A spatiotemporal 3D convolutional neural network model for ENSO predictions: A test case for the 2020/21 La Niña conditions

Bjerknes, 1969, Atmospheric teleconnections from the equatorial Pacific, Mon. Wea. Rev., 97, 163, 10.1175/1520-0493(1969)097<0163:ATFTEP>2.3.CO;2 Castro, 2021, STConvS2S: spatiotemporal convolutional sequence to sequence network for weather forecasting, Neurocomputing, 426, 285, 10.1016/j.neucom.2020.09.060 Chen, 2022, A multiscale model for El Niño complexity, NPJ Clim. Atmos. Sci., 5, 285, 10.1038/s41612-022-00241-x Chen, N., and Fang, X. 2022. A simple multiscale intermediate coupled stochastic model for El Niño diversity and complexity. doi:10.48550/arXiv.2206.06649. Eyring, 2016, Overview of the coupled model intercomparison project phase 6 (CMIP6) experimental design and organization, Geosci. Model Dev., 9, 1937, 10.5194/gmd-9-1937-2016 Fang, 2018, A three-region conceptual model for central pacific El Niño including zonal advective feedback, J. Clim., 31, 4965, 10.1175/JCLI-D-17-0633.1 Fang, 2023, Will the historic southeasterly wind over the equatorial pacific in March 2022 trigger a third-year la Niña event?, Adv. Atmos. Sci., 40, 6, 10.1007/s00376-022-2147-6 Fang, X., and Chen, N. 2022. Quantifying the predictability of ENSO complexity using a statistically accurate multiscale stochastic model and information theory. doi:10.48550/arXiv.2203.02657 Gao, 2016, Testing four dimensional variational data assimilation method using an improved intermediate coupled model for ENSO analysis and prediction, Adv. Atmos. Sci., 33, 875, 10.1007/s00376-016-5249-1 Gao, 2016, The roles of atmospheric wind and entrained water temperature (Te) in the second-year cooling of the 2010–12 La Niña event, Clim. Dyn., 48, 597 Gao, 2022, The 2020–2021 prolonged La Niña evolution in the tropical Pacific, Sci. China-Earth Sci., 65, 2248, 10.1007/s11430-022-9985-4 Ham, 2019, Deep learning for multi-year ENSO forecasts, Nature, 573, 568, 10.1038/s41586-019-1559-7 Hasan, 2022, The influence of tropical basin interactions on the 2020–2022 double-dip La Niña, Front. Clim., 4, 1001174, 10.3389/fclim.2022.1001174 Kingma, D. P., and J. Ba. 2014. Adam: a method for stochastic optimization. doi:10.48550/arXiv.1412.6980. McCreary, 1981, A linear stratified ocean model of the equatorial undercurrent, Philosoph. Trans. R. Soc. Lond. Series A, Math. Phys. Sci., 298, 603 Mu, 2021, ENSO-ASC 1.0.0: ENSO deep learning forecast model with a multivariate air–sea coupler, Geosci. Model Dev., 14, 6977, 10.5194/gmd-14-6977-2021 Song, 2022, The roles of off-equatorial subsurface cold-water incursions in triggering the second-year cooling of the la Niña event in 2021, J. Marine Sci. Eng., 10, 1667, 10.3390/jmse10111667 Tang, 2018, Progress in ENSO prediction and predictability study, Nat. Sci. Rev., 5, 826, 10.1093/nsr/nwy105 Timmermann, 2018, El Niño-Southern Oscillation complexity, Nature, 559, 535, 10.1038/s41586-018-0252-6 Zhang, 2016, The IOCAS intermediate coupled model (IOCAS ICM) and its real-time predictions of the 2015–2016 El Niño event, Sci. Bull., 61, 1061, 10.1007/s11434-016-1064-4 Zhang, 2020, A review of progress in coupled ocean-atmosphere model developments for ENSO studies in China, J. Oceanol. Limnol., 38, 930, 10.1007/s00343-020-0157-8 Zhang, 2022, Recent ENSO evolution and its real-time prediction challenges, Nat. Sci. Rev., 9, nwac052, 10.1093/nsr/nwac052 Zhang, 1998, Origin of upper-ocean warming and El Niño change on decadal scales in the tropical Pacific Ocean, Nature, 391, 879, 10.1038/36081 Zhang, 2005, An empirical parameterization of subsurface entrainment temperature for improved SST anomaly simulations in an intermediate ocean model, J. Clim., 18, 350, 10.1175/JCLI-3271.1 Zhang, 2003, A new intermediate coupled model for El Niño simulation and prediction, Geophys. Res. Lett., 30, 10.1029/2003GL018010 Zhang, 2005, Retrospective El Niño forecasts using an improved intermediate coupled model, Mon. Wea. Rev., 133, 2777, 10.1175/MWR3000.1 Zheng, 2020, Purely satellite data-driven deep learning forecast of complicated tropical instability waves, Sci. Adv., 6, eaba1482, 10.1126/sciadv.aba1482 Zhou, 2022, A Hybrid Neural Network model for ENSO prediction in combination with principal oscillation pattern analyses, Adv. Atmos. Sci., 39, 889, 10.1007/s00376-021-1368-4 Zhu, 2022, Physics-informed deep-learning parameterization of ocean vertical mixing improves climate simulations, Nat. Sci. Rev., 9, nwac044, 10.1093/nsr/nwac044