Prediction of Significant Wave Height in Offshore China Based on the Machine Learning Method

被引：45

作者：

Feng, Zhijie ^{[1
]}

Hu, Po ^{[2
,3
,4
]}

Li, Shuiqing ^{[2
,3
,4
]}

Mo, Dongxue ^{[2
,3
]}

机构：

[1] Shandong Univ Sci & Technol, Coll Math & Syst Sci, Qingdao 266580, Peoples R China

[2] Chinese Acad Sci, Inst Oceanol, Key Lab Ocean Circulat & Waves, Nanhai Rd, Qingdao 266071, Peoples R China

[3] Pilot Natl Lab Marine Sci & Technol Qingdao, Lab Ocean Dynam & Climate, Wenhai Rd 1, Qingdao 266237, Peoples R China

[4] Univ Chinese Acad Sci, 19A Yuquan Rd, Beijing 100049, Peoples R China

来源：

JOURNAL OF MARINE SCIENCE AND ENGINEERING | 2022年 / 10卷 / 06期

基金：

中国国家自然科学基金;

关键词：

wave height; recurrent neural network; long short-term memory network; GRU; EMD; SHORT-TERM PREDICTION; NEURAL-NETWORKS; MODEL; SPECTRUM; FLOW;

D O I：

10.3390/jmse10060836

中图分类号：

U6 [水路运输]; P75 [海洋工程];

学科分类号：

0814 ; 081505 ; 0824 ; 082401 ;

摘要：

Accurate wave prediction can help avoid disasters. In this study, the significant wave height (SWH) prediction performances of the recurrent neural network (RNN), long short-term memory network (LSTM), and gated recurrent unit network (GRU) were compared. The 10 m u-component of wind (U10), 10 m v-component of wind (V10), and SWH of the previous 24 h were used as input parameters to predict the SWHs of the future 1, 3, 6, 12, and 24 h. The SWH prediction model was established at three different sites located in the Bohai Sea, the East China Sea, and the South China Sea, separately. The experimental results show that the performance of LSTM and GRU networks based on the gating mechanism was better than that of traditional RNNs, and the performances of the LSTM and GRU networks were comparable. The EMD method was found to be useful in the improvement of the LSTM network to forecast the significant wave heights of 12 and 24 h.

引用

页数：20

共 28 条

[1]

Abhigna P, 2017, 2017 INTERNATIONAL CONFERENCE ON COMMUNICATION AND SIGNAL PROCESSING (ICCSP), P1856, DOI 10.1109/ICCSP.2017.8286717

[2] LEARNING LONG-TERM DEPENDENCIES WITH GRADIENT DESCENT IS DIFFICULT [J].

BENGIO, Y ;

SIMARD, P ;

FRASCONI, P .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 1994, 5 (02) :157-166

[3] Data preprocessing for river flow forecasting using neural networks: Wavelet transforms and data partitioning [J].

Cannas, Barbara ;

Fanni, Alessandra ;

See, Linda ;

Sias, Giuliana .

PHYSICS AND CHEMISTRY OF THE EARTH, 2006, 31 (18) :1164-1171

[4]

Cho K., 2014, PROC 8 WORKSHOP SYNT, P103, DOI DOI 10.3115/V1/W14-4012

[5]

Chung J, 2014, ARXIV

[6] Significant wave height and energy flux prediction for marine energy applications: A grouping genetic algorithm - Extreme Learning Machine approach [J].

Cornejo-Bueno, L. ;

Nieto-Borge, J. C. ;

Garcia-Diaz, P. ;

Rodriguez, G. ;

Salcedo-Sanz, S. .

RENEWABLE ENERGY, 2016, 97 :380-389

[7] Short-Term Traffic Flow Prediction Method for Urban Road Sections Based on SpaceTime Analysis and GRU [J].

Dai, Guowen ;

Ma, Changxi ;

Xu, Xuecai .

IEEE ACCESS, 2019, 7 :143025-143035

[8] Discrete wavelet neural network approach in significant wave height forecasting for multistep lead time [J].

Deka, Paresh Chandra ;

Prahlada, R. .

OCEAN ENGINEERING, 2012, 43 :32-42

[9] A hybrid EMD-SVR model for the short-term prediction of significant wave height [J].

Duan, W. Y. ;

Han, Y. ;

Huang, L. M. ;

Zhao, B. B. ;

Wang, M. H. .

OCEAN ENGINEERING, 2016, 124 :54-73

[10] A novel model to predict significant wave height based on long short-term memory network [J].

Fan, Shuntao ;

Xiao, Nianhao ;

Dong, Sheng .

OCEAN ENGINEERING, 2020, 205

← 1 2 3 →