The U.S. Geological Survey (USGS) participated in comparing artificial neu
ral networks (ANN's) to deterministic models of transport and water quality phenomena of an estuary in Charleston,
SC. The models were developed from real-time data from a gauging network operated by the USGS. The results favore
d the ANN's accuracy and reduced development time. They could spatially interpolate between gauging stations to pr
edict the location of the freshwater/saltwater interface, called the "salt front." The salt front location depends
on the interaction of freshwater flowing downstream from a hydroelectric dam and tidal forcing of saltwater upstr
eam. Government regulations conservatively control dam releases to prevent saltwater migrating into a freshwater r
eservoir, but sub-optimizes the commercial operation of the dam. This paper describes an alternative control appro
ach using an ANN model of the "gain" between the freshwater releases and the specific conductivity, used to estima
te salinity, near the reservoir. A scheme for implementing the model in a real-time control system is also describ
ed.
