Prediction of 3-D Ocean Temperature by Multilayer Convolutional LSTM

• Published in: IEEE geoscience and remote sensing letters Vol. 17; no. 8; pp. 1303 - 1307
• Main Authors: Zhang, Kun, Geng, Xupu, Yan, Xiao-Hai
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.08.2020; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Artificial neural networks; Convolutional neural network (CNN); Feature extraction; global marine environment observation data (ARGO); Logic gates; long- and short-term memory (LSTM); Marine environment; Multilayers; Neural networks; Ocean temperature; Oceans; Predictions; Predictive models; Sea surface; Sea surface temperature; Short term; Short term memory; Surface temperature; Temperature variations; Training
• ISSN: 1545-598X; 1558-0571
• DOI: 10.1109/LGRS.2019.2947170

Sea surface temperature (SST) prediction has raised considerable attention in various ocean-related fields. However, these methods were only limited to the time-sequence prediction of some isolated points, and their spatial linkage was not considered. Furthermore, these studies only predict the temperature of sea surface, but the subsurface temperature in the inner ocean is much more important. In this letter, we propose a model of multilayer convolutional long- and short-term memory (M-convLSTM) to predict 3-D ocean temperature, comprising convolutional neural networks (CNNs), long- and short-term memory (LSTM), and multiple layer stacking to consider the horizontal and vertical temperature variations from sea surface to subsurface to be about 2000 m below. Global marine environment observation data (ARGO) are used to conduct the prediction of 3-D ocean temperature in this letter, and the results demonstrate the overall good accuracy of forecast and ARGO data.