Component loadings correlation of each item with the principal component excel. The graphs are shown for a principal component analysis of the 150 flowers in the fisher iris data set. I have always preferred the singular form as it is compatible with factor analysis, cluster analysis, canonical correlation analysis and so on, but had no clear idea whether the singular or. Principal component analysis for alteration mapping asprs. Pdf new interpretation of principal components analysis. Commonly, seismic data processing procedures, such as stacking and prestack migration, require the ability to detect bad tracesshots and restore or replace them by interpolation, particularly when the seismic observations are noisy or there are malfunctioned components in the recording system. However, there are distinct differences between pca and efa. We use pca in a novel way to successfully make detailed effective porosity predictions in channelized sand and shale. This tutorial is designed to give the reader an understanding of principal components analysis pca. Some machine learning applications in seismic interpretation.
Sensitivity analysis and cascaded interpretation scheme. Seismic interpretation with machine learning geophysical insights. Principal components analysis is based on the correlation matrix of the variables involved, and correlations usually need a large sample size before they stabilize. Seismic data quality control and interpolation using. Principal component analysis example write up page 2 of 10 2 introduction kinnear and gray 2004, page 429 provide the following example which is suitable for principal component analysis though the sample size is completely inadequate.
Seismic interpretation techniques have always labored for acceptance across. A seismic attribute is any measurable property of seismic. A seismic attribute is any measurable property of seismic data, such as amplitude, dip, phase, frequency, and. Principal component analysis pca and selforganizing maps soms provide multiattribute analyses that have proven to be an excellent pattern recognition approach in the seismic interpretation workflow. Investigations thus far indicate the information can be reduced to 10% of the original data base size. A very important classification technique in seismic interpretation. Faults and fractures detection in 2d seismic data based on. Principal component analysis the central idea of principal component analysis pca is to reduce the dimensionality of a data set consisting of a large number of interrelated variables, while retaining as much as possible of the variation present in the data set. Principal component analysis pca pca is a multivariate statistical technique to reduce the dimensionality of the data. Nov 12, 2015 the second principal components are perpendicular to the first and have respective eigenvalues of a 0. Seismic attributes can be both powerful and challenging to incorporate into interpretation and analysis. Retain the principal components that explain an acceptable level of variance. Not all the tools in the data analytics component analysis, selforganizing mapping, fuzzy logic, support vector machines, neural networks, etc.
Risk reduction through additional insights to complement interpretation. University of bucharest, faculty of geology and geophysics. Unsupervised seismic facies classification using independent. Principal component analysis for a seismic usability model of. Pdf first steps in seismic interpretation khaled magdy. Pca for structural interpretation of seismic data expands.
A stepbystep explanation of principal component analysis. The pca analysis has found its major use in geoscience and in remote sensing rs image analysis. Principal component analysis 3 because it is a variable reduction procedure, principal component analysis is similar in many respects to exploratory factor analysis. Principalcomponentanalysis and dimensionalityreduction 1 mattgormley lecture14 october24,2016 school of computer science readings. The object of seismic interpretation is to extract all the geologic. Using multidimensional scaling and kernel principal. We apply a common statistical tool, principal component analysis pca to the problem of direct property estimation from threedimensional 3d seismic amplitude data.
We develop the reservoir interpretation workflow figure 1 as follows. Seismic attributes are an invaluable aid in the interpretation of seismic data. Principal component analysis pca is a multivariate exploratory analysis method, useful to separate systematic variation from noise. This campaign was accompanied by other type of data, like rocks, soils, heavy mineral concentrates, geophysics and landsat images.
Faults and fractures detection in 2d seismic data based on principal. An introduction to principal component analysis with. Sensitivity analysis and cascaded interpretation scheme for. A simple principal component analysis example brian russell. Pdf churning seismic attributes with principal component. The example we will be using is taken from seismic analysis, were we consider how to compute the principal components of m seismic attributes, each with n samples. Interpret all statistics and graphs for principal components. Principal component analysis applied to 3d seismic data for. The purpose is to reduce the dimensionality of a data set sample by finding a new set of variables, smaller than the original set of variables, that nonetheless retains most of the samples information. Nov 04, 2019 this article looks at four graphs that are often part of a principal component analysis of multivariate data.
