A scientific paper titled “On the variations of sea surface pCO2 in the northern South China Sea: A remote sensing based neural network approach” has been published in the Journal of Geophysical Research. This paper was jointly composed by Drs. Young-Heon Jo and Xiao-Hai Yan from the University of Delaware (UD), Drs. Minhan Dai, Weidong Zhai and Shaoling Shang from Xiamen University (XMU).
It remains challenging to constrainthe carbon fluxes in the coastal ocean due primarily to the large variability in both time and space. There is a great need of sufficient spatial and temporal pCO2 observations. Remote sensing with applicable algorithms can be a potentially important approach complementary to ship-board observations.Using a neural networking (NN) approach, XMU and UD scientists developed an algorithm primarily based upon sea surface temperature (SST) and chlorophyll (Chl(a)) to estimate the partial pressure of carbon dioxide (pCO(2)) at the sea surface in the northern South China Sea (NSCS). Randomly selected in situ data collected from May 2001, February and July 2004 cruises were used to develop and test the predictive capabilities of the NN based algorithm with four inputs (SST, Chl(a), longitudes and latitudes). The comparison revealed a high correlation coefficient of 0.98 with a root mean square error (RMSE) of 6.9 mu atm. They subsequently applied their NN algorithm to satellite SST and Chl(a) measurements, with associated longitudes and latitudes, to obtain surface water pCO(2). The resulting monthly mean pCO(2) map derived from the satellite measurements agreed reasonably well with the in situ observations. This is the first successful attempt to apply NN to an extremely dynamic coastal ocean for pCO(2) estimation.
Under the framework of the Joint-CRM (Joint Institute for Coastal Research and Management), this paper is the fourth publication worked jointly by UD and XMU scientists.