Skill comparisons between neural networks and canonical correlation analysis in predicting the equatorial Pacific sea surface temperatures

Among the statistical methods used for seasonal climate prediction, canonic al correlation analysis (CCA), a more sophisticated version of the linear r egression (LR) method, is well established. Recently, neural networks (NN) have been applied to seasonal climate prediction. Unlike CCA and LR, NN is a nonlinear method, which leads to the question whether the nonlinearity of NN brings any extra prediction skill. In this study, an objective comparison between the three methods (CCA, LR, and NN) in predicting the equatorial Pacific sea surface temperatures (in r egions Nino1 + 2, Nino3, Nino3.4, and Nino4) was made. The skill of NN was found to be comparable to that of LR and CCA. A cross-validated t test show ed that the difference between NN and LR and the difference between NN and CCA were not significant at the 5% level. The lack of significant skill dif ference between the nonlinear NN method and the linear methods suggests tha t at the seasonal timescale the equatorial Pacific dynamics is basically li near.