Articles | Volume 21, issue 8
https://doi.org/10.5194/bg-21-2159-2024
https://doi.org/10.5194/bg-21-2159-2024
Research article
 | 
30 Apr 2024
Research article |  | 30 Apr 2024

Assessing improvements in global ocean pCO2 machine learning reconstructions with Southern Ocean autonomous sampling

Thea H. Heimdal, Galen A. McKinley, Adrienne J. Sutton, Amanda R. Fay, and Lucas Gloege

Data sets

SOCAT+USV sampling masks for ML reconstruction of surface ocean pCO2 using the Large Ensemble Testbed Thea H. Heimdal et al. https://doi.org/10.5281/zenodo.10811018

Large ensemble pCO2 testbed. figshare. Collection Lucas Gloege https://doi.org/10.6084/m9.figshare.c.4568555.v2

Model code and software

Code for ML reconstruction of surface ocean pCO2 using the Large Ensemble Testbed (v1.0) Thea H. Heimdal et al. https://doi.org/10.5281/zenodo.10966977

Download
Short summary
Measurements of ocean carbon are limited in time and space. Machine learning algorithms are therefore used to reconstruct ocean carbon where observations do not exist. Improving these reconstructions is important in order to accurately estimate how much carbon the ocean absorbs from the atmosphere. In this study, we find that a small addition of observations from the Southern Ocean, obtained by autonomous sampling platforms, could significantly improve the reconstructions. 
Altmetrics
Final-revised paper
Preprint