Abstract
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.
摘 要
厄尔尼诺-南方涛动(ENSO)是地球气候系统中最强的年际变率信号。当前基于数理方程的动力模式可以提前至少6个月来对ENSO进行较好的预测,但在实时预测中仍存在较大的误差和不确定性。近几十年来,各种统计方法的提出和基于大数据的神经网络发展极大地提高了我们对ENSO的认识和预测能力,包括基于主振荡型(POP)分析的线性统计模式和基于神经网络的非线性统计模式等。本文中,我们把POP方法与神经网络卷积-长短时记忆网络(CNN-LSTM)相结合构建了一个混合型神经网络模式(简称为POP-Net),用于"Ni" "n" ̃"o" 3.4区海表温度(SST)异常的预测,并比较了单独POP模式、单独CNN-LSTM模型和其两者相结合的POP-Net模型对ENSO的预测能力。结果表明,将POP方法作为多尺度信号提取技术融合到神经网络模型中有助于增强ENSO相关的年际信号及对ENSO预测的影响,从而使得POP-Net模型比单独POP模型和神经网络模型都具有更好的预测性能。在1994-2020年测试期内,POP-Net模型可以提前17个月提供有效的ENSO预测(相关系数>0.5),并大幅改善了春季预报障碍(SPB)问题。可见,这种结合物理过程和大数据的混合建模方法可通过强化有效信息而削减无关噪音能有效提升ENSO的预测水平。
Similar content being viewed by others
References
Abiodun, O. I., A. Jantan, A. E. Omolara, K. V. Dada, N. A. Mohamed, and H. Arshad, 2018: State-of-the-art in artificial neural network applications: A survey. Heliyon, 4(11), e00938, https://doi.org/10.1016/j.heliyon.2018.e00938.
Barnett, T. P., N. Graham, S. Pazan, W. White, M. Latif, and M. Flügel, 1993: ENSO and ENSO-related predictability. Part I: Prediction of equatorial Pacific sea surface temperature with a hybrid coupled ocean-atmosphere model. J. Climate, 6(8), 1545–1566, https://doi.org/10.1175/1520-0442(1993)006<1545:EAERPP>2.0.CO;2.
Barnston, A. G., M. K. Tippett, M. L. L’Heureux, S. H. Li, and D. G. DeWitt, 2012: Skill of real-time seasonal ENSO model predictions during 2002–11: Is our capability increasing? Bull. Amer. Meteor. Soc., 93(5), 631–651, https://doi.org/10.1175/BAMS-D-11-00111.1.
Bjerknes, J., 1969: Atmospheric teleconnections from the equatorial Pacific. Mon. Wea. Rev., 97(3), 163–172, https://doi.org/10.1175/1520-0493(1969)097<0163:ATFTEP>2.3.CO;2.
Cane, M. A., and S. E. Zebiak, 1985: A theory for El Niño and the Southern Oscillation. Science, 228(4703), 1085–1087, https://doi.org/10.1126/science.228.4703.1085.
Cane, M. A., S. E. Zebiak, and S. C. Dolan, 1986: Experimental forecasts of El Niño. Nature, 321(6073), 827–832, https://doi.org/10.1038/321827a0.
Chen, D., S. E. Zebiak, A. J. Busalacchi, and M. A. Cane, 1995: An improved procedure for El Niño forecasting: Implications for predictability. Science, 269(5231), 1699–1702, https://doi.org/10.1126/science.269.5231.1699.
Duchi, J., E. Hazan, and Y. Singer, 2011: Adaptive subgradient methods for online learning and stochastic optimization. Journal of Machine Learning Research, 12, 2121–2159.
Eyring, V., S. Bony, G. A. Meehl, C. A. Senior, B. Stevens, R. J. Stouffer, and K. E. Taylor, 2016: Overview of the Coupled Model Intercomparison Project Phase 6 (CMIP6) experimental design and organization. Geosci. Model Dev., 9, 1937–1958, https://doi.org/10.5194/gmd-9-1937-2016.
