基于ConvLSTM的中国东南沿海波浪智能预报和评估

doi:10.3969/j.issn.1001-909X.2024.03.007

摘要/Abstract

摘要：

相较于半理论半分析和数值模型的波浪预报方法,智能波浪预报有着精度高、计算资源需求低的优势。该文基于卷积长短期记忆网络(convolutional long short-term memory network, ConvLSTM)算法,建立了有效波高(significant wave height, SWH)二维预报模型,以中国东南沿海2014—2022年ERA5数据进行训练,通过敏感性试验优化模型配置,并开展中国东南沿海SWH在2023年4个预报时效(6 h、12 h、18 h、24 h)下的预测性能评估。敏感性试验显示,输入时间序列长度N=4(即输入-18 h, -12 h, -6 h, 0 h的SWH值)时,模型在4个预报时效下的准确性均优于其他时间序列长度;输入物理要素组合为SWH、平均波向和海面10 m 风矢量时,模型在12 h、18 h和24 h预报时效下的准确性优于其他组合。通过对ConvLSTM模型训练及配置的精细调整,可以实现对中国东南沿海SWH的二维、高精度的智能预报。

关键词: 中国近海, 卷积长短期记忆网络, 数据驱动, 海浪, 有效波高, 二维预报模型, 短期预报, 人工智能, 深度学习

Abstract:

Compared with the semi-theoretical and semi-analytical wave forecasting and numerical modeling,artificial intelligence wave forecasting has the advantages of higher forecasting accuracy and lower computational resource requirements. In this paper, a two-dimensional significant wave height (SWH) forecasting model for the southeast coast of China is established based on the convolutional long short-term memory network (ConvLSTM) algorithm using ERA5 (ECMWF Reanalysis v5) reanalysis data as the initial field. The data from 2014-2022 are used to train the forecasts of SWH for the next 6 h, 12 h, 18 h and 24 h, and the data from 2023 are used for testing. Sensitivity tests are carried out to optimize the model configuration and evaluate the prediction performance of SWH in the southeast coast of China at four period validity (6 h, 12 h, 18 h, 24 h) in 2023. Sensitivity tests show that when input time series length N=4(input SWH value of -18 h, -12 h, -6 h, 0 h), the accuracies of the model at four period validity are better than those of other time series length. When the combination of input physical elements is SWH, mean wave direction and sea surface 10 m wind vector, the accuracy of the model is better than other combinations at 12 h, 18 h and 24 h. Through the fine-tuning of ConvLSTM model training and configuration, the two-dimensional and high-precision intelligent prediction of SWH in the southeast coast of China can be realized.

Key words: coast of China, convolutional long short-term memory network (ConvLSTM), data-driven, wave, significant wave height (SWH), two-dimensional prediction model, short-time forecast, artificial intelligence, deep learning

中图分类号:

P731.33
P714

金阳, 韩磊, 金梅兵, 董昌明. 基于ConvLSTM的中国东南沿海波浪智能预报和评估[J]. 海洋学研究, 2024, 42(3): 88-98.

JIN Yang, HAN Lei, JIN Meibing, DONG Changming. Intelligent wave forecasting and evaluation along the southeast coast of China based on ConvLSTM method[J]. Journal of Marine Sciences, 2024, 42(3): 88-98.

图/表 10

图1 中国东南海域的水深地形

Fig.1 The topography and water depth in the southeast seas of China

图2 SWH预报模型的结构示意图

Fig.2 Schematic diagram of the structure of the SWH prediction model

图3 不同时间序列长度的ConvLSTM模型预报性能评价指标

Fig.3 Evaluation indexes of ConvLSTM model prediction performance with different time series length

图4 ConvLSTM模型预报性能评价指数的季节差异

Fig.4 Seasonal difference of ConvLSTM model prediction performance evaluation indexes

