Spatio-temporal dependence-based tensor fusion for thermocline analysis in Argo data
As the ocean data acquired by the Argo project is increasingly huge, how to use artificial intelligence to analyze it so as to discover the distribution and variation of ocean temperature with space and time becomes an important research topic in the world. In this article, a spatio-temporal dependence-based tensor fusion method is proposed, which can be used to determine and analyze the thermocline. In the time dimension, long short-term memory is used to predict the temperature of seawater; in the spatial dimension, the thermocline is found incrementally by using tensor analysis. Experiments on BOA Argo data from 2004 to 2016 show that the proposed method can accurately determine the boundary of the thermocline and predict the future trend of the thermocline.