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

近海海面温度预报：集成多源数据的U-Net深度学习模型

刘辰1, 2，刘哲1, 2，张潇文1, 2，田泽丰1, 2，朱明明1, 2，赵玉庭1, 2，苏博1, 2，王晓霞1, 2， 史雪洁1, 2
  

  1. 1. 山东省海洋资源与环境研究院，山东 烟台 264000；

    2. 山东省数据开放创新应用实验室，山东 烟台 264000



  • 收稿日期:2025-12-11 修回日期:2026-03-06 接受日期:2026-03-17
  • 通讯作者: 史雪洁
  • 基金资助:

    国家重点研发计划项目(2023YFC3206400)；山东省重点研发计划项目(2020CXGC011404)

Sea Surface Temperature Forecast for Coastal Waters: U-Net Deep Learning Model Integrating Multi-Source Data

LIU Chen1, 2, LIU Zhe1, 2, ZHANG Xiaowen1, 2, TIAN Zefeng1, 2, ZHU Mingming1, 2, ZHAO Yuting1, 2, SU Bo1, 2, WANG Xiaoxia1, 2, SHI Xuejie1, 2   

  1. 1. Shandong Marine Resource and Environment Research Institute, Yantai 264000, China;

    2. Shandong Open Data Innovation and Application Laboratory, Yantai 264000, China




  • Received:2025-12-11 Revised:2026-03-06 Accepted:2026-03-17
  • Supported by:

     National Key Research and Development Programme Project (2023YFC3206400); Shandong Provincial Key Research and Development Programme Project (2020CXGC011404)

PDF (PC)

赞

摘要： SST(sea surface temperature)是海气相互作用中的关键物理参数，其精确预测对防灾减灾和海洋生态保护等方面具有重要意义。本研究基于U-Net架构，整合SST、DOS(density of sea surface)、NO₃(mole concentration of nitrate)及SWH(significant wave height)等多源海洋环境参数，构建了SP-UNet(sea surface temperature prediction model-UNet)，并对不同参数组合对比以得出最优组合。结果表明：引入SWH能够显著提升东海与南海区域的预测精度，其中在东海区域的表现尤为显著，其MAE(mean absolute error)相较于单SST输入降低了53%；DOS和NO₃的预测效果因海域而异，南海区域引入DOS效果更优，而东海区域则引入NO₃表现更佳；同时，模型误差随着季节变化而产生波动，南海区域在春夏季误差最低，东海区域则在秋冬季误差最低。此外，SP-UNet与ConvLSTM模型的对比结果展现出更优的预测性能，验证了该模型在海洋温度预报任务中的有效性。本研究为区域性海洋温度预测提供了有效方法，对海洋气象预警和气候变化研究具有重要意义。

关键词: 海面温度预测, 多源数据, 中国近海, 深度学习, U-Net

Abstract: SST (sea surface temperature) is a critical physical parameter in ocean-atmosphere interactions. Accurate prediction of SST is of great significance for disaster prevention and mitigation, and marine ecological conservation. This study integrates multi-source ocean environmental parameters—including SST, DOS (density of sea surface), NO₃ (mole concentration of nitrate), and SWH (significant wave height)—based on the U-Net architecture to construct a sea surface temperature prediction model (SP-UNet). By comparing different parameter combinations, an optimal configuration scheme is derived. Results indicate the following: Incorporating SWH significantly enhances prediction accuracy in both the East China Sea and South China Sea regions, with particularly notable improvements in the East China Sea. The MAE (mean absolute error) decreased by 53% compared to using SST input alone. The predictive performance of DOS and NO₃ varies by sea area: introducing DOS yields superior results in the South China Sea, while incorporating NO₃ performs better in the East China Sea. Concurrently, model errors fluctuate seasonally, with the lowest errors occurring in the South China Sea during spring and summer, and in the East China Sea during autumn and winter. Furthermore, comparative results between SP-UNet and ConvLSTM models demonstrate superior predictive performance, validating the model's effectiveness in marine temperature forecasting tasks. This study provides an effective method for regional ocean temperature forecasting, holding significant implications for marine meteorological early warning and climate change research.

Key words: sea surface temperature prediction, multi-source data, Chinese coastal waters, deep learning, U-Net