Neural network with multi-trend simulating transfer function for forecasting typhoon wave

Authors:
H. K. Chang;W. A. Chien
Affiliations:
Department of Civil Engineering, National Chiao-Tung University, Hsinchu, Taiwan, ROC;Department of Civil Engineering, National Chiao-Tung University, Hsinchu, Taiwan, ROC
Venue:
Advances in Engineering Software
Year:
2006

Citing 1
Cited 1

Neural network PC tools: a practical guide

Neural network PC tools: a practical guide

Prediction of sand ripple geometry under waves using an artificial neural network

Computers & Geosciences

Quantified Score

Hi-index	0.00

Visualization

Abstract

This study develops an NN typhoon wave model to accurately and efficiently calculate wave heights at a point of interest. Multitrend simulating transfer functions were first introduced to exemplify the relationship between wave heights and each conceivable input factor by regressive fitting. The proposed NN-MT model can accurately forecast wave peak with an error of less 1.2 m and with time delay within 3h and can be extended to cover the station besides the original station of interest.