean_pCO2 L. Gregor https://doi.org/10.5281/zenodo.3537200

Download
Short summary
The ocean plays a vital role in mitigating climate change by taking up atmospheric carbon dioxide (CO2). Historically sparse ship-based measurements of surface ocean CO2 make direct estimates of CO2 exchange changes unreliable. We introduce a machine-learning ensemble approach to fill these observational gaps. Our method performs incrementally better relative to past methods, leading to our hypothesis that we are perhaps reaching the limitation of machine-learning algorithms' capability.