热带海洋学报 ›› 2022, Vol. 41 ›› Issue (5): 1-16.doi: 10.11978/2021121

• 海洋水文学 •    下一篇

基于生成对抗网络模型的热带和亚热带海洋中尺度涡预报研究

刘爽1,2(), 经志友1(), 詹海刚1   

  1. 1.热带海洋环境国家重点实验室(中国科学院南海海洋研究所), 广东 广州 510301
    2.中国科学院大学, 北京 100049
  • 收稿日期:2021-09-07 修回日期:2021-12-27 出版日期:2022-09-10 发布日期:2021-12-28
  • 通讯作者: 经志友
  • 作者简介:刘爽(1996—), 女, 黑龙江省七台河市人, 硕士研究生, 从事海洋过程与大数据研究。email: liushuang_57@126.com
  • 基金资助:
    国家自然科学基金(92058201);国家自然科学基金(41776040);国家自然科学基金(41949907);国家自然科学基金(42149907);中国科学院基础前沿科学研究计划原始创新项目(ZDBS-LY-DQC011);广州市科学研究计划(201904010420)

Predicting the mesoscale eddy in the tropical and subtropical ocean based on generative adversarial network model

LIU Shuang1,2(), JING Zhiyou1(), ZHAN Haigang1   

  1. 1. State Key Laboratory of Tropical Oceanography (South China Sea Institute of Oceanology, Chinese Academy of Sciences), Guangzhou 510301, China
    2. University of Chinese Academy of Sciences, Beijing 100049, China
  • Received:2021-09-07 Revised:2021-12-27 Online:2022-09-10 Published:2021-12-28
  • Contact: JING Zhiyou
  • Supported by:
    National Natural Science Foundation of China(92058201);National Natural Science Foundation of China(41776040);National Natural Science Foundation of China(41949907);National Natural Science Foundation of China(42149907);Original Innovation Project of Basic Frontier Scientific Research Program of CAS(ZDBS-LY-DQC011);Guangzhou Science and Technology Project(201904010420)

摘要:

中尺度涡蕴含海洋超过90%的动能, 显著影响海洋物质能量循环。对中尺度涡的预报是目前物理海洋学研究的热点和难点。文章基于卫星高度计观测的近30年海表面高度异常数据(sea level anomaly, SLA), 采用基于博弈思想的生成对抗网络方法(generative adversarial networks, GAN), 构建了中尺度涡预报模型, 进行了28天预报, 并采用独立样本分析了预报涡旋的空间分布、时间分布、能量强度等特征参数, 探讨影响预报结果准确性和时效性的主要因素。结果表明, 半径为100~200km的涡旋在15天左右的预报时长仍能保持较好的准确性及时效性, 误差在20%以内。该区域的平均涡动能约为0.875m2·s-2, 其预报的均方根误差(root mean square error, RMSE)普遍介于0.02~0.04m2·s-2。且涡旋预报结果受异常天气影响较小, 在正常天气条件和台风娜基莉条件下具有相似的预报能力。这些结果对进一步理解并应用生成对抗网络这一新方法预报海洋中尺度涡提供了参考。

关键词: 生成对抗网络, 中尺度涡预报, 海表面高度异常, 深度学习方法

Abstract:

Mesoscale eddies occupy more than 90 % of the kinetic energy in oceans, which significantly impact on the oceanic mass and energy cycle. The prediction of mesoscale eddies remains a very essential, but difficult research topic in the current physical oceanography field. Based upon the sea level anomaly (SLA) data measured by satellite altimeter in the last 30 years, this study develops a model for the mesoscale eddy prediction according to the generative adversarial networks (GAN) method and game theory. The results of 28-day prediction, their spatial-temporal distributions, and energy intensities are analyzed with independent samples. The main factors that affect the spatial and temporal accuracies are discussed. The results show that the temporal accuracy of this method can be accepted in about 15 days. For the mesoscale eddies with a radius of 100 ~ 200 km, the prediction error is generally less than 20 % by this method. The mean eddy kinetic energy in the study domain is about 0.875 m2·s-2 and the root mean square error (RMSE) is roughly between 0.02 ~ 0.04 m2·s-2. Furthermore, the results are suggestive of that the prediction is less affected by abnormal weather, and has similar forecasting ability under normal weather conditions and typhoon Nakri. These results provide a reference for further understanding and applying the new method of generative adversarial networks to predict ocean mesoscale eddies.

Key words: generative adversarial networks, the prediction of the mesoscale eddy, sea level anomaly, deep learning methodology

中图分类号: 

  • P731.27