Estimating temporal and spatial variation of ocean surface pCO₂ in the North Pacific using a self-organizing map neural network technique

Abstract. This study uses a neural network technique to produce maps of the partial pressure of oceanic carbon dioxide (pCO₂^sea) in the North Pacific on a 0.25° latitude × 0.25° longitude grid from 2002 to 2008. The pCO₂^sea distribution was computed using a self-organizing map (SOM) originally utilized to map the pCO₂^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 pCO₂^sea distribution and biogeochemistry of the basin. The observed pCO₂^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 pCO₂^sea values agreed well with the pCO₂^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 pCO₂^sea estimates could be improved by including SSS as one of the training parameters and by taking into account secular increases of pCO₂^sea that have tracked increases in atmospheric CO₂. Estimated pCO₂^sea values accurately reproduced pCO₂^sea data at several time series locations in the North Pacific. The distributions of pCO₂^sea revealed by 7 yr averaged monthly pCO₂^sea maps were similar to Lamont-Doherty Earth Observatory pCO₂^sea climatology, allowing, however, for a more detailed analysis of biogeochemical conditions. The distributions of pCO₂^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.