Abstract
Estimation of a wave spectrum from specified values of significant wave heights and average zero cross periods is traditionally made through empirical equations like those of Pierson — Moskowitz and Jonswap. This technical note discusses an alternative scheme based on artificial neural network. Wave spectral distribution over various wave frequencies was obtained for given values of significant wave height and period using feedforward back-propagation network. The rider buoy data at a site off the United States coast monitored by the National Data Buoy Center was used as a basis for network development. Qualitative as well as quantitative comparisons of the network-yielded spectra with target spectra indicated that the developed network could model the wave spectral shapes in a better way than commonly used theoretical spectra.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: Journal of Waterway, Port, Coastal, and Ocean Engineering
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
