Ocean Engineering 30 (2003) 22752295
www.elsevier.com/locate/oceaneng
Extended Technical Note
Development of a regional neural network for
coastal water level predictions
Wenrui Huang a,∗, Catherine Murray a, Nicholas Kraus b,
Julie Rosati b
a
Civil Engineering Department, FAMU-FSU College of Engineering, 2525 Pottsdamer Street,
Tallahassee, FL 32310-6046, USA
b
US Army Engineer Research and Development Center, Coastal and Hydraulics Laboratory,
3909 Halls Ferry Road, Vicksburg, MS 39180-6199, USA
Received 21 August 2002; received in revised form 27 November 2002; accepted 5 March 2003
Abstract
This paper presents the development of a Regional Neural Network for Water Level (RNN--
WL) predictions, with an application to the coastal inlets along the South Shore of Long Island,
New York. Long-term water level data at coastal inlets are important for studying coastal
hydrodynamics sediment transport. However, it is quite common that long-term water level
observations may be not available, due to the high cost of field data monitoring. Fortunately,
the US National Oceanographic and Atmospheric Administration (NOAA) has a national net-
work of water level monitoring stations distributed in regional scale that has been operating
for several decades. Therefore, it is valuable and cost effective for a coastal engineering study
to establish the relationship between water levels at a local station and a NOAA station in
the region. Due to the changes of phase and amplitude of water levels over the regional coastal
line, it is often difficult to obtain good linear regression relationship between water levels from
two different stations. Using neural network offers an effective approach to correlate the non-
linear input and output of water levels by recognizing the historic patterns between them. In
this study, the RNN--WL model was developed to enable coastal engineers to predict long-
term water levels in a coastal inlet, based on the input of data in a remote NOAA station in
the region. The RNN--WL model was developed using a feed-forwards, back-propagation
neural network structure with an optimized training algorithm. The RNN--WL model can be
trained and verified using two independent data sets of hourly water levels.
The RNN--WL model was tested in an application to Long Island South Shore. Located
about 60100 km away from the inlets there are two permanent long-term water level stations,
Corresponding author. Tel.: +1850-410-6199; fax: +1-850-410-6236.
∗
E-mail address: whuang@eng.fsu.edu (W. Huang).
0029-8018/$ - see front matter 2003 Elsevier Ltd. All rights reserved.
doi:10.1016/S0029-8018(03)00083-0
Previous Page
