东海黑潮西边界及流轴位置的特征分析和预测  

Characteristics Analysis and Prediction of the Western Boundary and Current Axis Position of the Kuroshio Current in the East China Sea

作　　者：张磊[1] 徐为帅 吴易达 刘乐阳 ZHANG Lei;XU Weishuai;WU Yida;LIU Yueyang(Dalian Naval Academy,Dalian 116018,China;91937 Troops,Zhoushan 316002,China;92020 Troops,Qingdao 266001,China)

机构地区：[1]海军大连舰艇学院,辽宁大连116018 [2]91937部队,浙江舟山316002 [3]92020部队,山东青岛266001

出　　处：《海洋技术学报》2024年第5期8-17,共10页Journal of Ocean Technology

基　　金：海军大连舰艇学院资助项目;北太平洋深海声速区划研究项目(DJYSYF2020-008)。

摘　　要：东海黑潮是西北太平洋的主要海洋环流之一,对我国的气候、生态和军事活动都有重要影响。本文利用高分辨率的JCOPE2M(Japan Coastal Ocean Predictability Experiment 2Modified)逐月温度和海表面高度数据及北太平洋环流振荡指数,研究了东海黑潮路径的变化特征并构建其预测模型。基于锋线提取和流线法确定了黑潮的西边界和轴线,然后构建了基于“分解-预测-重构”策略的变分模态分解(Variational Mode Decomposition,VMD)结合长短期记忆网络(Long Short-Term Memory,LSTM)的预测模型。结果显示:VMD方法能有效地将黑潮路径序列分解为不同时间尺度的模态子序列,季节上表现为夏(冬)季偏东(西),年际变化上表现出2~10 a的不同尺度的振荡特性。此外,VMD-LSTM模型在预测黑潮路径上的性能和鲁棒性显著优于差分自回归滑动平均模型和LSTM模型,最低均方误差达0.064°。本文为理解东海黑潮的动态变异提供了实际参考,展示了VMD-LSTM模型在海洋环流位置研究和预测中的应用潜力。The Kuroshio Current in the East China Sea is one of the primary oceanic circulations in the northwest Pacific,exerting significant influence on China爷s climate,ecology,and military activities.This study employs high-resolution monthly temperature and sea surface height data from JCOPE2M(Japan Coastal Ocean Predictability Experiment 2 Modified),along with the North Pacific Gyre Oscillation index,to explore the variability of the Kuroshio path and construct a prediction model.Through the extraction of frontal boundaries and streamline methods,the western boundary and axis of the Kuroshio are identified.Subsequently,a prediction model combining Variational Mode Decomposition(VMD)with Long Short-Term Memory(LSTM)networks is developed using a"decompose-predict-reconstruct"strategy.The results indicate that the VMD method effectively decomposes the Kuroshio path sequence into modal sub-sequences at different time scales,exhibiting an eastward(westward)shift during summer(winter)seasons and oscillations at scales ranging from 2 to 10 years in interannual variations.Furthermore,the performance and robustness of the VMD-LSTM model in predicting the Kuroshio path significantly outperform ARIMA and LSTM models,achieving the lowest mean square error of 0.064毅.This study provides practical insights into understanding the dynamic variability of the Kuroshio in the East China Sea and demonstrates the potential application of the VMD-LSTM model in oceanic circulation research and prediction.

关 键 词：东海黑潮 流轴提取 模态分解 机器学习 

分 类 号：P731[天文地球—海洋科学]