人工智能海浪预报的发展与挑战

陆钰婷; 郭文康; 丁骏; 王林峰; 李晓辉; 王久珂

doi:10.3969/j.issn.1001-909X.2024.03.002

PDF(1059 KB)

海洋学研究 ›› 2024, Vol. 42 ›› Issue (3) : 28-37. DOI: 10.3969/j.issn.1001-909X.2024.03.002

研究综述

人工智能海浪预报的发展与挑战

陆钰婷 ¹ ,
郭文康 ² ,
丁骏 ³ ,
王林峰 ² ,
李晓辉 ⁴ ,
王久珂 ¹^,²^,^*

作者信息 +

Progress and challenges of artificial intelligence wave forecasting

LU Yuting ¹ ,
GUO Wenkang ² ,
DING Jun ³ ,
WANG Linfeng ² ,
LI Xiaohui ⁴ ,
WANG Jiuke ¹^,²^,^*

Author information +

文章历史 +

摘要

海浪是海洋中最为重要的现象之一,快速准确的海浪预报对于保障海上生产、生活安全具有重要意义。该文回顾了海浪预报方法的发展历程,包括传统统计预报、数值模式预报以及目前快速发展的人工智能预报。基于人工智能的海浪预报模型表现出计算速度快、预报精度自适应优化等优势,已经开始从研究阶段逐步应用于实际海浪预报业务之中,但同时该方法也存在预报要素有限、极端海况预报值偏低以及预报泛化能力弱的局限。该文根据人工智能海浪预报的特点,提出了人工智能海浪预报目前亟需解决的观测数据高效利用、先验知识引入、人工智能模型安全性与泛化能力提升等关键科学技术问题。

Abstract

Waves are one of the most important phenomena in the ocean. The accurate and quick updated wave forecasting is of crucial significance for ensuring marine activities safety. The development of wave forecast is presented, including the traditional statistical wave forecasting methods, numerical wave prediction models, and the rapidly developing artificial intelligence (AI) wave forecasting methods. Currently, AI wave forecast models have been demonstrated unique advantages in terms of computational efficiency and adaptive forecasting accuracy, and they are gradually being applied in practical wave forecasting operations, transitioning from the research stage. However, they also have limitations, including limited forecasting elements, underestimation of extreme wave conditions, and weak forecasting generalization ability. Based on the characteristics of AI wave prediction, key scientific and technological issues that need to be addressed in current AI wave forecasting are proposed. These include efficient utilization of observational data, incorporation of prior physical knowledge, and enhancement of AI model safety and generalization ability.

导出引用

陆钰婷, 郭文康, 丁骏, 等. 人工智能海浪预报的发展与挑战[J]. 海洋学研究. 2024, 42(3): 28-37 https://doi.org/10.3969/j.issn.1001-909X.2024.03.002

LU Yuting, GUO Wenkang, DING Jun, et al. Progress and challenges of artificial intelligence wave forecasting[J]. Journal of Marine Sciences. 2024, 42(3): 28-37 https://doi.org/10.3969/j.issn.1001-909X.2024.03.002

中图分类号： P731.33;P714

参考文献

列表( 原文顺序 | 文献年度倒序 | 文中引用次数倒序 ) 可视化分析

[1]	管长龙. 我国海浪理论及预报研究的回顾与展望[J]. 青岛海洋大学学报, 2000, 30(4):549-556. GUAN C L. A review of history and prospect for study of sea wave theory and its forecast in China[J]. Journal of Ocean University of Qingdao, 2000, 30(4): 549-556. 本文引用 [1]

[2]

YOUNG

I R

, RIBAL

. Multiplatform evaluation of global trends in wind speed and wave height[J]. Science, 2019, 364(6440): 548-552.

