Neural network forecasts of the tropical Pacific sea surface temperatures

Aiming Wu, William W. Hsieh and Benyang Tang

A neural network (NN) model had been used by our group to predict the sea surface temperature anomalies (SSTA) in the Nino3.4 region in the equatorial Pacific (Tang et al, 2000). The NN model has been extended to forecast the SSTA over the entire tropical Pacific, and in the latest version 3.5 (introduced in Mar. 2010), the model used is a Bayesian NN (Wu et al. 2006). Click here to see details about this model.

Using sea level pressure and sea surface temperature data up to the end of February 2019, forecasts were made with the NN model. Ensemble-averaged forecasts for the SSTA in the Nino3.4 region at various lead times are shown in Fig.1, and the forecasted SSTA fields over the tropical Pacific are displayed in Fig.2, showing weak El Niño warm conditions in the equatorial Pacific persisting till late 2019.

Figure 1. The SSTA (in degree Celsius) in the Nino3.4 area (170ºW-120ºW, 5ºS-5ºN) predicted by the ensemble-averaged nonlinear model at 3, 6, 9 and 12 months of lead time (circles), with observations denoted by the solid line. Tick marks along the abscissa indicate the January of the given years. (The observed Nino3.4 SSTA was computed from the ERSST data, with the mean defined over 1950-2009.) (The pdf file of Fig.1 is also available).
Figure 2. SSTA (in ºC) predicted by the ensemble-averaged nonlinear model for the four consecutive seasons starting with AMJ (April-June 2019). A thick black curve is used for the zero contour. (The pdf file of Fig.2 is also available).

Data in tabular format for the Nino3.4 SSTA predicted for the next four seasons:
AMJ 2019 0.72 ºC
JAS 2019 0.80 ºC
OND 2019 0.80 ºC
JFM 2020 0.46 ºC


Reference
Tang, B., W.W. Hsieh, A.H. Monahan and F.T. Tangang, 2000. Skill comparisons between neural networks and canonical correlation analysis in predicting the equatorial Pacific sea surface temperatures. J.Climate, 13: 287-293.

Wu, A., W.W. Hsieh and B. Tang, 2006. Neural network forecasts of the tropical Pacific sea surface temperatures. Neural Networks. 19: 145-154. doi:10.1016/j.neunet.2006.01.004. (preprint in PDF).

Back to [UBC Climate Prediction Group Home Page]

The UBC Climate Prediction Group is located in the
Department of Earth, Ocean and Atmospheric Sciences, University of British Columbia, 2207 Main Mall, Vancouver, B.C. V6T 1Z4, Canada