Name
Abstract | ||
|---|---|---|
Sea surface temperature (SST) is an important indicator for balancing surface energy and measuring sea heat. Various effects caused by the sea temperature field significantly affect human activities to a large extent. It is important to predict the sea surface temperature efficiently and accurately. Existing SST prediction methods regard each sensor as an independent individual, without considering the structure or topology of the sensor network and ignoring the connectivity of the sensor network. To address this problem, this study investigates the SST prediction problem from the perspective of graph learning. We propose a time-series graph network (TSGN) that can jointly capture graph-based spatial correlation and temporal dynamics. TSGN uses a long short-term memory network to aggregate the features of time series data and establishes a graph neural network model to complete the SST prediction task. Experiments using SST data from the Pacific Northwest from 2001 to 2005 show that this method is more efficient and accurate when dealing with data containing time-series information and is superior to the existing SST prediction methods. (C) 2021 Elsevier Inc. All rights reserved. |
Year | DOI | Venue |
|---|---|---|
2021 | 10.1016/j.bdr.2021.100237 | BIG DATA RESEARCH |
Keywords | DocType | Volume |
Graph neural network, Time-series graph, SST prediction | Journal | 25 |
ISSN | Citations | PageRank |
2214-5796 | 0 | 0.34 |
References | Authors | |
0 | 6 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Yongjiao Sun | 1 | 85 | 8.30 |
| Xin Yao | 2 | 0 | 0.34 |
| Xin Bi | 3 | 65 | 6.78 |
| Xuechun Huang | 4 | 0 | 0.34 |
| Xiangguo Zhao | 5 | 19 | 3.73 |
| Baiyou Qiao | 6 | 0 | 0.34 |