Exploration of multivariate atmospheric particulate compositional data by projection pursuit

Abstract With the availability of analytical methods that can measure multiple chemical species in a single sample and automated samplers that can obtain large numbers of samples, it is possible to obtain large data sets characterizing some portion of the atmospheric environment. The problem that arises with these large multivariate data sets is that they are too big to be easily visualized and numerical methods are needed to permit the identification of structures that exist in such data. One of these exploratory analysis methods is called projection pursuit. Projection pursuit is a method for projecting high dimension data into fewer and hence comprehensible number of dimensions that capture the main features of the data. Projection pursuit is a relatively new method for identifying interesting lower-dimensional views of multivariate data by optimizing a criterion index that measures how interesting each projection is. The basic methodology is outlined and its application to coarse and fine particle composition data obtained during the Regional Air Pollution Study of St. Louis, Missouri, are presented. The method permits the identification of clusters of samples that are influenced by the same emission sources. By examining the average wind direction for the clusters, it is possible to identify the individual sources that contribute material to those samples.

[1]  T. G. Dzubay,et al.  CHEMICAL ELEMENT BALANCE METHOD APPLIED TO DICHOTOMOUS SAMPLER DATA , 1980 .

[2]  Philip K. Hopke,et al.  Another coprocessor board to add power to your PC , 1986 .

[3]  Glen E. Gordon,et al.  Wind-trajectory method for determining compositions of particles from major air pollution sources , 1988 .

[4]  Philip K. Hopke,et al.  The Use of Principal Component Factor Analysis to Interpret Particulate Compositional Data Sets , 1982 .

[5]  Philip K. Hopke,et al.  Target-Transformation Factor Analysis of Airborne Particulate Samples Selected by Wind-Trajectory Analysis , 1988 .

[6]  Robin Sibson,et al.  What is projection pursuit , 1987 .

[7]  Martin A. Cohen,et al.  Observations less than the analytical limit of detection , 1989 .

[8]  P. Hopke,et al.  Exploration of multivariate chemical data by projection pursuit , 1992 .

[9]  Desire L. Massart,et al.  The Interpretation of Analytical Chemical Data by the Use of Cluster Analysis , 1983 .

[10]  Daniel J. Alpert,et al.  A determination of the sources of airborne particles collected during the regional air pollution study , 1981 .

[11]  R. C. Gatti,et al.  A .beta.-gage method applied to aerosol samples. , 1981, Environmental science & technology.

[12]  J. Kruskal.  TOWARD A PRACTICAL METHOD WHICH HELPS UNCOVER THE STRUCTURE OF A SET OF MULTIVARIATE OBSERVATIONS BY FINDING THE LINEAR TRANSFORMATION WHICH OPTIMIZES A NEW “INDEX OF CONDENSATION” , 1969 .

[13]  E. I. Hamilton.  Receptor modelling in environmental chemistry , 1986 .

[14]  J. Friedman,et al.  Projection Pursuit Regression , 1981 .

[15]  A. C. Thompson,et al.  LARGE-SCALE MEASUREMENT OF AIRBORNE PARTICULATE SULFUR , 1978 .

[16]  John W. Tukey,et al.  A Projection Pursuit Algorithm for Exploratory Data Analysis , 1974, IEEE Transactions on Computers.