大气和海洋科学快报(英文版)2023,Vol.16Issue(4):45-50,6.DOI:10.1016/j.aosl.2023.100347
Wave forecast in the Atlantic Ocean using a double-stage ConvLSTM network
Wave forecast in the Atlantic Ocean using a double-stage ConvLSTM network
摘要
Abstract
海浪预报对海上运输安全至关重要.本研究提出了一种涵盖物理信息的深度学习模型Double-stage ConvLSTM(D-ConvLSTM)以改进大西洋的海浪预报.将D-ConvLSTM模型与海浪持续性预测和原始ConvLSTM模型的预测技巧进行对比.结果表明,预测误差随着预测时长的增加而增加.D-ConvLSTM模型在预测准确度方面优于前二者,且第三天预测的均方根误差低于0.4 m,距平相关系数约在0.8.此外,当使用IFS预测风替代再分析风时,能够产生相似的预测效果.这表明D-ConvLSTM模型的预测能力能够与ECMWF-WAM模式相当,且更节省计算资源和时间.关键词
海浪预测/深度学习/预测模型/大西洋Key words
Wave forecast/Deep learning/Prediction model/Atlantic ocean引用本文复制引用
Lin Ouyang,Fenghua Ling,Yue Li,Lei Bai,Jing-Jia Luo..Wave forecast in the Atlantic Ocean using a double-stage ConvLSTM network[J].大气和海洋科学快报(英文版),2023,16(4):45-50,6.基金项目
This work was supported by the National Key Research and Develop-ment Program of China[grant number 2020YFA0608000]and the Na-tional Natural Science Foundation of China[grant number 42030605]. ()