文章基本信息

标题：Sverdruv Munk Bretschneider Modification (SMB)for Significant Wave Height Prediction in Java Sea
本地全文：下载
作者：Aulia Siti Aisjah ; Syamsul Arifin ; Wimala L. Danistha 等
期刊名称：Current Journal of Applied Science and Technology
印刷版ISSN：2457-1024
出版年度：2016
卷号：16
期号：2
页码：1-8
语种：English
出版社：Sciencedomain International
摘要：Sverdruv Munk Bretschneider (SMB) methods is a semi-empirical method that has been used for the prediction of the significant wave height – Hs in global watersheds. Indonesian waters are surrounded by thousands of islands and wind movement has different nature with the waters of free movement. Java sea is flanked by the waters of Java and Borneo island. Sea breeze movement in Indonesia as a result of changes in atmospheric pressure in Asia and Australia. SMB methods require modification in the waters of Indonesia, so as to be used as a predictor in accordance with the high degree of accuracy. In this paper, a propose methods of designing the predictor with a modified SMB. The method compared by numerical methods of Nonlinear Autoregressive Exogeneous (NLARX) and expertise method of Artificial Neural Network (ANN). Case studies conducted in the Java sea along Surabaya – Banjarmasin cruises. This line is a busiest sea transportation in Indonesia. The data obtained from Badan Meteorologi, Klimatologi dan Geofisika (BMKG), the agency of meteorology, climatology and geophysics in Indonesia. The data are the wind speed and significant wave height. The length of data in interval 6 years, since 2006 until 2011. Predictor results shows a Root Mean Square Error - RMSE of modified SMB is 0.05, while NLARX method and ANN respectively are 0.24 and 0.16.
关键词：SMB modified;ANN;NLARX;the significant wave height;wind speed;RMSE