Time Series Surface Temperature Prediction Based on Cyclic Evolutionary Network Model for Complex Sea Area

Abstract

The prediction of marine elements has become increasingly important in the field of marine research. However, time series data in a complex environment vary significantly because they are composed of dynamic changes with multiple mechanisms, causes, and laws. For example, sea surface temperature (SST) can be influenced by ocean currents. Conventional models often focus on capturing the impact of historical data but ignore the spatio–temporal relationships in sea areas, and they cannot predict such widely varying data effectively. In this work, we propose a cyclic evolutionary network model (CENS), an error-driven network group, which is composed of multiple network node units. Different regions of data can be automatically matched to a suitable network node unit for prediction so that the model can cluster the data based on their characteristics and, therefore, be more practical. Experiments were performed on the Bohai Sea and the South China Sea. Firstly, we performed an ablation experiment to verify the effectiveness of the framework of the model. Secondly, we tested the model to predict sea surface temperature, and the results verified the accuracy of CENS. Lastly, there was a meaningful finding that the clustering results of the model in the South China Sea matched the actual characteristics of the continental shelf of the South China Sea, and the cluster had spatial continuity.

Keywords

• time series
• deep learning
• data mining
• prediction