基于LSTM-ResNet模型的定点有效波高预测-海洋预报

基于LSTM-ResNet模型的定点有效波高预测

单位：广西师范大学电子工程学院, 广西桂林 541004

分类号：P731.22

出版年·卷·期（页码）：2022·39·第二期（80-85）

摘要：

基于北部湾单站位浮标采集数据，提出一种基于长短期记忆网络（LSTM）和残差网络（ResNet）相融合的网络模型，将研究结果运用到短时波高预测中，并将模型的数值预测结果与LSTM网络、反向传播（BP）网络和ResNet网络在短时波高预测中的数值计算结果进行对比分析。结果表明：该模型在短时波高预测中，预测结果偏差较小且实用性较高，能够在一定条件下提高有效波高短期预测数值的有效性。

Based on the data collected by single-station buoys in the Beibu Gulf, this paper proposes a network model using the fusion of Long Short-Term Memory (LSTM) and Residual Network (ResNet), and applies the research results to short-term wave height forecasting; Thereafter, the numerical prediction results of the model are compared with the numerical calculation results of LSTM network, Back Propagation (BP) network and ResNet in the prediction of short-term wave height. Finally, the research results show that the LSTM-ResNet model have the characteristics of small deviation and high practicability in predicting the short-term wave height, and could improve the effectiveness of the short-term prediction value of the significant wave height under certain conditions.

参考文献：

[1] Duan W Y, Han Y, Huang L M, et al. A hybrid EMD-SVR model for the short-term prediction of significant wave height[J]. Ocean Engineering, 2016, 124: 54-73.
[2] Altunkaynak A, Özger M. Temporal significant wave height estimation from wind speed by perceptron Kalman filtering[J]. Ocean Engineering, 2004, 31(10): 1245-1255.
[3] 陈希, 沙文钰, 李妍, 等. 人工神经网络技术在海浪预报中的应用[J]. 海洋通报, 2002, 21(2): 11-15. Chen X, Sha W Y, Li Y, et al. Application of the artificial neural network in the sea wave forecast[J]. Marine Science Bulletin, 2002, 21(2): 11-15.
[4] Meng L, He Y J, Chen J N, et al. Neural network retrieval of ocean surface parameters from SSM/I data[J]. Monthly Weather Review, 2007, 135(2): 586-597.
[5] 孟雷, 闻斌, 姜洪峰, 等. 神经网络方法对海浪有效波高数值模拟的改进[J]. 海洋预报, 2010, 27(2): 8-14. Meng L, Wen B, Jiang H F, et al. Neural network method to numerical simulation of significant wave height improvements[J]. Marine Forecasts, 2010, 27(2): 8-14.
[6] Makarynskyy O. Improving wave predictions with artificial neural networks[J]. Ocean Engineering, 2004, 31(5-6): 709-724.
[7] Londhe S N, Panchang V. One-day wave forecasts based on artificial neural networks[J]. Journal of Atmospheric and Oceanic Technology, 2006, 23(11): 1593-1603.
[8] Tsai C P, Lin C, Shen J N, et al. Neural network for wave forecasting among multi-stations[J]. Ocean Engineering, 2002, 29(13): 1683-1695.
[9] Fan S T, Xiao N H, Dong S. A novel model to predict significant wave height based on long short-term memory network[J]. Ocean Engineering, 2020, 205: 107298.
[10] Mandal S, Prabaharan N. Ocean wave forecasting using recurrent neural networks[J]. Ocean Engineering, 2006, 33(10): 1401-1410.
[11] Zhang X N, Dai H. Significant wave height prediction with the CRBM-DBN model[J]. Journal of Atmospheric and Oceanic Technology, 2019, 36(3): 333-351.
[12] 许小峰, 顾建峰, 李永平. 海洋气象灾难[M]. 北京: 气象出版社, 2009: 79-82. Xu X F, Gu J F, Li Y P. Marine meteorological disaster[M]. Beijing: China Meteorological Press, 2009: 79-82.
[13] 周媛媛, 周林, 关皓, 等. 基于浮标资料的中国东部海域最大波高特征分析[J]. 海洋预报, 2019, 36(2): 21-29. Zhou Y Y, Zhou L, Guan H, et al. Characteristic analysis of maximum wave height in the eastern China Sea based on buoy data[J]. Marine Forecasts, 2019, 36(2): 21-29.
[14] Hochreiter S, Schmidhuber J. Long short-term memory[J]. Neural Computation, 1997, 9(8): 1735-1780.
[15] 崔文植. 基于长短期记忆与残差网络的航班延误预测[D]. 杭州: 杭州师范大学, 2019. Cui W Z. Flight delay prediction based on long short-term memory and residual network[D]. Hangzhou: Hangzhou Normal University, 2019.

服务与反馈：

【文章下载】【发表评论】【查看评论】【加入收藏】