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    

基于多尺度大核卷积门控注意力的海面温度预测方法

谭博文1，黄婉舟2，王小英1，龙浩辰1，黄劼1   

  1. 1. 四川大学，成都 610065；

    2. 国网四川省电力公司成都市温江供电分公司，成都 611130；

        


  • 收稿日期:2025-08-25 修回日期:2025-11-06 接受日期:2025-12-05
  • 通讯作者: 黄劼
  • 基金资助:
    川大-泸州校地项目基金（省级课题）(2023CDLZ-4)

Sea surface temperature prediction method based on multi-scale large kernel convolutional gated attention

TAN Bowen1, HUANG Wanzhou1, 2, WANG Xiaoying1, LONG Haochen1, HUANG Jie1   

  1. 1. Sichuan University, Chengdu 610065;

    2. State Grid Sichuan Electric Power Company Chengdu Wenjiang Power Supply Branch, Chengdu 611130;




  • Received:2025-08-25 Revised:2025-11-06 Accepted:2025-12-05
  • Supported by:

    Sichuan University-Luzhou Joint Fund Project(2023CDLZ-4)

PDF (PC)

赞

摘要： 海面温度(sea surface temperature, SST)是研究全球气候和海洋环境的重要因素,准确的海面温度预测对海洋生态保护和研究等领域有重要意义｡目前的SST预测方法存在无法充分利用数据的空间关联信息和时间演变信息的问题｡为了解决这个问题,本文提出一种多尺度大核门控注意力网络(multiscale large kernel gated attention networks,MuLKGANet),该网络由编码器,时空翻译器和解码器组成｡其编､解码器用于空间特征的提取与还原,核心时空翻译器旨在利用多种卷积核充分提取数据的全局和局部空间依赖,并使用门控注意力机制学习数据的时间演变｡实验结果表明,与广泛使用的ConvLSTM模型相比,在12小时海面温度预测时,本方法均方误差指标提升了约83%,并且在海岸附近的预测误差明显较小｡

关键词: 海表面温度, 注意力机制, 多尺度, 门控机制, 时空预测

Abstract: Sea surface temperature (SST) is an important factor in the study of global climate and marine environment, and accurate SST prediction is of great significance in the fields of marine ecological protection and research.The current SST prediction methods have the problem of not being able to make full use of the spatial correlation information and temporal evolution information of the data.To solve this problem, this paper proposes a multi-scale large kernel gated attention network(MuLKGANet), which consists of an encoder, a spatio-temporal translator and a decoder.Its encoder and decoder are used for spatial feature extraction and reduction. The core spatio-temporal translator aims to fully extract the global and local spatial dependencies of the data using multiple convolutional kernels, and learn the temporal evolution of the data using the gated attention mechanism. The experimental results show that, compared to the widely used ConvLSTM model, the present method improves the mean-square error metric by about 83% for 12-hour sea surface temperature prediction, and the prediction error is significantly smaller near the coast.

Key words: sea surface temperature, attention mechanism, multiscale, gated mechanism, spatial and temporal prediction