Skill Comparisons between Neural Networks and Canonical Correlation Analysis in Predicting the Equatorial Pacific Sea Surface Temperatures

Abstract

Among the statistical methods used for seasonal climate prediction, canonical correlation analysis (CCA), a more sophisticated version of the linear regression (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.\nIn this study, an objective comparison between the three methods (CCA, LR, and NN) in predicting the equatorial Pacific sea surface temperatures (in regions Niño1+2, Niño3, Niño3.4, and Niño4) was made. The skill of NN was found to be comparable to that of LR and CCA. A cross-validated t test showed 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 difference between the nonlinear NN method and the linear methods suggests that at the seasonal timescale the equatorial Pacific dynamics is basically linear. Copyright 2000 American Meteorological Society (AMS). Permission\nto use figures, tables, and brief excerpts from this work in scientific and educational\nworks is hereby granted provided that the source is acknowledged. Any use of material in\nthis work that is determined to be “fair use” under Section 107 of the U.S. Copyright Act\nor that satisfies the conditions specified in Section 108 of the U.S. Copyright Act (17\nUSC §108, as revised by P.L. 94-553) does not require the AMS’s permission.\nRepublication, systematic reproduction, posting in electronic form, such as on a web site\nor in a searchable database, or other uses of this material, except as exempted by the\nabove statement, requires written permission or a license from the AMS. Additional\ndetails are provided in the AMS Copyright Policy, available on the AMS Web site\nlocated at (http://www.ametsoc.org/) or from the AMS at 617-227-2425 or\[e-mail].