Graph-Based Memory Recall Recurrent Neural Network for Mid-Term Sea-Surface Height Anomaly Forecasting

doi:10.1109/JSTARS.2024.3368766

IOCAS-IR > 海洋环流与波动重点实验室

	Graph-Based Memory Recall Recurrent Neural Network for Mid-Term Sea-Surface Height Anomaly Forecasting
	Zhou, Yuan 1; Ren, Tian 1; Chen, Keran 1; Gao, Le 2; Li, Xiaofeng 2
	2024
发表期刊	IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
ISSN	1939-1404
卷号	17 页码:6642-6657
通讯作者	Gao, Le(gaole@qdio.ac.cn) ; Li, Xiaofeng(xiaofeng.li@ieee.org)
摘要	Sea surface height anomaly (SSHA) plays a pivotal role in ocean dynamics and climate systems. This article develops a graph-based memory recall recurrent neural network (GMR-Net) to achieve accurate and reliable mid-term spatiotemporal prediction of the SSHA field. The proposed method designs a newly developed long-term memory recall cell as the building block of the network, which utilizes the proposed memory store recall (MSR) module to learn and capture the mid- and long-term temporal dependencies of the SSHA field. The MSR module can efficiently recall memories stored in the memory bank across multiple timestamps through the proposed graph representation mechanism even after long periods of disturbance. The mid-term SSHA forecasting is performed with a 30-day ahead, and our proposed GMR-Net model achieves high prediction accuracy in different geographical regions: the Tropical Western Pacific and the South China Sea, yielding an RMSE of 0.026 and 0.035 m, respectively. Compared with advanced prediction models, our proposed GMR-Net model exhibits high reliability and superior performance in mid-term SSHA forecasting. Moreover, marine phenomena, such as Rossby waves, which can cause dramatic changes in sea-surface height, are successfully observed from our forecast data, further verifying the effectiveness of our prediction method.
关键词	Forecasting Predictive models Atmospheric waves Spatiotemporal phenomena Sea surface Ocean waves Data models Sea-surface height anomaly (SSHA) deep learning (DL) spatiotemporal prediction Rossby waves
DOI	10.1109/JSTARS.2024.3368766
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China
WOS研究方向	Engineering ; Physical Geography ; Remote Sensing ; Imaging Science & Photographic Technology
WOS类目	Engineering, Electrical & Electronic ; Geography, Physical ; Remote Sensing ; Imaging Science & Photographic Technology
WOS记录号	WOS:001188473800014
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS关键词	EMPIRICAL MODE DECOMPOSITION ; ROSSBY WAVES ; LEVEL RISE ; LARGE-SCALE ; CHINA SEA ; VARIABILITY ; PREDICTION ; ATMOSPHERE ; FREQUENCY ; ALTIMETRY
引用统计
文献类型	期刊论文
条目标识符	http://ir.qdio.ac.cn/handle/337002/185101
专题	海洋环流与波动重点实验室
通讯作者	Gao, Le; Li, Xiaofeng
作者单位	1.Tianjin Univ, Sch Elect & Informat Engn, Tianjin 300072, Peoples R China 2.Chinese Acad Sci, Inst Oceanol, Key Lab Ocean Circulat & Waves, Qingdao 266071, Peoples R China
通讯作者单位	海洋环流与波动重点实验室
推荐引用方式 GB/T 7714	Zhou, Yuan,Ren, Tian,Chen, Keran,et al. Graph-Based Memory Recall Recurrent Neural Network for Mid-Term Sea-Surface Height Anomaly Forecasting[J]. IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING,2024,17:6642-6657.
APA	Zhou, Yuan,Ren, Tian,Chen, Keran,Gao, Le,&Li, Xiaofeng.(2024).Graph-Based Memory Recall Recurrent Neural Network for Mid-Term Sea-Surface Height Anomaly Forecasting.IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING,17,6642-6657.
MLA	Zhou, Yuan,et al."Graph-Based Memory Recall Recurrent Neural Network for Mid-Term Sea-Surface Height Anomaly Forecasting".IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 17(2024):6642-6657.