W. Huang et al. / Ocean Engineering 30 (2003) 22752295
2276
which have been operated by NOAA since the1940s. The neural network model was trained
using hourly data over a one-month period and validated for another one-month period. The
model was then tested over year-long periods. Results indicate that, despite significant changes
in the amplitudes and phases of the water levels over the regional study area, the RNN--WL
model provides very good long-term predictions of both tidal and non-tidal water levels at the
regional coastal inlets. In order to examine the effects of distance on the RNN--WL model
performance, the model was also tested using water levels from other remote NOAA stations
located at longer distances, which range from 234 km to 591 km away from the local station
at the inlets. The satisfactory results indicate that the RNN--WL model is able to supplement
long-term historical water level data at the coastal inlets based on the available data at remote
NOAA stations in the coastal region.
2003 Elsevier Ltd. All rights reserved.
Keywords: Neural networks; Tides; Water level; Coastal inlet
1. Introduction
Coastal inlets are important due to their navigation links between inland waterway
and coastal ocean, and because of their effects on shoreline and beach stability. For
example, on the South Shore of Long Island (Fig. 1) there are several inlets that are
Fig. 1. South Shore of Long Island, New York.
Previous Page