https://doi.org/10.1126/science.aav9527

https://www.ncbi.nlm.nih.gov/pubmed/31023894

本文引用 [2] 摘要

In this study, global satellite data were analyzed to determine trends in oceanic wind speed and significant wave height over the 33-year period from 1985 to 2018. The analysis uses an extensive database obtained from 31 satellite missions comprising three types of instruments-altimeters, radiometers, and scatterometers. The analysis shows small increases in mean wind speed and significant wave height over this period, with larger increases in extreme conditions (90th percentiles). The largest increases occur in the Southern Ocean. Confidence in the results is strengthened because the wind speed trends are confirmed by all three satellite systems. An extensive set of sensitivity analyses confirms that both the mean and 90th percentile trends are robust, with only small impacts caused by satellite calibration and sampling patterns.Copyright © 2019 The Authors, some rights reserved; exclusive licensee American Association for the Advancement of Science. No claim to original U.S. Government Works.

[3]	HEMER M A, WANG X L, WEISSE R, et al. Advancing wind-waves climate science[J]. Bulletin of the American Meteorological Society, 2012, 93(6): 791-796. 本文引用 [1]

[4]	WANG X L, SWAIL V R, ZWIERS F W, et al. Detection of external influence on trends of atmospheric storminess and northern oceans wave heights[J]. Climate Dynamics, 2009, 32: 189-203. 本文引用 [1]

[5]

YOUNG

I R

, ZIEGER

, BABANIN

A V

. Global trends in wind speed and wave height[J]. Science, 2011, 332(6028): 451-455.

https://doi.org/10.1126/science.1197219

https://www.ncbi.nlm.nih.gov/pubmed/21436400

本文引用 [1] 摘要

Studies of climate change typically consider measurements or predictions of temperature over extended periods of time. Climate, however, is much more than temperature. Over the oceans, changes in wind speed and the surface gravity waves generated by such winds play an important role. We used a 23-year database of calibrated and validated satellite altimeter measurements to investigate global changes in oceanic wind speed and wave height over this period. We find a general global trend of increasing values of wind speed and, to a lesser degree, wave height, over this period. The rate of increase is greater for extreme events as compared to the mean condition.

[6]	YOUNG I R, VINOTH J, ZIEGER S, et al. Investigation of trends in extreme value wave height and wind speed[J]. Journal of Geophysical Research: Oceans, 2012, 117: C00J06. 本文引用 [1]

[7]	MENTASCHI L, VOUSDOUKAS M I, VOUKOUVALAS E, et al. Global changes of extreme coastal wave energy fluxes triggered by intensified teleconnection patterns[J]. Geophysical Research Letters, 2017, 44(5): 2416-2426. 本文引用 [1]

[8]	OUMERACI H. Review and analysis of vertical breakwater failures-Lessons learned[J]. Coastal Engineering, 1994, 22(1/2): 3-29. 本文引用 [1]

[9]	PULLEN T, ALLSOP N W H, BRUCE T, et al. EurOtop: Wave overtopping of sea defences and related structures: Assessment manual[M]. [S.l.]: Boyens Medien GmbH, 2007. 本文引用 [1]

[10]	VANEM E, FAZERES-FERRADOSA T, ROSA-SANTOS P, et al. Statistical description and modelling of extreme ocean wave conditions[J]. Proceedings of the Institution of Civil Engineers-Maritime Engineering, 2019, 172(4): 124-132. 本文引用 [1]

[11]	ADYTIA D, SAEPUDIN D, PUDJAPRASETYA S R, et al. A deep learning approach for wave forecasting based on a spatially correlated wind feature, with a case study in the Java Sea, Indonesia[J]. Fluids, 2022, 7(1): 39. 本文引用 [1]

[12]	TÜR R. Maximum wave height hindcasting using ensemble linear-nonlinear models[J]. Theoretical and Applied Clima-tology, 2020, 141: 1151-1163. 本文引用 [1]

