A neural network (NN) model has been used by our group to predict the SST anomalies in the Nino3.4 region in the equatorial Pacific (Tang et al. 2000). By version 3.1, the NN model has been extended to forecast the SST anomalies over the whole tropical Pacific. In version 3.2, the subsurface temperature anomalies in the tropical Pacific ocean were included as predictors. In this current version (version 3.3), we have removed the subsurface temperature anomalies as predictors, since their record is relatively short (available only since 1980), and they are not always available on time for our monthly forecasts. We have, however, introduced a Bayesian NN in this latest version. See Wu et al. (2006) for details on this latest version.
The data used in this forecast came from two datasets: (a) the monthly sea level pressure (SLP) on 2.5° × 2.5° grids from the NCEP/NCAR reanalysis (Kalnay et al. 1996; downloadable from ftp.cdc.noaa.gov/Datasets/ncep.reanalysis.derived/surface); (b) the monthly extended reconstructed sea surface temperature on 2° × 2° grids (ERSST version 2; Smith and Reynolds 2004; downloadable from ftp.ncdc.noaa.gov/pub/data/ersst-v2).
Bayesian regularization was used in the NN training, where the optimal weight penalty parameter in the cost function was estimated by a Bayesian approach (Mackay, 1992), as coded by the program 'trainbr' in the MATLAB Neural Network toolbox. For more information on Bayesian NN, see also the books by Bishop (1995) and MacKay (2003).References: