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

作     者：Lu ZHOU Rong-Hua ZHANG Lu ZHOU;Rong-Hua ZHANG

作者机构：CAS Key Laboratory of Ocean Circulation and WavesInstitute of Oceanologyand Center for Ocean Mega-ScienceChinese Academy of SciencesQingdao 266071China University of Chinese Academy of SciencesBeijing 100029China Laboratory for Ocean and Climate DynamicsPilot National Laboratory for Marine Science and TechnologyQingdao 266237China Center for Excellence in Quaternary Science and Global ChangeChinese Academy of SciencesXi’an 710061China 

出 版 物：《Advances in Atmospheric Sciences》 (大气科学进展（英文版）)

年 卷 期：2022年第39卷第6期

页      面：889-902页

核心收录：

学科分类：07[理学] 070601[理学-气象学] 0706[理学-大气科学] 

基　　金：supported by the Strategic Priority Research Program of the Chinese Academy of Sciences(Grant No.XDA19060102) the National Natural Science Foundation of China[NSFC Grant Nos.41690122(41690120),and 42030410] 

主　　题：ENSO prediction the principal oscillation pattern(POP)analyses neural network a hybrid approach 

摘      要：El Niño-Southern Oscillation(ENSO)can be currently predicted reasonably well six months and longer,but large biases and uncertainties remain in its real-time *** 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 ***,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 Niño-3.4 sea surface temperature(SST)*** predictions are compared with each other from the corresponding three models:POP model,CNN-LSTM model,and POP-Net,*** POP-based pre-processing acts to enhance ENSO-related signals of interest while filtering unrelated ***,an improved prediction is achieved in the POP-Net relative to *** POP-Net shows a high-correlation skill for 17-month lead time prediction(correlation coefficients exceeding 0.5)during the 1994-2020 validation *** 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.