检索
E-mail
RSS

作者投稿 主编审稿 专家审稿 远程编辑

热带海洋学报

• • 上一篇    下一篇

中尺度涡AI预报的多维度综合评估方法与应用

解一1, 孙钰坤2, 陈建1, 年睿3, 王强4, 杨一凯4, 陈默5, 张博6

  

  1. 1. 北京应用气象研究所, 北京 100029;

    2. 北京林业大学草业与草原学院, 北京 100083;

    3. 中国海洋大学电子工程学院, 山东 青岛 266100;

    4. 热带海洋环境与岛礁生态全国重点实验室(中国科学院南海海洋研究所), 广东 广州 510301;

    5. 香港科技大学工学院, 香港 999077;

    6. 中交四航工程研究院有限公司, 广东 广州 510540

  • 收稿日期:2026-08-11 修回日期:2026-10-31 接受日期:2026-11-03
  • 通讯作者: 陈建
  • 基金资助:

    国家自然科学基金面上项目(42576025, 42376191)

A Multi-Dimensional Comprehensive Evaluation Method and Application for AI-Based Mesoscale Eddy Prediction

XIE Yi1, SUN Yukun2, CHEN Jian1, NIAN Rui3, WANG Qiang4, YANG Yikai4, CHEN Mo5, ZHANG Bo6    

  1. 1. Beijing Institute of Applied Meteorology, Beijing 100029, China

    2. School of Grassland Science, Beijing Forestry University, Beijing 100083, China

    3. School of Electronic Engineering, Ocean University of China, Qingdao 266100, China

    4. State Key Laboratory of Tropical Oceanography, South China Sea Institute of Oceanology, Chinese Academy of Sciences, Guangzhou 510301, China

    5. School of Engineering, the Hong Kong University of Science and Technology, Hong Kong 999077, China

    6. CCCC Fourth Harbor Engineering Institute Co., Ltd., Guangzhou 510540, China

  • Received:2026-08-11 Revised:2026-10-31 Accepted:2026-11-03
  • Contact: CHEN Jian
  • Supported by:
     National Natural Science Foundation of China (42576025, 42376191)

PDF (PC)

赞

摘要： 中尺度涡是海洋动力系统的重要组成部分，但其AI预报结果的可信度难以用单一误差指标直接判断。本文针对现有评估方法指标单一、难以反映物理合理性与时空演变的问题，提出由物理一致性检验、时空演变特征匹配和核心参数精度量化构成的多维度综合评估体系，并给出量化指标、合格阈值和判定流程。以南海以东的西北太平洋海域的AI中尺度涡预报模型为评价对象，采用2000—2018年逐日海平面异常资料，输入连续14天海平面异常并输出未来14天预报，利用10个独立28天测试序列开展验证。结果表明：第14天海平面异常均方根误差平均值为3.29cm，55个有效真值涡旋全部成功匹配，核心参数均满足预设标准。该评估体系兼顾数值精度与物理合理性，可支撑中尺度涡AI预报系统的研发、检验与业务化应用。

关键词: 中尺度涡, AI预报, 评估方法, 物理一致性, 时空演变

Abstract: Mesoscale eddies are ubiquitous ocean dynamical structures, but the credibility of AI-based eddy forecasts cannot be judged by a single error metric alone. This paper proposes a multi-dimensional evaluation framework consisting of physical consistency checking, spatiotemporal evolution matching, and core parameter accuracy quantification, with quantitative metrics, pass thresholds, and a decision procedure. The framework is applied to an AI-based mesoscale eddy forecast model for the northwestern Pacific Ocean region east of the South China Sea, using daily sea level anomaly data from 2000 to 2018. The model ingests 14 days of observations and produces 14-day forecasts, and it is evaluated on ten independent 28-day test sequences. The mean 14-day sea surface height anomaly RMSE is 3.29 cm; all 55 effective truth eddies are successfully matched. The framework balances numerical accuracy and physical plausibility, supporting the development, validation, and operational use of AI-based mesoscale eddy forecasting systems.

Key words: Mesoscale eddy, AI prediction, Evaluation method, Physical consistency, Spatiotemporal evolution