Neural network-based estimates of North Atlantic surface pCO2 from satellite data: A methodological study.

Friedrich, Tobias and Oschlies, Andreas (2009) Neural network-based estimates of North Atlantic surface pCO2 from satellite data: A methodological study. Open Access Journal of Geophysical Research: Oceans, 114 . C03020. DOI 10.1029/2007JC004646.

2007JC004646.pdf - Published Version

Download (35Mb)

Supplementary data:


A new method is proposed to estimate ocean surface pCO2 from remotely sensed surface temperature and chlorophyll data. The method is applied to synthetic observations provided by an eddy-resolving biogeochemical model of the North Atlantic. The same model also provides a perfectly known simulated pCO2 “ground truth” used to quantitatively assess the success of the estimation method. Model output is first sampled according to realistic voluntary observing ship (VOS) and satellite coverage. The model-generated VOS “observations” are then used to train a self-organizing neural network that is subsequently applied to model-generated “satellite data” of surface temperature and surface chlorophyll in order to derive basin-wide monthly maps of surface pCO2. The accuracy of the estimated pCO2 maps is analyzed with respect to the “true” surface pCO2 fields simulated by the biogeochemical circulation model. We also investigate the accuracy of the estimated pCO2 maps as a function of VOS line coverage, remote sensing errors, and the interpolation of missing remote sensing data due to cloud cover and low solar irradiation in winter. For a simulated “sampling” corresponding to VOS lines and patterns of optical satellite coverage of the year 2005, the neural net can successfully reproduce pCO2 from model-generated “remote sensing data” of SST and Chl. Basin-wide RMS errors amount to 19.0 μatm for a hypothetical perfect interpolation scheme for remote sensing data gaps and 21.1 μatm when climatological surface temperature and chlorophyll values are used to fill in areas lacking optical satellite coverage.

Document Type: Article
Keywords: Geodesy; pCO2; remote sensing; neural networks
Research affiliation: OceanRep > GEOMAR > FB2 Marine Biogeochemistry > FB2-BM Biogeochemical Modeling
OceanRep > The Future Ocean - Cluster of Excellence
Refereed: Yes
Open Access Journal?: No
DOI etc.: 10.1029/2007JC004646
ISSN: 2169-9275
Projects: Future Ocean, CARBOOCEAN
Date Deposited: 27 Mar 2009 14:33
Last Modified: 25 Apr 2018 08:04

Actions (login required)

View Item View Item

Document Downloads

More statistics for this item...