Feng, L. C., R.-H. Zhang, B. Yu, and X. Han, 2020: The roles of wind stress and subsurface cold water in the second-year cooling of the 2017/18 La Niña event. Adv. Atmos. Sci., 37, 847–860, https://doi.org/10.1007/s00376-020-0028-4.
Gao, C., and R.-H. Zhang, 2017: The roles of atmospheric wind and entrained water temperature (Te) in the second-year cooling of the 2010–12 La Niña event. Climate Dyn., 48(1–2), 597–617, https://doi.org/10.1007/s00382-016-3097-4.
Gao, C., R.-H. Zhang, X. R. Wu, and J. C. Sun, 2018: Idealized experiments for optimizing model parameters using a 4D-Variational method in an intermediate coupled model of ENSO. Adv. Atmos. Sci., 35, 410–422, https://doi.org/10.1007/s00376-017-7109-z.
Goddard, L., S. J. Mason, S. E. Zebiak, C. F. Ropelewski, R. Basher, and M. A. Cane, 2001: Current approaches to seasonal to interannual climate predictions. International Journal of Climatology, 21(9), 1111–1152, https://doi.org/10.1002/joc.636.
Guo, Y. N., X. O. Cao, B. N. Liu, and K. C. Peng, 2020: El Niño index prediction using deep learning with ensemble empirical mode decomposition. Symmetry, 12(6), 893, https://doi.org/10.3390/sym12060893.
Ham, Y. G., J. H. Kim, and J. J. Luo, 2019: Deep learning for multi-year ENSO forecasts. Nature, 573(7775), 568–572, https://doi.org/10.1038/s41586-019-1559-7.
Hasselmann, K., 1988: PIPs and POPs: The reduction of complex dynamical systems using principal interaction and oscillation patterns. J. Geophys. Res.: Atmos., 93(D9), 11015–11021, https://doi.org/10.1029/JD093iD09p11015.
Hirst, A. C., 1986: Unstable and damped equatorial modes in simple coupled ocean-atmosphere models. Journal of Atmospheric Sciences, 43(6), 606–632, https://doi.org/10.1175/1520-0469(1986)043<0606:UADEMI>2.0.CO;2.
Hochreiter, S., and J. Schmidhuber, 1997: Long short-term memory. Neural Computation, 9(8), 1735–1780, https://doi.org/10.1162/neco.1997.9.8.1735.
Irrgang, C., N. Boers, M. Sonnewald, E. A. Barnes, C. Kadow, J. Staneva, and J. Saynisch-Wagner, 2021: Towards neural earth system modelling by integrating artificial intelligence in earth system science. Nature Machine Intelligence, 3(8), 667–674, https://doi.org/10.1038/s42256-021-00374-3.
Jin, E. K., and Coauthors, 2008: Current status of ENSO prediction skill in coupled ocean—atmosphere models. Climate Dyn., 31(6), 647–664, https://doi.org/10.1007/s00382-008-0397-3.
Latif, M., and Coauthors, 1998: A review of the predictability and prediction of ENSO. J. Geophys. Res.: Oceans, 103(C7), 14375–14393, https://doi.org/10.1029/97JC03413.
LeCun, Y., and Y. Bengio, 1995: Convolutional networks for images, speech, and time series. The Handbook of Brain Theory and Neural Networks, Cambridge, MA, United States, MIT Press, 255–258.
McCreary, J. P. Jr., and D. L. T. Anderson, 1991: An overview of coupled ocean-atmosphere models of El Niño and the Southern Oscillation. J. Geophys. Res.: Oceans, 96(S01), 3125–3150, https://doi.org/10.1029/90JC01979.
McPhaden, M. J., S. E. Zebiak, and M. H. Glantz, 2006: ENSO as an integrating concept in earth science. Science, 314(5806), 1740–1745, https://doi.org/10.1126/science.1132588.
