Deep Neural Networks for ENSO Prediction in the Niño 3.4 and Niño 1+2 Regions
Publication: World Environmental and Water Resources Congress 2023
ABSTRACT
Forecasting the El Niño-Southern Oscillation (ENSO) is one of the most challenging tasks because ENSO events show large differences in their amplitude, temporal evolution, and spatial pattern. This research discusses a deep neural network model that integrates convolutional short-term and long-term memory (ConvLSTM) to forecast the patterns of sea surface temperature that represent the evolution of ENSO over different time horizons with simultaneous space-time sequences in the Niño 3.4 and Niño 1+2 regions. Monthly gridded sea surface temperature and anomaly index data were used in El Niño regions for the period 1854–2021. In general, the methodology includes the sea surface temperature (SST) normalization of the tropical Pacific, the creation and selection of the architecture of the deep neural network model, and the training and validation. Furthermore, the forecast and evaluation of the SST and SST anomalies in space-time with the El Niño of 1982/1983 and 1997/1998 and with different time horizons for the test stage were developed. The results show a good model performance with ENSO data for El Niño 1982/1983 (training) and El Niño 1997/1998 (validation) in space and time, and with climatic indices for regions 3.4 and 1+2. The model performance was evaluated using statistical metrics of observed and forecasted data over six months in the equatorial Pacific Ocean (latitude 10°S–10°N and longitude 140°E–80°W). In general, all the metrics used to evaluate the accuracy and forecast of the model show a range from good to excellent for both El Niño regions in the six months of forecast.
Get full access to this chapter
View all available purchase options and get full access to this chapter.
REFERENCES
Bjerknes, J. (1969). Atmospheric Teleconnections from the Equatorial Pacific, Monthly Weather Review, Vol. 97, No. 2, pp. 163–172. doi:https://doi.org/10.1175/1520-0493(1969)097%3C0163:ATFTEP%3E2.3.CO;2.
Chen, R., Bloomfield, P. Y., and Fu, J. S. (2003). An evaluation of alternative forecasting methods to recreation visitation. Journal of Leisure Research, 35(4):441–454.
Chollet, F., et al. (2015). Keras Published on GitHub (https://github.com/fchollet/keras).
Glantz, M. H., Katz, R. W., and Nicholls, N. (1991). Teleconnections Linking Worldwide Climate Anomalies: Scientific Basis and Societal Impact. Cambridge: Cambridge University Press.
Hyndman, R. J. (2006). Another Look at Forecast Accuracy Metrics for Intermittent Demand. Foresight Int. J. Appl. Forecast. 43–46.
Jamieson, P., Porter, J. Y., and Wilson, D. (1991). A test of the computer simulation model ARCWHEAT1 on wheat crops grown in New Zealand. Field crops research, 27(4):337–350.
Kingma, D. P., and Lei Ba, J. (2015). A Method for Stochastic optimization. In ICLR.
Lewis, C. D. (1982). Industrial and business forecasting methods: A practical guide to exponential smoothing and curve fitting. Butterworth-Heinemann.
Li, M.-F., Tang, X.-P., Wu, W. Y., and Liu, H.-B. (2013). General models for estimating daily global solar radiation for different solar radiation zones in mainland China. Energy conversion and management, 70:139–148.
Makridakis, S. G., Wheelwright, S. C., and Hyndman, R. J. (2008). Forecasting: Methods and Applications (3rd ed.), New York: John Wiley & Sons.
Mason, S., and Goddard, L. (2001). Probabilistic precipitation anomalies associated with ENSO. Bull. Am. Meteorol. Soc. 82, 619–638.
McPhaden, M. J. (2002). El Niño and La Niña: Causes and global consequences. Encyclopedia of Global Environmental Change, Anonymous John Wiley and Sons, LTD, 353–370.
Neelin, J. D., Battisti, D. S., Hirst, A. C., Jin, F., Wakata, Y., Yamagata, T., and Zebiak, S. E. (1998). ENSO theory. J. Geophys. Res., 103, 14261–14290.
Philander, S. (1990). El Niño, La Niña, and the Southern Oscillation. Geological Magazine, 127(5):478–478.
Rasmusson, E. M., and Carpenter, T. H. (1982). Variations in tropical sea surface temperature and surface wind fields associated with the Southern Oscillation/El Niño, Mon. Wea. Rev., 110, 354–384.
Ropelewski, C. F., and Halpert, M. (1987). Global and regional scale precipitation patterns associated with the El Nino/Southern Oscillation. Mon. Wea. Rev., 110:1606–1626.
Sanders, N. R. (1997). Measuring forecast accuracy: some practical suggestions. Production and inventory management journal, 38(1):43.
Shi, X., Zhourong, C., Wang, H. Y., and Yeung, D. Y. (2015). Convolutional LSTM network: A machine learning approach for precipitation nowcasting, In Advances in neural information processing systems.
Shi, X., and Yeung, D. Y. (2018). Machine Learning for Spatiotemporal Sequence Forecasting: A Survey. arXiv preprint arXiv:1808.06865.
Trenberth, K. E. (1997). The Definition of El Niño. Bull. Amer. Meteor. Soc.78: 2771–2777. doi:10.1175/1520-0477(1997)078<2771:TDOENO>2.0.CO;2.
Trenberth, K. E., Branstator, G. W., Karoly, D., Kumar, A., Lau, N.-C. Y., and Ropelewski, C. (1998). Progress during TOGA in understanding and modeling global teleconnections associated with tropical sea surface temperatures. Journal of Geophysical Research: Oceans, 103(C7):14291–14324.
Wallace, J. M. Y., and Gutzler, D. S. (1981). Teleconnections in the geopotential height field during the Northern Hemisphere winter. Monthly Weather Review, 109(4): 784–812. doi:10.1175/1520-0493(1981)109<0784:TITGHF>2.0.CO.
WMO. (2014). El Niño/Southern Oscillation. World Meteorological Agency.
WMO. (2020). Guidance on operational practices for objective seasonal forecasting. World Meteoerological Organization.
Zeiler, M. D., Krishnan, D., Taylor, G. W., and Fergus, R. (2010). Deconvolutional Networks. In CVPR.
Information & Authors
Information
Published In
World Environmental and Water Resources Congress 2023
Pages: 307 - 316
History
Published online: May 18, 2023
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.