The shortcomings of nonlinear principal component analysis in identifying circulation regimes

被引:39
作者
Christiansen, B [1 ]
机构
[1] Danish Meteorol Inst, Div Climate Res, DK-2100 Copenhagen, Denmark
关键词
D O I
10.1175/JCLI3569.1
中图分类号
P4 [大气科学(气象学)];
学科分类号
0706 ; 070601 ;
摘要
Recent studies of regime behavior in the extratropical variability have been based on a nonlinear extension to principal component analysis. Multimodality has been identified in the nonlinear principal component, and the multimodality has been interpreted as evidence for the existence of multiple circulation regimes. Here, multimodality is shown to be abundant in nonlinear principal component analysis when applied to sufficiently isotropic data even if these data are inherently unimodal. It is recommended that the nonlinear principal component analysis should not be used for detection of multimodality and regime behavior.
引用
收藏
页码:4814 / 4823
页数:10
相关论文
共 23 条
[1]  
Christiansen B, 2002, GEOPHYS RES LETT, V29, DOI [10.1029/2002GL015208, 10.1029/2002GL016051]
[2]   Signature of recent climate change in frequencies of natural atmospheric circulation regimes [J].
Corti, S ;
Molteni, F ;
Palmer, TN .
NATURE, 1999, 398 (6730) :799-802
[3]   Representation of the quasi-biennial oscillation in the tropical stratospheric wind by nonlinear principal component analysis [J].
Hamilton, K ;
Hsieh, WW .
JOURNAL OF GEOPHYSICAL RESEARCH-ATMOSPHERES, 2002, 107 (D15) :ACL3-1
[4]   Nonlinear multivariate and time series analysis by neural network methods [J].
Hsieh, WW .
REVIEWS OF GEOPHYSICS, 2004, 42 (01) :RG10031-25
[5]   Nonlinear principal component analysis by neural networks [J].
Hsieh, WW .
TELLUS SERIES A-DYNAMIC METEOROLOGY AND OCEANOGRAPHY, 2001, 53 (05) :599-615
[6]  
Kalnay E, 1996, B AM METEOROL SOC, V77, P437, DOI 10.1175/1520-0477(1996)077<0437:TNYRP>2.0.CO
[7]  
2
[8]   NONLINEAR PRINCIPAL COMPONENT ANALYSIS USING AUTOASSOCIATIVE NEURAL NETWORKS [J].
KRAMER, MA .
AICHE JOURNAL, 1991, 37 (02) :233-243
[9]   Limitations of nonlinear PCA as performed with generic neural networks [J].
Malthouse, EC .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 1998, 9 (01) :165-173
[10]  
Monahan AH, 2000, J CLIMATE, V13, P821, DOI 10.1175/1520-0442(2000)013<0821:NPCABN>2.0.CO