Abstract
Climate disasters such as floods and droughts often cause significant losses to human life, national economy, and public safety. The El Niño Southern Oscillation (ENSO) is one of the most important interannual climate signals in tropical regions, and has a global impact on atmospheric circulation and precipitation. Accurate ENSO predictions can help prevent related climate disasters. Recently, convolutional neural networks (CNNs) have shown the best techniques for ENSO prediction. However, it is difficult for convolutional kernels to capture the long-distance features of ENSO due to the locality of convolution itself. We regard ENSO prediction as a spatiotemporal series prediction problem, and propose an ENSO non-stationary spatiotemporal prediction deep learning model based on a new attention mechanism and a recurrent neural network, called ENSOMIM. The model expands the Receptive field of the network to achieve the learning space characteristics of local and global interaction, and uses high-order nonlinear spatiotemporal neural networks to encode long-term time series features. In order to adequate training the model, we also add historical simulation data to the training set and conduct transfer learning. The experimental results indicate that ENSOMIM is more suitable for large-scale and long-term prediction. During the testing period from 2015 to 2023, ENSOMIM's Niño3.4 index’s all-season correlation skill improved by 11% compared to classical CNNs, and the root mean square error decreased by 29%. It can provide effective predictions for a lead time of up to 20 months. Therefore, ENSOMIM can serve as a powerful tool for predicting ENSO events.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
McPhaden, M.J., Zebiak, S.E.: ENSO as an integrating concept in earth science. Science 314(5806), 1740–1745 (2006)
Bjerknes, J.: Atmospheric teleconnections from the equatorial Pacific. Mon. Weather Rev. 97(3), 163–172 (1969)
Lin, J., Qian, T.: Switch between el nino and la nina is caused by subsurface ocean waves likely driven by lunar tidal forcing. Sci. Rep. 9(1), 1–10 (2019)
Siegert, F., Ruecker, G.: Increased damage from fires in logged forests during droughts caused by El Nino. Nature 414(6862), 437–440 (2001)
Ward, P.J., Jongman, B.: Strong influence of El Niño Southern Oscillation on flood risk around the world. Proc. Natl. Acad. Sci. 111(44), 15659–15664 (2014)
Tang, Y., Zhang, R.H.: Progress in ENSO prediction and predictability study. Natl. Sci. Rev. 5(6), 826–839 (2018)
Masson, S., Terray, P.: Impact of intra-daily SST variability on ENSO characteristics in a coupled model. Clim. Dyn. 39(3), 681–707 (2012)
Alexander, M.A., Matrosova, L.: Forecasting pacific SSTs: linear inverse model predictions of the PDO. J. Clim. 21(2), 385–402 (2008). https://doi.org/10.1175/2007JCLI1849.1
Barnston, A.G., Van, den, Dool, H.M., Zebiak, S.E.: Long-lead seasonal forecasts—where do we stand. Bull. Am. Meteorol. Soc. 75(11), 2097–2114 (1994)
Xue, Y., Leetmaa, A.: Forecasts of tropical Pacific SST and sea level using a Markov model. Geophys. 27(2), 2701–2704 (2000)
Hirst, A.C.: Unstable and damped equatorial modes in simple coupled ocean-atmosphere models. J. Atmos. Sci. 43(6), 606–632 (1986)
Zebiak, S.E., Cane, M.A.: A model el niño–southern oscillation. Mon. Weather Rev. 115(10), 2262–2278 (1987)
Barnett, T.P., Graham, N.: ENSO and ENSO-related predictability. Part I: prediction of equatorial Pacific sea surface temperature with a hybrid coupled ocean–atmosphere model. J. Clim. 6(8), 1545–1566 (1993)
Luo, J.J., Yuan, C.: Current status of intraseasonal–seasonal-to-interannual prediction of the Indo-Pacific climate. Indo-Pacific Climate variability and predictability. pp. 63–107 (2016)
Jin, E.K., Kinter, J.L.: Current status of ENSO prediction skill in coupled ocean–atmosphere models. Clim. Dyn. 31(6), 647–664 (2008)
Ren, F.M., Yuan, Y.: Review of progress of ENSO studies in the past three decades. Adv. Meteorol. Sci. Technol. 2(3), 17–24 (2012)
Clarke, A.J.: El Niño physics and El Niño predictability. Annu. 6(1), 79–99 (2014)
Fang, X., Xie, R.: A brief review of ENSO theories and prediction. Sci. China Earth Sci. 63, 476–491 (2020)
Petersik, P.J., Dijkstra, H.A.: Probabilistic forecasting of El Niño using neural network models. Geophys. Res. Lett. 47(6), e2019GL086423 (2020)