[13]	屈远, 高志一, 蔡靖泽, 等. 数值模型和智能模型的海浪预报能力比较[J]. 海洋预报, 2022, 39(5):17-26. QU Y, GAO Z Y, CAI J Z, et al. Comparison of wave prediction ability between numerical model and AI model[J]. Marine Forecasts, 2022, 39(5): 17-26. 本文引用 [1]

[14]	OWENS E H. Beaufort wind scale[M]//SCHWARTZ M. Beaches and coastal geology. New York: Springer, 1982: 161-162. 本文引用 [1]

[15]	许富祥, 许林之. 海浪预报方法综述(一)[J]. 海洋预报, 1989(3):33-43. XU F X, XU L Z. A review of wave forecasting methods (I)[J]. Marine Forecasts, 1989 (3): 33-43. 本文引用 [4]

[16]	SVERDRUP H U, MUNK W H. Wind, sea and swell: theory of relations for forecasting[M]. Washington, D.C: Hydrographic Office, 1947. 本文引用 [2]

[17]	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. 本文引用 [2]

[18]	PIERSON W J, NEUMANN G, JAMES R. Practical methods for observing and forecasting ocean waves by means of wave spectra and statistics[J]. Hydrographic Office Publication, 1955, 603: 300. 本文引用 [1]

[19]	文圣常. 我在海浪理论及应用领域的研究工作[J]. 中国科学院院刊, 1996(2):61. WEN S C. My Research work in the field of wave theory and applications[J]. Bulletin of the Chinese Academy of Sciences, 1996(2): 61. 本文引用 [1]

[20]	汪炳祥. 新型风浪谱及其应用[J]. 海洋与湖沼, 1962(Z2):142-160. WANG B X. New type of wind wave spectrum and its applications[J]. Oceanologia et Limnologia Sinica, 1962(Z2): 142-160. 本文引用 [1]

[21]	汪炳祥. 风浪谱的形式的再探讨[J]. 海洋与湖沼, 1964(1): 23-37. WANG B X. Reconsideration of the form of wave spectrum[J]. Oceanologia et Limnologia Sinica, 1964(1): 23-37. 本文引用 [1]

[22]	WILSON B W. Numerical prediction of ocean waves in the North Atlantic for December, 1959[J]. Deutsche Hydro-grafische Zeitschrift, 1965, 18(3): 114-130. 本文引用 [1]

[23]	BRETSCHNEIDER C. Wave variability and wave spectra for wind generated gravity waves[J]. Beach Erosion Board, 1959: 196. 本文引用 [1]

[24]	TSYPLUKHIN V F, KHASKHACHIKH G D, SAMARIN V G. U.S. Army coastal engineering research center[J]. Hydro-technical Construction, 1971, 5(9): 860-863. 本文引用 [1]

[25]	关孟儒. 台风波浪推算方法的探讨[J]. 华东水利学院学报, 1981(2):17-36. GUAN M R. A discussion on the calculation method of typhoon waves[J]. Journal of East China College of Hydraulic Engineering, 1981(2): 17-36. 本文引用 [1]

[26]	SWAMP Group. Wave dynamics (Book reviews: Ocean wave modeling)[J]. Science, 1985, 229.DOI:10.1126/science.229.4711.377. 本文引用 [1]

[27]	PHILLIPS O M. The equilibrium range in the spectrum of wind-generated waves[J]. Journal of Fluid Mechanics, 1958, 4(4): 426. 本文引用 [1]

[28]	WAMDI Group. The WAM model—a third generation ocean wave prediction model[J]. Journal of Physical Oceanography, 1988, 18(12): 1775-1810. 本文引用 [3]

[29]	BOOIJ N, RIS R C, HOLTHUIJSEN L H. A third-generation wave model for coastal regions: 1. Model description and validation[J]. Journal of Geophysical Research: Oceans, 1999, 104(C4): 7649-7666. 本文引用 [2]

[30]	HASSELMANN S. The WAM wave model system[R]. Max Planck Institut für Meteorologie, 1987. 本文引用 [1]

