Neural network modeling of salinity variation in Apalachicola River

Salinity is an important indicator for water quality and aquatic ecosystem in tidal rivers. The increase of salinity intrusion in a river may have an adverse effect on the aquatic environment system. This study presents an application of the artificial neural network (ANN) to assess salinity variation responding to the multiple forcing functions of freshwater input, tide, and wind in Apalachicola River, Florida. Parameters in the neural network model were trained until the model predictions of salinity matched well with the observations. Then, the trained model was validated by applying the model to another independent data set. The results indicate that the ANN model is capable of correlating the non-linear time series of salinity to the multiple forcing signals of wind, tides, and freshwater input in the Apalachicola River. This study suggests that the ANN model is an easy-to-use modeling tool for engineers and water resource managers to obtain a quick preliminary assessment of salinity variation in response to the engineering modifications to the river system.