Kang, Y.Y.; Ding, X.R., and Ge, X.P., 2018. Using Geostationary Ocean Color Imager to map the diurnal dynamics of suspended sediment concentration in estuary area. In: Shim, J.-S.; Chun, I., and Lim, H.S. (eds.), Proceedings from the International Coastal Symposium (ICS) 2018 (Busan, Republic of Korea). Journal of Coastal Research, Special Issue No. 85, pp. 101–105. Coconut Creek (Florida), ISSN 0749-0208.
Geostationary ocean color imager (GOCI), the first in-orbit operation of the geostationary satellite ocean color sensor, provides hourly observations of the covered area. Quick atmospheric correction (QUAC) algorithm was used for GOCI data to remove the atmospheric effects and an artificial neural network (ANN) inversion model (multi-layer feed forward neural network) was proposed to derive suspended sediment concentration (SSC) via GOCI in coastal waters of Yongjiang estuary, China. This model has three parts those are the input layer with eight nodes, two hidden layers with seventeen nodes in each layer, and output layer with one node. Compared with in-suit situ measurements taken in the Yongjiang estuary, the inversion model produces a superior performance compared with two other experience models (a linear regression model and an exponent model). Based on these atmospheric correction and ANN model, hourly SSC maps from GOCI data were generated. These maps revealed that SSC of Yongjiang estuary suffers from obvious spatial-temporal variation mainly affected by tide and topography.