Nonlinear Principal Component Analysis: Tropical Indo–Pacific Sea Surface Temperature and Sea Level Pressure

Abstract. Principal Component Analysis (PCA) is one of the popular statistical methods for feature extraction. The neural network model has been performed on the PCA to obtain nonlinear principal component analysis (NLPCA), which allows the extraction of nonlinear features in the dataset missed by the PCA. NLPCA is applied to the monthly Sea Surface Temperature (SST) data from the eastern tropical Atlantic Ocean (29° W–21° E, 25° S–7° N) for the period 1982–2005. The focus is on the differences between SST inter-annual variability patterns; either extracted through traditional PCA or the NLPCA methods.The first mode of NLPCA explains 45.5% of the total variance of SST anomaly compared to 42% explained by the first PCA. Results from previous studies that detected the Atlantic cold tongue (ACT) as the main mode are confirmed. It is observed that the maximum signal in the Gulf of Guinea (GOG) is located along coastal Angola. In agreement with composite analysis, NLPCA exhibits two types of ACT, referred to as weak and strong Atlantic cold tongues. These two events are not totally symmetrical. NLPCA thus explains the results given by both PCA and composite analysis. A particular area observed along the northern boundary between 13 and 5° W vanishes in the strong ACT case and reaches maximum extension to the west in the weak ACT case. It is also observed that the original SST data correlates well with NLPCA and PCA, but with a stronger correlation on ACT area for NLPCA and southwest in the case of PCA.

Download Full-text

Trend analysis of sea surface temperature and sea level pressure employing a pseudo-EMD method

2013 Proceedings of IEEE Southeastcon ◽

10.1109/secon.2013.6567384 ◽

2013 ◽

Author(s):

Sharif M. A. Bhuiyan ◽

Sherell Carey ◽

Jesmin F. Khan

Keyword(s):

Surface Temperature ◽

Sea Surface Temperature ◽

Trend Analysis ◽

Sea Level ◽

Sea Surface ◽

Sea Level Pressure ◽

Level Pressure ◽

Emd Method ◽

And Sea Level

Download Full-text

Decadal variability of northern northeast Brazil rainfall and its relation to tropical sea surface temperature and global sea level pressure anomalies

Journal of Geophysical Research Atmospheres ◽

10.1029/2004jc002429 ◽

2004 ◽

Vol 109 (C11) ◽

Cited By ~ 22

Author(s):

Mary Toshie Kayano

Keyword(s):

Surface Temperature ◽

Sea Surface Temperature ◽

Sea Level ◽

Decadal Variability ◽

Sea Surface ◽

Northeast Brazil ◽

Sea Level Pressure ◽

Level Pressure ◽

Global Sea Level ◽

Tropical Sea

Download Full-text

Estudo da Temperatura da Superfície do Mar para os Oceanos Atlântico e Pacífico Utilizando a Técnica de Análises de Componente Principal e de Agrupamento (Study of Sea Surface Temperature for the Atlantic and Pacific Oceans Using the Technique of...)

Revista Brasileira de Geografia Física ◽

10.26848/rbgf.v4i2.232728 ◽

2011 ◽

Vol 4 (2) ◽

pp. 264

Author(s):

Madson Tavares Silva ◽

Stephany C. F. Do Egito Costa ◽

Manoel Francisco Gomes Filho ◽

Daisy B. Lucena

Keyword(s):

Principal Component Analysis ◽

Cluster Analysis ◽

Surface Temperature ◽

Sea Surface Temperature ◽

Research Laboratory ◽

Principal Component ◽

Component Analysis ◽

Sea Surface ◽

Earth System ◽

System Research

Apresenta-se neste estudo a avaliação da metodologia de Análises Multivariadas: Análises em Componente Principal (ACP) e de Agrupamento (AA), aos dados de Temperatura da Superfície do Mar (TSM) para os Oceanos Atlântico (Norte (NATL), Tropical (TROP) e Sul (SATL)) e Pacifico (NIÑO1+2, NIÑO3.4, NIÑO3 e NIÑO4). Foram utilizados dados mensais de janeiro de 1950 a dezembro de 2010 de TSM obtidos na NOAA (National Oceanic and Atmospheric Administration/Earth System Research Laboratory). As regiões TROP e NIÑO4 apresentam as maiores TSM para os meses entre dezembro-julho. A região NATL apresenta no período de agosto-outubro seu maiores valores de TSM. A região NIÑo1+2 apresentou os menores valores de TSM. Os resultados da Análise em Componente Principal (ACP) identificaram maiores pesos na variação total explicada pelas duas primeiras componentes, que representam cerca de 100% da variância total dos dados de TSM. A Análise de Agrupamento (AA), pelo método Ward, permitiu o agrupamento das estações em três grupos homogêneos. Palavras - chave: Análises Multivariadas, Mudanças climáticas, Aquecimento Global. Study of Sea Surface Temperature for the Atlantic and Pacific Oceans Using the Technique of Principal Component Analysis and Cluster ABSTRACT Presented in this study was to evaluate the methodology of Multivariate Analysis: Principal Component Analysis (PCA) and cluster analysis (CA), the data of sea surface temperature (SST) for the Atlantic (North (NATL), Tropical (TROP) and South (Satler)) and Pacific (+2 NIÑO1, NIÑO3.4, and NIÑO3 NIÑO4). We used monthly data from January 1950 to December 2010 SST obtained from NOAA (National Oceanic and Atmospheric Administration / Earth System Research Laboratory). TROP and NIÑO4 regions have the highest SST for the months from December to July. NATL The region has in the period August-October SST your highest values +2 NIÑo1 The region had the lowest values of TSM. Results on Principal Component Analysis (PCA) identified higher weights in the total variation explained by the first two components, which represent about 100% of the total variance of SST. The Cluster Analysis (AA), the Ward method, allowed the grouping of stations into three homogeneous groups. Keywords: Multivariate Analysis, Climate Change, Global Warming.

Download Full-text