图5 2023年春季观测SWH和预报SWH:ERA5(a~d), ConvLSTM模型(N=4, e~h)以及相对变化(i~l)

Fig.5 Observed SWH and predicted SWH of 2023 spring: ERA5 (a-d), ConvLSTM model (N=4, e-h) and the relative variability between model and ERA5 (i-l)

图6 ConvLSTM模型预报结果评价指数空间分布

Fig.6 Spatial distribution of ConvLSTM model prediction results evaluation indexes

表1 物理要素敏感性试验的ConvLSTM模型配置

Tab.1 ConvLSTM model configuration for the sensitivity test of physical elements

试验编号	输入的物理要素
2.1	SWH
2.2	SWH、平均波向
2.3	海面10 m经向风速、海面10 m纬向风速
2.4	SWH、海面10 m 经向风速、海面10 m纬向风速
2.5	SWH、平均波向、海面10 m纬向风速
2.6	SWH、平均波向、海面10 m经向风速、海面10 m纬向风速

图7 不同试验组的ConvLSTM模型预报性能评价

Fig.7 Evaluation of ConvLSTM model prediction performance in different experiment groups

图8 2023年春季观测SWH和预报SWH:ERA5(a~d),基于试验2.4配置的ConvLSTM模型(e~h)以及相对变化(i~l)

Fig.8 Observed SWH and predicted SWH of 2023 spring: ERA5 (a-d), ConvLSTM model based on experiment 2.4 configuration (e-h) and the relative variability between model and ERA5 (i-l)

图9 基于试验2.4配置的ConvLSTM模型性能评价

Fig.9 Performance evaluation of ConvLSTM model based on experiment 2.4 configuration