[31]	TOLMAN H L, BALASUBRAMANIYAN B, BURROUGHS L D, et al. Development and implementation of wind-generated ocean surface wave modelsat NCEP[J]. Weather and Forecasting, 2002, 17(2): 311-333. 本文引用 [2]

[32]	MOSAVI A, OZTURK P, CHAU K W. Flood prediction using machine learning models: Literature review[J]. Water, 2018, 10(11): 1536. 本文引用 [2]

[33]

SHAMSHIRBAND

, MOSAVI

, RABCZUK

, et al. Prediction of significant wave height; comparison between nested grid numerical model, and machine learning models of artificial neural networks, extreme learning and support vector machines[J]. Engineering Applications of Compu-tational Fluid Mechanics, 2020, 14(1): 805-817.

本文引用 [1]

[34]	ZENG P. Artificial neural networks principle for finite element method[J]. Zeitschrift fur Angewandte Mathematik und Mechanik, 1996, 76(S5): 565-566. 本文引用 [1]

[35]	FUNAHASHI K I, NAKAMURA Y. Approximation of dynamical systems by continuous time recurrent neural networks[J]. Neural Networks, 2008, 6(6): 801-806. DOI:10.1016/S0893-6080(05)80125-X. 本文引用 [1]

[36]

MARCHI

, VESPERINI

, EYBEN

, et al. A novel approach for automatic acoustic novelty detection using a denoising autoencoder with bidirectional LSTM neural networks[C]// International Conference on Acoustics, Speech and Signal Processing (ICASSP). South Brisbane, QLD, Australia. IEEE, 2015: 1996-2000.

本文引用 [1]

[37]	CHEN K, TAO W B. Once for all: A two-flow convolutional neural network for visual tracking[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2018, 28(12): 3377-3386. 本文引用 [1]

[38]	ŠEVO I, AVRAMOVIĆ A. Convolutional neural network based automatic object detection on aerial images[J]. IEEE Geoscience and Remote Sensing Letters, 2016, 13(5): 740-744. 本文引用 [1]

[39]	VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[Z/OL]. arXiv, 2017: 1706.03762. http://arxiv.org/abs/1706.03762. http://arxiv.org/abs/1706.03762 本文引用 [1]

[40]	LIN T, WANG Y, LIU X, et al. A survey of transformers[J]. AI Open, 2022, 3: 111-132. 本文引用 [1]

[41]

SCARSELLI

, GORI

, TSOI

A C

, et al. The graph neural network model[J]. IEEE Transactions on Neural Networks, 2009, 20(1): 61-80.

https://doi.org/10.1109/TNN.2008.2005605

https://www.ncbi.nlm.nih.gov/pubmed/19068426

本文引用 [1] 摘要

Many underlying relationships among data in several areas of science and engineering, e.g., computer vision, molecular chemistry, molecular biology, pattern recognition, and data mining, can be represented in terms of graphs. In this paper, we propose a new neural network model, called graph neural network (GNN) model, that extends existing neural network methods for processing the data represented in graph domains. This GNN model, which can directly process most of the practically useful types of graphs, e.g., acyclic, cyclic, directed, and undirected, implements a function tau(G,n) is an element of IR(m) that maps a graph G and one of its nodes n into an m-dimensional Euclidean space. A supervised learning algorithm is derived to estimate the parameters of the proposed GNN model. The computational cost of the proposed algorithm is also considered. Some experimental results are shown to validate the proposed learning algorithm, and to demonstrate its generalization capabilities.

