A Hybrid Neural Network Model for ENSO Prediction in Combination with Principal Oscillation Pattern Analyses

doi:10.1007/s00376-021-1368-4

IOCAS-IR

	A Hybrid Neural Network Model for ENSO Prediction in Combination with Principal Oscillation Pattern Analyses
	Zhou, Lu 1,2,3; Zhang, Rong-Hua1,2,3,4,5
	2022-03-08
发表期刊	ADVANCES IN ATMOSPHERIC SCIENCES
ISSN	0256-1530
页码	14
通讯作者	Zhang, Rong-Hua([email protected])
摘要	El Nino-Southern Oscillation (ENSO) can be currently predicted reasonably well six months and longer, but large biases and uncertainties remain in its real-time prediction. Various approaches have been taken to improve understanding of ENSO processes, and different models for ENSO predictions have been developed, including linear statistical models based on principal oscillation pattern (POP) analyses, convolutional neural networks (CNNs), and so on. Here, we develop a novel hybrid model, named as POP-Net, by combining the POP analysis procedure with CNN-long short-term memory (LSTM) algorithm to predict the Nino-3.4 sea surface temperature (SST) index. ENSO predictions are compared with each other from the corresponding three models: POP model, CNN-LSTM model, and POP-Net, respectively. The POP-based pre-processing acts to enhance ENSO-related signals of interest while filtering unrelated noise. Consequently, an improved prediction is achieved in the POP-Net relative to others. The POP-Net shows a high-correlation skill for 17-month lead time prediction (correlation coefficients exceeding 0.5) during the 1994-2020 validation period. The POP-Net also alleviates the spring predictability barrier (SPB). It is concluded that value-added artificial neural networks for improved ENSO predictions are possible by including the process-oriented analyses to enhance signal representations.
关键词	ENSO prediction the principal oscillation pattern (POP) analyses neural network a hybrid approach
DOI	10.1007/s00376-021-1368-4
收录类别	SCI
语种	英语
资助项目	Strategic Priority Research Program of the Chinese Academy of Sciences[XDA19060102]; National Natural Science Foundation of China [NSFC][41690122(41690120)]; National Natural Science Foundation of China [NSFC][42030410]
WOS研究方向	Meteorology & Atmospheric Sciences
WOS类目	Meteorology & Atmospheric Sciences
WOS记录号	WOS:000766037100001
出版者	SCIENCE PRESS
引用统计	被引频次：23[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.qdio.ac.cn/handle/337002/178201
专题	中国科学院海洋研究所
通讯作者	Zhang, Rong-Hua
作者单位	1.Chinese Acad Sci, Inst Oceanol, Qingdao 266071, Peoples R China 2.Chinese Acad Sci, Ctr Ocean MegaSci, Qingdao 266071, Peoples R China 3.Univ Chinese Acad Sci, Beijing 100029, Peoples R China 4.Pilot Natl Lab Marine Sci & Technol, Lab Ocean & Climate Dynam, Qingdao 266237, Peoples R China 5.Chinese Acad Sci, Ctr Excellence Quaternary Sci & Global Change, Xian 710061, Peoples R China
第一作者单位	中国科学院海洋研究所; 中国科学院海洋大科学研究中心
通讯作者单位	中国科学院海洋研究所; 中国科学院海洋大科学研究中心
推荐引用方式 GB/T 7714	Zhou, Lu,Zhang, Rong-Hua. A Hybrid Neural Network Model for ENSO Prediction in Combination with Principal Oscillation Pattern Analyses[J]. ADVANCES IN ATMOSPHERIC SCIENCES,2022:14.
APA	Zhou, Lu,&Zhang, Rong-Hua.(2022).A Hybrid Neural Network Model for ENSO Prediction in Combination with Principal Oscillation Pattern Analyses.ADVANCES IN ATMOSPHERIC SCIENCES,14.
MLA	Zhou, Lu,et al."A Hybrid Neural Network Model for ENSO Prediction in Combination with Principal Oscillation Pattern Analyses".ADVANCES IN ATMOSPHERIC SCIENCES (2022):14.

条目包含的文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
Zhou-Zhang2022_Artic（2978KB）	期刊论文	出版稿	限制开放	CC BY-NC-SA	浏览