Using principal components analysis to select a subset of variables. Principal component analysis is the most widely used method of multivariate data analysis owing to the simplicity of its algebra and to its straightforward interpretation. Machine learning applied to 3d seismic data from the. Jun 03, 2017 new interpretation of principal components analysis applied to all points in the space of the standardized primary variables, then all points in the principal component space will be obtained.
Churning seismic attributes with principal component analysis. In the next section, we present a workflow for generating thin shalysand sequences and their corresponding synthetic seismograms. The higher the proportion, the more variability that the principal component explains. Neural networks for seismic principal components analysis ieee. Principal components analysis spss annotated output. Thus, the incorporation of pca which is known for high efficiency in lowering data. However, currently available traceshot interpolation methods in the spatial or fourier domain must. Principal component analysis pca, a linear quantitative technique, has proven to be an excellent.
Principalcomponentanalysis and dimensionalityreduction. Gcsome machine learning applications in seismic interpretation satinder chopra1. May 01, 2017 theory of principal components analysis and applications to multistory frame buildings responding to seismic excitation eng struct, 24 2002, pp. Pdf seismic data interpretation using the hough transform. How can machine learning improve geophysical interpretation. Different attributes are derived for different purposes. Principal component analysis pca and selforganizing maps soms provide. We need to determine which attributes are the most important and which can be ignored in the final. The attributes considered in this study are obtained using multidimensional scaling mds and kernel principal component analysis kpca.
Fewer variables little lost in information reduce the problem of multicollinearity among original. The principal component p is the projection of the variable x on to the eigenvector basis. Principal components pca and exploratory factor analysis. Principal component analysis pca is a linear mathematical technique used to reduce a large set of seismic attributes to a small set that still contains most of the variation in the large set. Pca aids in the selection of which attributes are approp. Fisher discriminant analysis fda, a supervised feature.
Spectral decomposition of seismic data is a recently introduced interpretation tool that. It makes it easy to remove irrelevant information considering faults and fractures from a seismic image, and thus, combining the attribute sections in principle component analysis produce a higher quality image. Keywords principal component analysis multivariate outlier orthogonal factor seismic trace uncorrelated factor. Geo expro seismic interpretation with machine learning. The theorem is applied to the interpretation of a fault seismogram and the uniform property of other seismograms. The size of the proportion can help you decide whether the principal component is important enough to retain. If the pdf is narrow, entropy is low, and if the pdf is broad, entropy is high. Seismic data interpretation using the hough transform and principal component analysis. For descriptive purposes, you may only need 80% of the variance explained.
As 5d interpolation discussed above regularizes the geometry of. Rotate the components in order to make their interpretation more understandable in terms of a specific theory. Using multidimensional scaling and kernel principal component. The principal component analysis pca reduces a large set of seismic attributes to highlight variations in the data by a linear combination of. Principal components analysis applied multivariate data. A simple principal component analysis example brian. Interpret the key results for principal components analysis. Seismic interpretation with machine learning geophysical. An introduction to principal component analysis with examples.
Principal component analysis principal component analysis a linear mathematical technique to reduce a large set of variables seismic attributes to a small set that still contains most of the variation of independent information in the large set. Because it is orthogonal to the rst eigenvector, their projections will be uncorrelated. Dec 16, 2016 multiattribute analyses employing principal component analysis pca and selforganizing maps are components of a machinelearning interpretation workflow figure 1 that involves the selection of appropriate seismic attributes and the application of these attributes in an unsupervised neural network analysis, also known as a selforganizing. Typically, an interpreter might generate 80 or more spectral ampl. Multiattribute machine learning interpretation workflow with principal component analysis pca and selforganizing maps som. Before discussing principal component analysis, we need to understand the concepts of eigenvectors and eigenvalues. Principal component analysis for a seismic usability model. Seismic attribute analysis and the use of unsupervised neural networks and principal component analysis in unconventional and conventional reservoirs.
Sep 01, 2016 an introduction to principal component analysis with examples in r thomas phan first. The set is used to extract attributes based on kernel principal components for characterizing subresolution reservoir properties such as nettogross ratio. Tabachnick and fidell 2001, page 588 cite comrey and lees 1992 advise regarding sample size. In other words, pca is a good approach to identify the combination of most meaningful seismic attributes generated from an original volume. This book begins with an introduction that is more philosophical than technical, followed by five chapters on fundamentals of reflection seismic titled seismic response, seismic attributes, velocity, migration, and resolution.