参考文献 28

[1]	SHENG W N. Wave energy conversion and hydrodynamics modelling technologies: A review[J]. Renewable and Sustainable Energy Reviews, 2019, 109: 482-498.
[2]	REGUERO B G, LOSADA I J, MÉNDEZ F J. A recent increase in global wave power as a consequence of oceanic-warming[J]. Nature Communications, 2019, 10: 205.
[3]	KAMPHUIS J W. Introduction to coastal engineering and management[M]. Singapore: World Scientific, 2020.
[4]	WANG W X, TANG R C, LI C, et al. A BP neural network model optimized by mind evolutionary algorithm for predicting the ocean wave heights[J]. Ocean Engineering, 2018, 162: 98-107.
[5]	YEGANEH-BAKHTIARY A, EYVAZOGHLI H, SHABAKHTY N, et al. Machine learning prediction of wave characteristics: Comparison between semi-empirical approaches and DT model[J]. Ocean Engineering, 2023, 286: 115583.
[6]	刘凡, 陆小敏, 徐丹, 等. 海浪预报方法研究进展[J]. 河海大学学报:自然科学版, 2021, 49(5):387-393.
	LIU F, LU X M, XU D, et al. Research progress of ocean waves forecasting method[J]. Journal of Hohai University: Natural Sciences, 2021, 49(5): 387-393.
[7]	BRETSCHNEIDER C L. Hurricane design wave practices[J]. Journal of the Waterways and Harbors Division, 1957, 83: 1-33.
[8]	NEUMANN G, PIERSON W J. A detailed comparison of theoretical wave spectra and wave forecasting methods[J]. Deutsche Hydrographische Zeitschrift, 1957, 10(4): 134-146.
[9]	文圣常. 普遍风浪谱及其应用[J]. 山东海洋学院学报,1960:15-43.
	WEN S C. Universal wind wave spectrum and its applications[J]. Journal of Shandong Ocean University, 1960: 15-43.
[10]	KAMRANZAD B, ETEMAD-SHAHIDI A, KAZEMINEZHAD M H. Wave height forecasting in Dayyer, the Persian Gulf[J]. Ocean Engineering, 2011, 38(1): 248-255.
[11]	GELCI R, CAZALÉ H, VASSAL J. La méthode des densités spectroangulaires[J]. Comité Central Océanogr, 1957, 9: 416-435.
[12]	DURRANT T, GREENSLADE D, HEMER M, et al. A global wave hindcast focussed on the Central and South Pacific[R]//The Centre for Australian Weather and Climat Research Technical Report No. 070, 2014.
[13]	BOOIJ N, RIS R C, HOLTHUIJSEN L H. A third-generation wave model for coastal regions: 1. Model descrip-tion and validation[J]. Journal of Geophysical Research: Oceans, 1999, 104(C4): 7649-7666.
[14]	TOLMAN H L. User manual and system documentation of WAVEWATCH-III TM version 3.14[R]. [S.l.]: NECP, 2009.
[15]	文圣常, 钱成春, 叶安乐, 等. 基于选定风浪方向谱的海浪模拟方法(英文)[J]. 青岛海洋大学学报, 1999(3): 345-397.
	WEN S C, QIAN C C, YE A L, et al. Wave modeling based on adopted wind-wave direction spectrum[J]. Journal of Ocean University of Qingdao, 1999 (3): 345-397.
[16]	袁业立, 华锋, 潘增弟, 等. LAGFD-WAM海浪数值模式:Ⅱ.区域性特征线嵌入格式及其应用[J]. 海洋学报, 1992, 14(6):12-24.
	YUAN Y L, HUA F, PAN Z D, et al. LAGFD-WAM numerical model of ocean waves—Ⅱ. Embedding scheme of regional characteristic lines and its application[J]. Acta Oceanologica Sinica, 1992, 14(6): 12-24.
[17]	MAKARYNSKYY O. Improving wave predictions with artificial neural networks[J]. Ocean Engineering, 2004, 31(5/6): 709-724.
[18]	ZUBIER K. Using an artificial neural network for wave height forecasting in the Red Sea[J]. Indian Journal of Geo Marine Sciences, 2020, 49: 184-191.
[19]	CORNEJO-BUENO L, NIETO-BORGE J C, GARCÍA-DÍAZ P, et al. Significant wave height and energy flux prediction for marine energy applications: A grouping genetic algorithm-extreme learning machine approach[J]. Renewable Energy, 2016, 97: 380-389.
[20]	KUMAR N K, SAVITHA R, MAMUN A A. Ocean wave height prediction using ensemble of extreme learning machine[J]. Neurocomputing, 2018, 277: 12-20.
[21]	PUSHPAM P M M, ENIGO V S F. Forecasting significant wave height using RNN-LSTM Models[C]//2020 4th Inter-national Conference on Intelligent Computing and Control Systems (ICICCS). Madurai, India. IEEE, 2020: 1141-1146.
[22]	GERS F A, SCHRAUDOLPH N N, SCHMIDHUBER J. Learning precise timing with LSTM recurrent networks[J]. Journal of Machine Learning Research, 2002, 3: 115-143.
[23]	HOCHREITER S, SCHMIDHUBER J. Long short-term memory[J]. Neural Computation, 1997, 9(8): 1735-1780. DOI PMID
[24]	HU H G, VAN DER WESTHUYSEN A J, CHU P, et al. Predicting Lake Erie wave heights and periods using XGBoost and LSTM[J]. Ocean Modelling, 2021, 164: 101832.
[25]	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.
[26]	SHI X J, CHEN Z R, WANG H, et al. Convolutional LSTM network: A machine learning approach for precipitation nowcasting[J]. Advances in Neural Information Processing Systems, 2015: 802-810.
[27]	CHOI H, PARK M, SON G, et al. Real-time significant wave height estimation from raw ocean images based on 2D and 3D deep neural networks[J]. Ocean Engineering, 2020, 201: 107129.
[28]	ZHOU S Y, XIE W H, LU Y X, et al. ConvLSTM-based wave forecasts in the South and East China Seas[J]. Frontiers in Marine Science, 2021, 8: 680079.