Mahesh, A., Evans, M., Jain, G.: Forecasting El Niño with convolutional and recurrent neural networks. In: 33rd Conference on Neural Information Processing Systems (NIPS 2019), pp. 8–14. Vancouver, Canada (2019)
Broni-Bedaiko: El Niño-southern oscillation forecasting using complex networks analysis of LSTM neural networks. Life Robot. 24(4), 445–451 (2019)
Yuan, Y., Lin, L., Huo, L.Z.: Using an attention-based LSTM encoder–decoder network for near real-time disturbance detection. IEEE J. Select. Top. Appl. Earth Observ. Remote Sens. 13, 1819–1832 (2020)
Kim, J., Kwon, M., Kim, S.D.: Spatiotemporal neural network with attention mechanism for El Niño forecasts. Sci. Rep. 12(1), 7204 (2022)
Gupta, M., Kodamana, H.: Prediction of ENSO beyond spring predictability barrier using deep convolutional LSTM networks. Remote Sense. 19, 1–5 (2020)
Yan, J., Mu, L., Wang, L.: Temporal convolutional networks for the advance prediction of ENSO. Sci. Rep. 10(1), 1–15 (2020)
Cachay, S.R., Erickson, E.: The World as a Graph: Improving El Ni\~ no Forecasts with Graph Neural Networks. arXiv pre-print arXiv:2104.05089 (2021)
Ham, Y.G., Kim, J.H.: Deep learning for multi-year ENSO forecasts. Nature 573(7775), 568–572 (2019)
Srivastava, N., Mansimov, E., Salakhudinov, R.: Unsupervised learning of video representations using LSTMS. In: International Conference on Machine Learning, pp. 843–852. PMLR (2015)
Shi, X., Chen, Z., Wang, H.: Convolutional LSTM network: a machine learning approach for precipitation nowcasting. Adv. Neural. Inf. Process. Syst. 28(3), 802–810 (2015)
Wang, Y., Long, M., Wang, J.: Predrnn: recurrent neural net-works for predictive learning using spatiotemporal LSTMS. Adv. Neural. Inf. Process. Syst. 30(2), 879–888 (2017)
Wang, Y., Gao, Z., Long, M.: Predrnn++: Towards a resolution of the deep-in-time dilemma in spatiotemporal predictive learning. PMLR. 80(5), 5123–5132 (2018)
Wang, Y., Zhang, J., Zhu, H.: Memory in memory: a predictive neural network for learning higher-order non-stationarity from spatiotemporal dynamics. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9154–9162 (2019)
He, D., Lin, P.: Dlenso: A deep learning enso forecasting model. In: Pacific Rim International Conference on Artificial Intelligence, pp. 12–23. Springer, Cham (2019)
Hu, J., Weng, B.: Deep residual convolutional neural network combining dropout and transfer learning for ENSO forecasting. Geophys. Res. Let. 48, e2021GL093531 (2021)
Mu, B., Qin, B., Yuan, S.: ENSO-ASC 1.0. 0: ENSO deep learning forecast model with a multivariate air–sea coupler. Geoscientific Model Development. 14(11), 6977–6999 (2021)
Ye, F., Hu, J., Huang, T.Q.: Transformer for EI Niño-Southern oscillation prediction. IEEE Geosci. Remote Sens. Lett. 19, 1–5 (2021)
Hai, L.L., Wei, G.S., Jia, K.Z.: Spatiotemporal semantic decoupling network for improved ENSO forecasting. CLIVAR Exch. 81, 12–15 (2021)
Zhou, L., Zhang, R.H.: A self-attention–based neural network for three-dimensional multivariate modeling and its skillful ENSO predictions. Sci. Adv. 9(10), eadf2827 (2023)
Carton, J.A., Giese, B.S.: A reanalysis of ocean climate using Simple Ocean Data Assimilation (SODA). Mon. Weather Rev. 136(8), 2999–3017 (2008)
Tian-Jun, Z., Li-Wei, Z.O.U., Xiao-Long, C.: Commentary on the coupled model intercomparison project phase 6 (CMIP6). Adv. Clim. Chang. Res. 15(5), 445 (2019)
Saha, S., Nadiga, S., Thiaw, C.: The NCEP climate forecast system. J. Clim. 19(15), 3483–3517 (2006)
Acknowledgement
This work is supported by the National Natural Science Foundation of China (Grant No.42075007), the Open Grants of the State Key Laboratory of Severe Weather (No.2021LASW-B19), and the Open Project of Provincial Key Laboratory for Computer Information Processing Technology under Grant KJS2275, Soochow University.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Fang, W., Sha, Y., Zhang, X. (2023). Spatiotemporal Model with Attention Mechanism for ENSO Predictions. In: Iliadis, L., Papaleonidas, A., Angelov, P., Jayne, C. (eds) Artificial Neural Networks and Machine Learning – ICANN 2023. ICANN 2023. Lecture Notes in Computer Science, vol 14262. Springer, Cham. https://doi.org/10.1007/978-3-031-44201-8_30
Download citation
DOI: https://doi.org/10.1007/978-3-031-44201-8_30
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-44200-1
Online ISBN: 978-3-031-44201-8
eBook Packages: Computer ScienceComputer Science (R0)