Abstract
El Niño-Southern Oscillation (ENSO) phenomenon is the strongest signal in the interannual time scale of global climate, and has a significant impact on the global short-term climate (temperature, precipitation, etc.). Every year, researchers around the world would predict ENSO for the coming year, and have been studied new forecasting methods all the time, including numerical methods, statistical methods and deep learning methods. The existing deep learning methods are only for the ENSO index or single-point meteorological elements forecasting and rarely involve forecasting of specific regions. In this paper, we formulate a deep learning ENSO forecasting model (DLENSO) to predict ENSO through predicting Sea Surface Temperature (SST) in the tropical Pacific region directly. DLENSO is a sequence to sequence model whose encoder and decoder are both multilayered Convolutional Long Short-Term Memory (ConvLSTM), the input and prediction target of DLENSO are both spatiotemporal sequences. We explore the optimal setting of this model by experiments and report the accuracy on Niño3.4 region to confirm the effectiveness of the proposed method. Moreover, it can be concluded that DLENSO is superior to the LSTM model and deterministic forecast model, and almost equivalent to the ensemble-mean forecast model in the medium and long-term (4–12 months ahead) forecast. This model will pave a new way of predicting ENSO using deep learning technology.
Keywords
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bjerknes, J.: Atmospheric teleconnections from the equatorial Pacific. Mon. Weather Rev. 97(3), 163–172 (1968)
Iizumi, T., Luo, J.J., Challinor, A.J., et al.: Impacts of El Niño Southern Oscillation on the global yields of major crops. Nat. Commun. 5, 3712 (2014)
Shuai, J., Zhao, Z., Sun, D.Z., et al.: ENSO, climate variability and crop yields in China. Clim. Res. 58(2), 133–148 (2013)
Zhai, P., Yu, R., Guo, Y., et al.: The strong El Niño of 2015/16 and its dominant impacts on global and China’s climate. Meteorol. Res. 30, 283 (2016)
Goddard, L., Mason, S.J., Zebiak, S.E., Ropelewski, C.F., Basher, R., Cane, M.A.: Current approaches to seasonal to interannual climate predictions. Int. J. Climatol. 12(9), 1111–1152 (2001)
Yuzhu, W., Jinrong, J., et al.: A scalable parallel algorithm for atmospheric general circulation models on a multi-core cluster. Future Gener. Comput. Syst. 72, 1–10 (2017)
Jin, E.K., Kinter, J.L., Wang, B., et al.: Current status of ENSO prediction skill in coupled ocean-atmosphere models. Clim. Dyn. 31(6), 647–664 (2008)
Jiang, J., Wang, T., Chi, X., et al.: SC-ESAP: a parallel application platform for earth system model. Procedia Comput. Sci. 80, 1612–1623 (2016)
Aguilarmartinez, S., Hsieh, W.W.: Forecasts of tropical Pacific sea surface temperatures by neural networks and support vector regression. Int. J. Oceanogr. 2009, 1687–9406 (2009)
Zhang, Q., Wang, H., Dong, J., et al.: Prediction of sea surface temperature using long short-term memory. IEEE Geosci. Remote Sens. Lett. 14, 1745–1749 (2017)
Feng, Q.Y., Vasile, R., Segond, M., et al.: ClimateLearn: a machine-learning approach for climate prediction using network measures. Geosci. Model Dev. Discuss. 1–18 (2016)
Nooteboom, P.D.: Using network theory and machine learning to predict El Niño. Earth Syst. Dyn. 9, 969–983 (2017)
Zheng, F., Zhu, J., et al.: Improved ensemble-mean forecasting of ENSO events by a zero-mean stochastic error model of an intermediate coupled model. Clim. Dyn. 47(12), 3901–3915 (2016)
Shi, X., Chen, Z., Wang, H., et al.: Convolutional LSTM network: a machine learning approach for precipitation nowcasting, vol. 9199, pp. 802–810 (2015)
Hochreiter, S., Schmidhuber, J.: Long Short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Graves, A.: Supervised sequence labelling. In: Kawakami, K. (ed.) Supervised Sequence Labelling with Recurrent Neural Networks. Studies in Computational Intelligence, vol. 385, pp. 1735–1780. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-24797-2_2
Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks (2014)
Plank, B., Søgaard, A., Goldberg, Y.: Multilingual part-of-speech tagging with bidirectional long short-term memory models and auxiliary loss (2014)
NOAA ESRL: NOAA OI SST V2 high resolution dataset. https://www.esrl.noaa.gov/psd/data/gridded/data.noaa.oisst.v2.highres.html
Saha, S., et al.: NCEP climate forecast system reanalysis (CFSR) 6-hourly products, January 1979 to December 2010. Research Data Archive at the National Center for Atmospheric Research, Computational and Information Systems Laboratory, Boulder, CO (2010)
Bengio, S., Vinyals, O., Jaitly, N., et al.: Scheduled sampling for sequence prediction with recurrent neural networks. In: Proceedings of the International Conference on Neural Information Processing Systems (2015)
Luo, J.J., Masson, S., Behera, S.K., et al.: Extended ENSO predictions using a fully coupled ocean-atmosphere model. J. Clim. 21(1), 84–93 (2008)
Acknowledgments
The research is funded by the National Key Research and Development Program of China (No. 2016YFB0200800), the Knowledge Innovation Program of the Chinese Academy of Sciences (No. XXH13506-402, No. XXH13506-302), Strategic Priority Research Programme (XDC01040000).
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
He, D., Lin, P., Liu, H., Ding, L., Jiang, J. (2019). DLENSO: A Deep Learning ENSO Forecasting Model. In: Nayak, A., Sharma, A. (eds) PRICAI 2019: Trends in Artificial Intelligence. PRICAI 2019. Lecture Notes in Computer Science(), vol 11671. Springer, Cham. https://doi.org/10.1007/978-3-030-29911-8_2
Download citation
DOI: https://doi.org/10.1007/978-3-030-29911-8_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-29910-1
Online ISBN: 978-3-030-29911-8
eBook Packages: Computer ScienceComputer Science (R0)