Nonlinear multivariate and time series analysis by neural network methods

Methods in multivariate statistical analysis are essential for working with large amounts of geophysical data— data from observational arrays, from satellites or from numerical model output. In classical multivariate statistical analysis, there is a hierarchy of methods, starting with linear regression (LR) at the base, followed by principal component analysis (PCA), and finally canonical correlation analysis (CCA). A multivariate time series method, the singular spectrum analysis (SSA), has been a fruitful extension of the PCA technique. The common drawback of these classical methods is that only linear structures can be correctly extracted from the data. Since the late 1980s, neural network methods have become popular for performing nonlinear regression (NLR) and classification. More recently, neural network methods have been extended to perform nonlinear PCA (NLPCA), nonlinear CCA (NLCCA) and nonlinear SSA (NLSSA). This paper presents a unified view of the NLPCA, NLCCA and NLSSA techniques, and their applications to various datasets of the atmosphere and the ocean (especially for the El NiñoSouthern Oscillation and the stratospheric Quasi-Biennial Oscillation). These datasets reveal that the linear methods are often too simplistic to describe real-world systems — with a tendency to scatter a single oscillatory phenomenon into numerous unphysical modes or higher harmonics, which can be largely alleviated in the new nonlinear paradigm.