Prediction of Significant Wave Heights Based on CS-BP Model in the South China Sea

Shaobo Yang,Jianjun Xu,Zhenquan Zhang,Tianliang Xia,Xingfei Li,Chongwei Zheng,Hongyu Li

doi:10.1109/access.2019.2944422

Abstract

Forecasting the significant wave heights (Hs) is indispensable in HS-related engineering studies and is exceedingly important in the assessment of wave energy in future. As a technique essential for the future of clean energy systems, reducing the forecasting errors related to Hs has always been a vital research subject. In this paper, an optimized hybrid method based on the back propagation neural network (BP) and the cuckoo search algorithm (CS) is proposed to forecast the Hs in the South China Sea. This approach employs the CS as an intelligent optimization algorithm to optimize the parameters of the BP model, which develop a hybrid model that is suit for the data set, reducing the forecasting errors. The proposed method is subsequently tested based on nine prediction points selected in the South China Sea, where the proposed hybrid model is proved to perform effectively and steadily.

Highlights

Ocean waves are complex phenomenon because their production depends on many atmospheric, meteorological and oceanographic factors [1]
Wang et al [7] used a back propagation neural network (BP) neural network model optimized by mind evolutionary algorithm (MEA-BP) to predict the ocean wave heights, and the results indicated that MEA-BP was superior to the genetic algorithm-BP neural network model (GA-BP) and standard BP neural network model (St-BP) with faster running time and higher prediction accuracy
After the Hs are predicted based on cuckoo search algorithm (CS)-BP model, the network learning and prediction results will be checked to evaluate the prediction performance of the model

Summary

Introduction

Ocean waves are complex phenomenon because their production depends on many atmospheric, meteorological and oceanographic factors [1]. The study of ocean waves is of great significance to marine engineering construction, marine development, transportation, marine fishery, aquaculture and so on. The rapid and accurate prediction of wave heights is crucial for disaster warning and emergency prevention [2]. The complex and random characteristics of ocean waves make it more difficult to predict the height of ocean waves. For effective prediction of wave heights, many experts and scholars put forward different methods such as empirical, numerical and soft computing approaches.

Methods

Results

Conclusion