Principal Component Analysis for SPAT PG course Joanna D. Haigh.

Slides:



Advertisements
Similar presentations
Face Recognition Sumitha Balasuriya.
Advertisements

MJO Metrics Combined EOFs using day filtered OLR, u850, and u200 averaged between 15°N-15°S Prior to computing EOFs, each equatorially-averaged.
Eigen Decomposition and Singular Value Decomposition
1 To centre or not to centre …or perhaps do it twice Ian Jolliffe Universities of Reading, Southampton, Aberdeen
Principal Component Analysis (PCA) or Empirical Orthogonal Functions (EOFs) Arnaud Czaja (SPAT Data analysis lecture Nov. 2011)
Krishna Rajan Data Dimensionality Reduction: Introduction to Principal Component Analysis Case Study: Multivariate Analysis of Chemistry-Property data.
Eigen Decomposition and Singular Value Decomposition
Noise & Data Reduction. Paired Sample t Test Data Transformation - Overview From Covariance Matrix to PCA and Dimension Reduction Fourier Analysis - Spectrum.
Image Pre-Processing Continuation… Spectral Enhancement Image Pre-Processing Continuation… Spectral Enhancement.
Covariance Matrix Applications
PCA Tomography and its application to nearby galactic nuclei João Steiner IAG - Universidade de São Paulo +R. B. Menezes, T. V. Ricci +F. Ferrari (UNIPAMPA)
Machine Learning Lecture 8 Data Processing and Representation
1er. Escuela Red ProTIC - Tandil, de Abril, 2006 Principal component analysis (PCA) is a technique that is useful for the compression and classification.
Principal Components Analysis Babak Rasolzadeh Tuesday, 5th December 2006.
An introduction to Principal Component Analysis (PCA)
Principal Component Analysis
Principal Component Analysis
Unsupervised Learning - PCA The neural approach->PCA; SVD; kernel PCA Hertz chapter 8 Presentation based on Touretzky + various additions.
What is EOF analysis? EOF = Empirical Orthogonal Function Method of finding structures (or patterns) that explain maximum variance in (e.g.) 2D (space-time)
Principal Component Analysis Principles and Application.
Principal Component Analysis. Consider a collection of points.
Computer Vision Spring ,-685 Instructor: S. Narasimhan WH 5409 T-R 10:30am – 11:50am Lecture #18.
EOF Analysis.
Principal Component Analysis. Philosophy of PCA Introduced by Pearson (1901) and Hotelling (1933) to describe the variation in a set of multivariate data.
Empirical Modeling Dongsup Kim Department of Biosystems, KAIST Fall, 2004.
Principle Component Analysis Presented by: Sabbir Ahmed Roll: FH-227.
Dimensionality Reduction: Principal Components Analysis Optional Reading: Smith, A Tutorial on Principal Components Analysis (linked to class webpage)
Principal Components Analysis (PCA). a technique for finding patterns in data of high dimension.
Chapter 2 Dimensionality Reduction. Linear Methods
Extensions of PCA and Related Tools
Computer Vision Spring ,-685 Instructor: S. Narasimhan Wean 5403 T-R 3:00pm – 4:20pm Lecture #19.
Feature extraction 1.Introduction 2.T-test 3.Signal Noise Ratio (SNR) 4.Linear Correlation Coefficient (LCC) 5.Principle component analysis (PCA) 6.Linear.
Review of Statistics and Linear Algebra Mean: Variance:
El Niño-Southern Oscillation in Tropical Column Ozone and A 3.5-year signal in Mid-Latitude Column Ozone Jingqian Wang, 1* Steven Pawson, 2 Baijun Tian,
What is it? Principal Component Analysis (PCA) is a standard tool in multivariate analysis for examining multidimensional data To reveal patterns between.
Principal Component Analysis Bamshad Mobasher DePaul University Bamshad Mobasher DePaul University.
N– variate Gaussian. Some important characteristics: 1)The pdf of n jointly Gaussian R.V.’s is completely described by means, variances and covariances.
Descriptive Statistics vs. Factor Analysis Descriptive statistics will inform on the prevalence of a phenomenon, among a given population, captured by.
Central limit theorem revisited
GEOG2021 Environmental Remote Sensing Lecture 3 Spectral Information in Remote Sensing.
AIRS Radiance and Geophysical Products: Methodology and Validation Mitch Goldberg, Larry McMillin NOAA/NESDIS Walter Wolf, Lihang Zhou, Yanni Qu and M.
Principal Components Analysis. Principal Components Analysis (PCA) A multivariate technique with the central aim of reducing the dimensionality of a multivariate.
Carlos H. R. Lima - Depto. of Civil and Environmental Engineering, University of Brasilia. Brazil. Upmanu Lall - Water Center, Columbia.
CHAPTER 10 Principal Components BAND TRANSFORMATIONS A. Dermanis.
CpSc 881: Machine Learning PCA and MDS. 2 Copy Right Notice Most slides in this presentation are adopted from slides of text book and various sources.
Christina Bonfanti University of Miami- RSMAS MPO 524.
Principal Component Analysis Zelin Jia Shengbin Lin 10/20/2015.
Feature Extraction 主講人:虞台文. Content Principal Component Analysis (PCA) PCA Calculation — for Fewer-Sample Case Factor Analysis Fisher’s Linear Discriminant.
3 “Products” of Principle Component Analysis
Feature Extraction 主講人:虞台文.
Oceanography 569 Oceanographic Data Analysis Laboratory Kathie Kelly Applied Physics Laboratory 515 Ben Hall IR Bldg class web site: faculty.washington.edu/kellyapl/classes/ocean569_.
Central limit theorem revisited Throw a dice twelve times- the distribution of values is not Gaussian Dice Value Number Of Occurrences.
Principal Components Analysis ( PCA)
Central limit theorem - go to web applet. Correlation maps vs. regression maps PNA is a time series of fluctuations in 500 mb heights PNA = 0.25 *
Unsupervised Learning II Feature Extraction
PRINCIPAL COMPONENT ANALYSIS(PCA) EOFs and Principle Components; Selection Rules LECTURE 8 Supplementary Readings: Wilks, chapters 9.
GEOG2021 Environmental Remote Sensing
Principal Component Analysis (PCA)
Principal Component Analysis
9.3 Filtered delay embeddings
Principal Component Analysis (PCA)
Machine Learning Dimensionality Reduction
Principal Component Analysis
Principal Component Analysis
PCA is “an orthogonal linear transformation that transfers the data to a new coordinate system such that the greatest variance by any projection of the.
Descriptive Statistics vs. Factor Analysis
Recitation: SVD and dimensionality reduction
X.1 Principal component analysis
Spectral Transformation
Principal Component Analysis
Presentation transcript:

