AUTHOR=Zhou Shuyi , Xie Wenhong , Lu Yuxiang , Wang Yuanlin , Zhou Yulong , Hui Nian , Dong Changming 

TITLE=ConvLSTM-Based Wave Forecasts in the South and East China Seas

JOURNAL=Frontiers in Marine Science

VOLUME=Volume 8 - 2021

YEAR=2021

URL=https://www.frontiersin.org/journals/marine-science/articles/10.3389/fmars.2021.680079

DOI=10.3389/fmars.2021.680079

ISSN=2296-7745

ABSTRACT=Numerical wave models have been developed for the wave forecast in last two decades, however it faces challenges in terms of the requirement of large computing resources and improvement of accuracy. Based on a convolutional long short-term memory (ConvLSTM) algorithm, this paper establishes a two-dimensional significant wave height (SWH) prediction model for the South and East China Seas trained by WaveWatch III reanalysis data. We conduct 24 hours predictions under normal and extreme conditions, respectively. Under the normal wave condition, for 6-hour, 12-hour and 24-hour forecasting, their correlation coefficients are 0.98, 0.93 and 0.83, the mean absolute percentage errors are 15%, 29% and 61%. Under the extreme condition (typhoon), for 6-hour, 12-hour, their correlation coefficients are 0.98 and 0.94, the mean absolute percentage errors are 19% and 40%, which is better than the model trained by the all the data. It is concluded that the ConvLSTM can be applied to the two-dimensional wave forecast with high accuracy and efficiency.