[42]	ZHOU J, CUI G Q, HU S D, et al. Graph neural networks: A review of methods and applications[J]. AI Open, 2020, 1: 57-81. 本文引用 [1]

[43]	HUANG H, ZENG Z N, YAO D Y, et al. Spatial-temporal ConvLSTM for vehicle driving intention prediction[J]. Tsinghua Science and Technology, 2022, 27(3): 599-609. 本文引用 [1]

[44]	LIM X Y, GAN K B, ABD AZIZ N A. Deep ConvLSTM network with dataset resampling for upper body activity recognition using minimal number of IMU sensors[J]. Applied Sciences, 2021, 11(8): 3543. 本文引用 [1]

[45]	PENG S Q, XIE L. Effect of determining initial conditions by four-dimensional variational data assimilation on storm surge forecasting[J]. Ocean Modelling, 2006, 14(1/2): 1-18. 本文引用 [1]

[46]	LIU X, WANG Q, MU M. Optimal initial error growth in the prediction of the Kuroshio large meander based on a high-resolution regional ocean model[J]. Advances in Atmospheric Sciences, 2018, 35(11): 1362-1371. 本文引用 [1]

[47]	ZHANG Z X, LI C W, LI Y S, et al. Incorporation of artificial neural networks and data assimilation techniques into a third-generation wind-wave model for wave forecasting[J]. Journal of Hydroinformatics, 2006, 8(1): 65-76. 本文引用 [1]

[48]	许立兵, 王安喜, 汪纯阳, 等. 基于机器学习的海洋环境预报订正方法研究[J]. 海洋通报, 2020, 39(6): 695-704. XU L B, WANG A X, WANG C Y, et al. Research on correction method of ocean environmental forecasting based on machine learning[J]. Marine Bulletin, 2020, 39(6): 695-704. 本文引用 [1]

[49]	ELLENSON A, PEI Y L, WILSON G, et al. An application of a machine learning algorithm to determine and describe error patterns within wave model output[J]. Coastal Engi-neering, 2020, 157: 103595. 本文引用 [1]

[50]	GRACIA S, OLIVITO J, RESANO J, et al. Improving accuracy on wave height estimation through machine learning techniques[J]. Ocean Engineering, 2021, 236: 108699. 本文引用 [1]

[51]	ALI M, PRASAD R. Significant wave height forecasting via an extreme learning machine model integrated with improved complete ensemble empirical mode decomposition[J]. Renewable and Sustainable Energy Reviews, 2019, 104: 281-295. 本文引用 [1]

[52]	DEO M C, SRIDHAR NAIDU C. Real time wave forecasting using neural networks[J]. Ocean Engineering, 1998, 26(3): 191-203. 本文引用 [1]

[53]	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. 本文引用 [1]

[54]	DEKA P C, PRAHLADA R. Discrete wavelet neural network approach in significant wave height forecasting for multistep lead time[J]. Ocean Engineering, 2012, 43: 32-42. 本文引用 [1]

[55]	DIXIT P, LONDHE S, DANDAWATE Y. Removing predic-tion lag in wave height forecasting using Neuro-Wavelet modeling technique[J]. Ocean Engineering, 2015, 93: 74-83. 本文引用 [1]

[56]	MAHJOOBI J, ADELI MOSABBEB E. Prediction of signi-ficant wave height using regressive support vector machines[J]. Ocean Engineering, 2009, 36(5): 339-347. 本文引用 [1]

[57]	ELBISY M S. Sea wave parameters prediction by support vector machine using a genetic algorithm[J]. Journal of Coastal Research, 2015, 314: 892-899. 本文引用 [1]

[58]	GOLESTANI M, ZEINODDINI M. Gap-filling and predicting wave parameters using support vector regression method[C]//Proceedings of ASME 2011 30th International Conference on Ocean, Offshore and Arctic Engineering, Rotterdam, The Netherlands. 2011: 613-620. 本文引用 [1]

[59]	NITSURE S P, LONDHE S N, KHARE K C. Wave forecasts using wind information and genetic programming[J]. Ocean Engineering, 2012, 54: 61-69. 本文引用 [1]