Principal Component Analysis for SPAT PG course Joanna D. Haigh

PCA also known as… Empirical Orthogonal Function (EOF) Analysis Singular Value Decomposition Hotelling Transform Karhunen-Loève Transform 11 Nov 2013

Purpose/applications To identify internal structure in a dataset (e.g. “modes of variability”) Data compression – by identifying redundancy, reducing dimensionality Noise reduction Feature identification, classification…. 11 Nov 2013

Basic approach Data measured as function of two variables E.g. surface pressure (space, time) If measurements at two points in space are highly correlated in time then we only need one measure (not two) as a function of time to identify their behaviour. How many measures we need overall depends on correlations between each point and every other. 11 Nov 2013

Correlations 11 Nov 2013 value at point 1 value at point 2 measurements at point 1 and point 2 highly correlated main (average) signal is measure in direction of PC1 deviations (the interesting bit?) are in PC2 PC1 PC2 to calculate PCs we need to rotate axes with M points just rotate in M dimensions 1 2

11 Nov 2013 Approach E.g. data measured N times at M spatial points In M-dimensional space i.Find axis of greatest correlation, i.e. main variability, this is PC1. ii.Find axis orthogonal to this of next highest variability, this is PC2. iii.Continue until M new axes, i.e. M PCs. Each PC is composed of a weighted average of the original axes. The weightings are the EOFs.

Concept Often it is possible to identify a particular mode/feature with an EOF. Each PC indicates the variation with time (in our example) of the mode identified with its EOF. Once EOFs established can project other datasets (e.g. different time periods) onto them to compare behaviours. 11 Nov 2013

ENSO as EOF1 of SST data EOF1 of tropical Pacific SSTs: 576 monthly anomalies Jan Dec 1997 EOF1 explains 45% of the total SST variance over this domain. 11 Nov

Maths Calculate MxM covariance matrix Find eigenvectors and eigenvalues EOFs are the M eigenvectors, ranked in order of decreasing eigenvalue Eigenvalues give measure of variance PCs from decomposition of data onto EOFs. 11 Nov 2013

Examples of applications 11 Nov 2013 ApplicationMNVisualise dataEOFs: weightings of PCs MeteorologyspacetimeTime series at each place (or map at each time) places (maps) Time series of EOFs maps Earth obs (e.g. land cover) spectral bands spaceMap in each wavelength band bandsMaps of band combos Earth obs (e.g. cloud) caseswave- length Spectrum for each case casesSpectra of case combos Polarity of IMF Solar longitude timeIMF polarity f(longitude) at each time longitudesTime series of lon. distbn

High cloud E. Asia Kang et al (1997) 11 Nov 2013

Southern Annular Mode geopotential height of 1000hPa surface 11 Nov 2013

Examples of applications 11 Nov 2013 ApplicationMNVisualise dataEOFs: weightings of PCs MeteorologyspacetimeTime series at each place (or map at each time) places (maps) Time series of EOFs maps Earth obs (e.g. land cover) spectral bands spaceMap in each wavelength band bandsMaps of band combos Earth obs (e.g. cloud) caseswave- length Spectrum for each case casesSpectra of case combos Polarity of IMF Solar longitude timeIMF polarity f(longitude) at each time longitudesTime series of lon. distbn

Landsat Thematic Mapper ( Wageningen) 11 Nov µm

example of TM EOFs (unnormalised) [NB not for Wageningen images] 11 Nov 2013 µm eigenvalues: EOF:

Examples of applications 11 Nov 2013 ApplicationMNVisualise dataEOFs: weightings of PCs MeteorologyspacetimeTime series at each place (or map at each time) places (maps) Time series of EOFs maps Earth obs (e.g. land cover) spectral bands spaceMap in each wavelength band bandsMaps of band combos Earth obs (e.g. cloud) caseswave- length Spectrum for each case casesSpectra of case combos Polarity of IMF Solar longitude timeIMF polarity f(longitude) at each time longitudesTime series of lon. distbn

Modelled IR spectra of cirrus cloud Bantges et al (1999) 11 Nov 2013

PC0: Average PC1: Ice water path PC2: Effective radius PC3: Aspect ratio Bantges et al (1999) 11 Nov 2013

Examples of applications 11 Nov 2013 ApplicationMNVisualise dataEOFs: weightings of PCs MeteorologyspacetimeTime series at each place (or map at each time) places (maps) Time series of EOFs maps Earth obs (e.g. land cover) spectral bands spaceMap in each wavelength band bandsMaps of band combos Earth obs (e.g. cloud) caseswave- length Spectrum for each case casesSpectra of case combos Polarity of IMF Solar longitude timeIMF polarity f(longitude) at each time longitudesTime series of lon. distbn

Polarity of Interplanetary Magnetic Field 11 Nov 2013 Cadavid et al 2007

Maths – a little more detail Represent data by MxN matrix D MxM covariance matrix is C = (D – D)(D – D) T Calculate i=1,M eigenvalues λ i & eigenvectors v i EOFs in MxM matrix of eigenvectors E MxN matrix of PCs P = E T D NB can rewrite D = (E T ) -1 P = E P (E Hermitian) i.e. PCs give weighting of EOFs in data 11 Nov 2013

Data reduction/noise removal Higher order PCs are composed of lowest correlations so uncorrelated noise lies in these. Can reconstruct data omitting higher order EOFs to reduce noise. Can reduce data by keeping only PCs of lowest order EOFs. 11 Nov 2013

Books R W Priesendorfer 1988 PCA in meteorology and oceanography Elsevier I T Jolliffe 2002 Principal component analysis Springer 11 Nov 2013