Mu, B., B. Qin, and S. J. Yuan, 2021: ENSO-ASC 1.0.0: ENSO deep learning forecast model with a multivariate air—sea coupler. Geoscientific Model Development, 14, 6977–6999, https://doi.org/10.5194/gmd-14-6977-2021.
Nooteboom, P. D., Q. Y. Feng, C. López, E. Hernández-García, and H. A. Dijkstra, 2018: Using network theory and machine learning to predict El Niño. Earth System Dynamics, 9(3), 969–983, https://doi.org/10.5194/esd-9-969-2018.
Philander, S. G., 1999: A review of tropical ocean—atmosphere interactions. Tellus B, 51(1), 71–90, https://doi.org/10.3402/tellusb.v51i1.16261.
Pratt, L. Y., J. Mostow, and C. A. Kamm, 1991: Direct transfer of learned information among neural networks. Proc. 9th National Conf. on Artificial Intelligence, Anaheim, California, AAAI Press, 584–589.
Reichstein, M., G. Camps-Valls, B. Stevens, M. Jung, J. Denzler, N. Carvalhais, and Prabhat, 2019: Deep learning and process understanding for data-driven Earth system science. Nature, 566(7743), 195–204, https://doi.org/10.1038/s41586-019-0912-1.
Scarselli, F., and A. C. Tsoi, 1998: Universal approximation using feedforward neural networks: A survey of some existing methods, and some new results. Neural Networks, 11(1), 15–37, https://doi.org/10.1016/S0893-6080(97)00097-X.
Tang, Y., and W. Hsieh, 2002: Hybrid coupled models of the tropical Pacific—II ENSO prediction. Climate Dyn., 19(3), 343–353, https://doi.org/10.1007/s00382-002-0231-2.
Tang, Y. M., and Coauthors, 2018: Progress in ENSO prediction and predictability study. National Science Review, 5(6), 826–839, https://doi.org/10.1093/nsr/nwy105.
Tangang, F. T., W. W. Hsieh, and B. Tang, 1997: Forecasting the equatorial Pacific sea surface temperatures by neural network models. Climate Dyn., 13(2), 135–147, https://doi.org/10.1007/s003820050156.
Tippett, M. K., A. G. Barnston, and S. H. Li, 2012: Performance of recent multimodel ENSO forecasts. J. Appl. Meteorol. Climatol., 51(3), 637–654, https://doi.org/10.1175/JAMC-D-11-093.1.
Varotsos, C. A., C. G. Tzanis, and N. V. Sarlis, 2016: On the progress of the 2015–2016 El Niño event. Atmospheric Chemistry and Physics, 16(4), 2007–2011, https://doi.org/10.5194/acp-16-2007-2016.
Von Storch, H., T. Bruns, I. Fischer-Bruns, and K. Hasselmann, 1988: Principal oscillation pattern analysis of the 30- to 60-day oscillation in general circulation model equatorial troposphere. J. Geophys. Res.: Atmos., 93(D9), 11022–11036, https://doi.org/10.1029/JD093iD09p11022.
Wang, C. Z., 2019: Three-ocean interactions and climate variability: A review and perspective. Climate Dyn., 53(7), 5119–5136, https://doi.org/10.1007/s00382-019-04930-x.
Wang, S., L. Mu, and D. R. Liu, 2021: A hybrid approach for El Niño prediction based on Empirical Mode Decomposition and convolutional LSTM Encoder-Decoder. Computers & Geosciences, 149, 104695, https://doi.org/10.1016/j.cageo.2021.104695.
Wu, A. M., W. W. Hsieh, and B. Y. Tang, 2006: Neural network forecasts of the tropical Pacific sea surface temperatures. Neural Networks, 19(2), 145–154, https://doi.org/10.1016/j.neunet.2006.01.004.
