Estimating temporal and spatial variation of ocean surface p CO 2 in the North Pacific using a self-organizing map neural network technique
This study uses a neural network technique to produce maps of the partial pressure of oceanic carbon dioxide ( p CO 2 sea ) in the North Pacific on a 0.25° latitude × 0.25° longitude grid from 2002 to 2008. The p CO 2 sea distribution was computed using a self-organizing map (SOM) originally utilize...
Published in: | Biogeosciences |
---|---|
Main Authors: | , , , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Copernicus Publications
2013
|
Subjects: | |
Online Access: | https://doi.org/10.5194/bg-10-6093-2013 https://doaj.org/article/2b155ec3ebdd4627b76fc61275a3b46b |
Summary: | This study uses a neural network technique to produce maps of the partial pressure of oceanic carbon dioxide ( p CO 2 sea ) in the North Pacific on a 0.25° latitude × 0.25° longitude grid from 2002 to 2008. The p CO 2 sea distribution was computed using a self-organizing map (SOM) originally utilized to map the p CO 2 sea in the North Atlantic. Four proxy parameters – sea surface temperature (SST), mixed layer depth, chlorophyll a concentration, and sea surface salinity (SSS) – are used during the training phase to enable the network to resolve the nonlinear relationships between the p CO 2 sea distribution and biogeochemistry of the basin. The observed p CO 2 sea data were obtained from an extensive dataset generated by the volunteer observation ship program operated by the National Institute for Environmental Studies (NIES). The reconstructed p CO 2 sea values agreed well with the p CO 2 sea measurements, with the root-mean-square error ranging from 17.6 μatm (for the NIES dataset used in the SOM) to 20.2 μatm (for independent dataset). We confirmed that the p CO 2 sea estimates could be improved by including SSS as one of the training parameters and by taking into account secular increases of p CO 2 sea that have tracked increases in atmospheric CO 2 . Estimated p CO 2 sea values accurately reproduced p CO 2 sea data at several time series locations in the North Pacific. The distributions of p CO 2 sea revealed by 7 yr averaged monthly p CO 2 sea maps were similar to Lamont-Doherty Earth Observatory p CO 2 sea climatology, allowing, however, for a more detailed analysis of biogeochemical conditions. The distributions of p CO 2 sea anomalies over the North Pacific during the winter clearly showed regional contrasts between El Niño and La Niña years related to changes of SST and vertical mixing. |
---|