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

• Published in: Advances in atmospheric sciences Vol. 39; no. 6; pp. 889 - 902
• Main Authors: Zhou, Lu, Zhang, Rong-Hua
• Format: Journal Article
• Language: English
• Published: Heidelberg Science Press 01.06.2022; Springer Nature B.V; Laboratory for Ocean and Climate Dynamics,Pilot National Laboratory for Marine Science and Technology,Qingdao 266237,China; University of Chinese Academy of Sciences,Beijing 100029,China%CAS Key Laboratory of Ocean Circulation and Waves,Institute of Oceanology,and Center for Ocean Mega-Science,Chinese Academy of Sciences,Qingdao 266071,China; CAS Key Laboratory of Ocean Circulation and Waves,Institute of Oceanology,and Center for Ocean Mega-Science,Chinese Academy of Sciences,Qingdao 266071,China; University of Chinese Academy of Sciences,Beijing 100029,China; Center for Excellence in Quaternary Science and Global Change,Chinese Academy of Sciences,Xi'an 710061,China
• Subjects: Algorithms; Artificial neural networks; Atmospheric Sciences; Coefficients; Correlation coefficient; Correlation coefficients; Earth and Environmental Science; Earth Sciences; El Nino; El Nino phenomena; El Nino-Southern Oscillation event; Geophysics/Geodesy; Lead time; Long short-term memory; Mathematical models; Meteorology; Modelling; Neural networks; Noise prediction; Original Paper; Pattern analysis; Predictions; Sea surface; Sea surface temperature; Signal processing; Southern Oscillation; Statistical analysis; Statistical models; Surface temperature; the principal oscillation pattern (POP) analyses; a hybrid approach; ENSO prediction; 神经网络; 混合建模; neural network; 主振荡型分析和神经网络相结合; ENSO预测; 主振荡型分析
• ISSN: 0256-1530; 1861-9533
• DOI: 10.1007/s00376-021-1368-4

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 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 Niño-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.