Xu, G. J., and Coauthors, 2019: Oceanic eddy identification using an AI scheme. Remote Sensing, 11(11), 1349, https://doi.org/10.3390/rs11111349.
Xu, J. S., 1990: Analysis and prediction of the El Niño Southern Oscillation phenomenon using principal oscillation pattern analysis. PhD dissertation, University of Hamburg.
Yan, J. N., L. Mu, L. Z. Wang, R. Ranjan, and A. Y. Zomaya, 2020: Temporal convolutional networks for the advance prediction of ENSO. Scientific Reports, 10(1), 8055, https://doi.org/10.1038/s41598-020-65070-5.
You, Y. J., and J. C. Furtado, 2018: The South Pacific meridional mode and its role in tropical Pacific climate variability. J. Climate, 31(24), 10141–10163, https://doi.org/10.1175/JCLI-D-17-0860.1.
Zebiak, S. E., and M. A. Cane, 1987: A model El Niño—Southern oscillation. Mon. Wea. Rev., 115(10), 2262–2278, https://doi.org/10.1175/1520-0493(1987)115<2262:AMENO>2.0.CO;2.
Zhang, R.-H., and C. Gao, 2016: The IOCAS intermediate coupled model (IOCAS ICM) and its real-time predictions of the 2015–2016 El Niño event. Science Bulletin, 61(13), 1061–1070, https://doi.org/10.1007/s11434-016-1064-4.
Zhang, R.-H., L. M. Rothstein, and A. J. Busalacchi, 1998: Origin of upper-ocean warming and El Niño change on decadal scales in the tropical Pacific Ocean. Nature, 391(6670), 879–883, https://doi.org/10.1038/36081.
Zhang, R.-H., S. E. Zebiak, R. Kleeman, and N. Keenlyside, 2005: Retrospective El Niño forecasts using an improved intermediate coupled model. Mon. Wea. Rev., 133(9), 2777–2802, https://doi.org/10.1175/MWR3000.1.
Zhang, R.-H., and Coauthors, 2020: A review of progress in coupled ocean-atmosphere model developments for ENSO studies in China. Journal of Oceanology and Limnology, 38(4), 930–961, https://doi.org/10.1007/s00343-020-0157-8.
Zhang, S. W., H. Wang, H. Jiang, and W. T. Ma, 2021: Evaluation of ENSO prediction skill changes since 2000 based on multimodel hindcasts. Atmosphere, 12(3), 365, https://doi.org/10.3390/atmos12030365.
Zheng, G., X. F. Li, R.-H. Zhang, and B. Liu, 2020: Purely satellite data-driven deep learning forecast of complicated tropical instability waves. Science Advances, 6(29), eaba1482, https://doi.org/10.1126/sciadv.aba1482.
Acknowledgements
The authors wish to thank the two anonymous reviewers for their comments that helped to improve the original manuscript. The authors thank Dr. Yuchao ZHU for his help in providing us with CMIP6 products. This research is supported by the Strategic Priority Research Program of the Chinese Academy of Sciences (Grant No. XDA19060102), and the National Natural Science Foundation of China [NSFC; Grant Nos. 41690122(41690120), and 42030410].
Author information
Authors and Affiliations
Corresponding author
Additional information
Article Highlights
• A novel hybrid neural network model, named as POP-Net, is developed by combining the POP analysis procedure with CNN-LSTM algorithm for ENSO prediction.
• The POP-Net produces skillful ENSO predictions for lead times of up to 17 months and alleviates the spring predictability barrier.
• Value-added artificial neural networks are demonstrated for ENSO prediction improvements by including process-oriented POP analyses and for applications.
Rights and permissions
About this article
Cite this article
Zhou, L., Zhang, RH. A Hybrid Neural Network Model for ENSO Prediction in Combination with Principal Oscillation Pattern Analyses. Adv. Atmos. Sci. 39, 889–902 (2022). https://doi.org/10.1007/s00376-021-1368-4
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00376-021-1368-4