When dealing with datasets such as gene expression measurements, some of the biggest challenges stem from the size of the data itself. Applying principal component analysis to seismic attributes for interpretation of evaporite facies. If raw data are used, the procedure will create the original correlation matrix or covariance matrix, as specified by the user. Neural networks for seismic principal components analysis. By animating through the seismic as well as the corresponding coherence slices, the interpreter can define the change in footprint with depth. The application of principal components analysis to seismic. Seismic facies classification using machine learning techniques. The four plots are the scree plot, the profile plot, the score plot, and the pattern plot. Leonardo azevedo guerra raposo pereira atributos sismicos na. Quantitative understanding in biology principal component. We model thin sandshale sequences and their corresponding synthetic seismograms to generate a training set.
Geologic pattern recognition from seismic attributes. Principal component analysis example write up page 1 of 10 principal component analysis example robin beaumont chris dracup 28 february 2006 contents. Pc is the standard deviation of principal component. Principal component analysis, or pca, is a dimensionalityreduction method that is often used to reduce the dimensionality of large data sets by transforming a large set of variables into a smaller one that still contains most of the information in the large set. The application of principal components analysis to. For this reason, multiattribute techniques such as principal component analysis pca, selforganizing maps som are commonly used. Unsupervised machine learning facies classification in.
Based on higher order statistics, independent component analysis separates a multivariate signal into subcomponents. Principal component analysis pca is a simple yet powerful method widely used for analyzing high dimensional datasets. In fact, projections on to all the principal components are uncorrelated with each other. This manuscript is a preprint and was submitted for publication to.
Lower triassic jialingjiang formation, sichuan basin, china suyun hu, wenzhi zhao, zhaohui xu, hongliu zeng, qilong fu, lei jiang, shuyuan shi, zecheng wang, and wei liu. We illustrate pca in 2d with the natural clusters of figure 1, although the concepts extend to any dimension. The basic idea is to find optimally weighted linear combinations of original variables principal components such that the variability in the original data is preserved. Pdf principal component analysis as a tool for enhanced well. Before the analysis, there is no interpretation assigned to any given g. It is a linear mathematical method that reduces large sets of seismic attributes to a smaller set of attributes that still have most of the variations of the larger set. In fact, the steps followed when conducting a principal component analysis are virtually identical to those followed when conducting an exploratory factor analysis.
University of northern colorado abstract principal component analysis pca and exploratory factor analysis efa are both variable reduction techniques and sometimes mistaken as the same statistical method. Sep 04, 2019 the purpose of this post is to provide a complete and simplified explanation of principal component analysis, and especially to answer how it works step by step, so that everyone can understand it and make use of it, without necessarily having a strong mathematical background. Principal components analysis, like factor analysis, can be preformed on raw data, as shown in this example, or on a correlation or a covariance matrix. Principal component analysis pca there exist various techniques for dimensionality reduction which principal component analysis pca is one of the oldest and most commonly used. Preconditioning seismic data with 5d interpolation for. Oct 01, 1982 the application of principal components analysis takes advantage of the high degree of redundancy in the seismic data set to determine its statistical behavior and reduce it to its essential features. For example, a principal component with a proportion of 0.
Machine learning and seismic interpretation seg wiki. Machine learning applied to 3d seismic data from the denver. Principal component analysis pca is a technique that is useful for the compression and classification of data. Principal component analysis pca is a mathematical analytical approach that extracts the relevant information from any datasets based on the objectives of the study. Pca is a useful statistical technique that has found application in. Integrated data analysis using electrofacies and seismic. Seismic data interpretation using the hough transform and principal component analysis this article has been downloaded from iopscience. It allows to define a space of reduced dimensions that preserve. How to interpret graphs in a principal component analysis.
Principal component analysis is a useful statistical. Index terms data compression, eigenvectors, generalized hebbian algorithm, neural network, principal component analysis pca, ricker wavelets, seismic interpretation. Marfurt, journalseg technical program expanded abstracts, year2014. Two simple examples of principal components analysis. The individual factors are obtained through the principal component factoring. More complex examples of the application of principal components analysis.
1776 602 1039 18 826 1804 1528 1497 728 468 1545 1060 888 676 1289 316 1411 1097 259 65 930 105