文献类型：期刊文献

英文题名：Numerical Weather Prediction of Sea Surface Temperature in South China Sea Using Attention-Based Context Fusion Network

作者：He, Hailun[1,2];Shi, Benyun[3];Zhu, Yuting[3];Feng, Liu[4];Ge, Conghui[3];Tan, Qi[3];Peng, Yue[3];Liu, Yang[4];Ling, Zheng[5];Li, Shuang[6]

机构：[1]Minist Nat Resources, Inst Oceanog 2, State Key Lab Satellite Ocean Environm Dynam, Hangzhou 310012, Peoples R China;[2]Southern Marine Sci & Engn Guangdong Lab Zhuhai, Zhuhai 519082, Peoples R China;[3]Nanjing Tech Univ, Coll Comp & Informat Engn, Coll Artificial Intelligence, Nanjing 211816, Peoples R China;[4]Hong Kong Baptist Univ, Dept Comp Sci, Hong Kong, Peoples R China;[5]Guangdong Ocean Univ, Coll Ocean & Meteorol, Key Lab Climate Resources & Environm Continental S, Dept Educ Guangdong Prov, Zhanjiang 524088, Peoples R China;[6]Zhejiang Univ, Inst Phys Oceanog & Remote Sensing, Ocean Coll, Zhoushan 316021, Peoples R China

年份：2024

卷号：16

期号：20

外文期刊名：REMOTE SENSING

收录：SCI-EXPANDED(收录号：WOS:001341568300001)、、EI(收录号：20244417293930)、Scopus(收录号：2-s2.0-85207412418)、WOS

基金：This research was funded by the National Natural Science Foundation of China (Grant no. 42227901) and the National Natural Science Foundation of China (NSFC) and Research Grants Council (RGC) of Hong Kong Joint Research Scheme (Grant no. 62261160387).

语种：英文

外文关键词：numerical weather prediction; sea surface temperature; South China Sea; attention-based context fusion network; deep learning

外文摘要：Numerical weather prediction of sea surface temperature (SST) is crucial for regional operational forecasts. Deep learning offers an alternative approach to traditional numerical general circulation models for numerical weather prediction. In our previous work, we developed a sophisticated deep learning model known as the Attention-based Context Fusion Network (ACFN). This model integrates an attention mechanism with a convolutional neural network framework. In this study, we applied the ACFN model to the South China Sea to evaluate its performance in predicting SST. The results indicate that for a 1-day lead time, the ACFN model achieves a Mean Absolute Error of 0.215 degrees C and a coefficient of determination (R2) of 0.972. In addition, in situ buoy data were utilized to validate the forecast results. The Mean Absolute Error for forecasts using these data increased to 0.500 degrees C for a 1-day lead time, with a corresponding R2 of 0.590. Comparative analyses show that the ACFN model surpasses traditional models such as ConvLSTM and PredRNN in terms of accuracy and reliability.