[60]	KUMAR N K, SAVITHA R, AL MAMUN A. Ocean wave height prediction using ensemble of extreme learning machine[J]. Neurocomputing, 2018, 277: 12-20. 本文引用 [1]

[61]	HUANG G B, ZHU Q Y, SIEW C K. Extreme learning machine: A new learning scheme of feedforward neural networks[C]// 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No. 04CH37541). Budapest, Hungary. DOI:10.1109/IJCNN.2004.1380068. 本文引用 [1]

[62]	KALOOP M R, KUMAR D, ZARZOURA F, et al. A wavelet-Particle swarm optimization-Extreme learning machine hybrid modeling for significant wave height prediction[J]. Ocean Engineering, 2020, 213: 107777. 本文引用 [1]

[63]	MANDAL S, PRABAHARAN N. Ocean wave forecasting using recurrent neural networks[J]. Ocean Engineering, 2006, 33(10): 1401-1410. 本文引用 [1]

[64]	WEI C C, CHENG J Y. Nearshore two-step typhoon wind-wave prediction using deep recurrent neural networks[J]. Journal of Hydroinformatics, 2020, 22(2): 346-367. 本文引用 [1]

[65]	MIKY Y, KALOOP M R, ELNABWY M T, et al. A Recurrent-Cascade-Neural network-nonlinear autoregressive networks with exogenous inputs (NARX) approach for long-term time-series prediction of wave height based on wave characteristics measurements[J]. Ocean Engineering, 2021, 240: 109958. 本文引用 [1]

[66]	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. 本文引用 [1]

[67]	JÖRGES C, BERKENBRINK C, STUMPE B. Prediction and reconstruction of ocean wave heights based on bathymetric data using LSTM neural networks[J]. Ocean Engineering, 2021, 232: 109046. 本文引用 [1]

[68]	ZHOU S Y, BETHEL B J, SUN W J, et al. Improving significant wave height forecasts using a joint empirical mode decomposition—long short-term memory network[J]. Journal of Marine Science and Engineering, 2021, 9(7): 744. 本文引用 [1]

[69]	ALI M, PRASAD R, XIANG Y, et al. Advanced extreme learning machines vs. deep learning models for peak wave energy period forecasting: A case study in Queensland, Australia[J]. Renewable Energy, 2021, 177: 1031-1044. 本文引用 [1]

[70]	CHEN D L, LIU F, ZHANG Z Q, et al. Significant wave height prediction based on Wavelet Graph Neural Network[C]//2021 IEEE 4th International Conference on Big Data and Artificial Intelligence (BDAI). Qingdao, China. IEEE, 2021: 80-85. 本文引用 [1]

[71]	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. 本文引用 [1]

[72]	BAI G, WANG Z F, ZHU X Y, et al. Development of a 2-D deep learning regional wave field forecast model based on convolutional neural network and the application in South China Sea[J]. Applied Ocean Research, 2022, 118: 103012. 本文引用 [1]

[73]	HOLTHUIJSEN L H. Waves in oceanic and coastal waters[M]. Cambridge, UK: Cambridge University Press, 2007. 本文引用 [1]

[74]	张新宇, 石爱国, 周波, 等. 一种海浪谱预报的新模式[J]. 中国航海, 2015, 38(2):118-121. ZHANG X Y, SHI A G, ZHOU B, et al. A new method to predict ocean wave spectra[J]. Navigation of China, 2015, 38(2): 118-121. 本文引用 [1]

[75]	MOONEYHAM J, CROSBY S C, KUMAR N, et al. SWRL net: A spectral, residual deep learning model for improving short-term wave forecasts[J]. Weather and Forecasting, 2020, 35(6): 2445-2460. 本文引用 [1]

[76]	SONG Y H, JIANG H Y. A deep learning-based approach for empirical modeling of single-point wave spectra in open oceans[J]. Journal of Physical Oceanography, 2023, 53(9): 2089-2103. 本文引用 [1]