Source contributions to ambient aerosol calculated by discriminat partial least squares regression (PLS)

Partial least squares regression (PLS) is proposed for solving ir pollution source apportionment problems as an alternative method to the frequently used chemical mass balance technique. A discriminant PLS is used to calculate linear mixing proportions for a synthetic ambient aerosol data set where the truth is known. Without sacrificing orthogonality of the source profiles, PLS can resolve the emission sources and accurately predict the emission source contributions. Further extensions of the PLS approach to environmental receptor modelling are discussed.

[1]  S. Friedlander,et al.  Chemical element balances and identification of air pollution sources. , 1973, Environmental science & technology.

[2]  S. Wold.  Cross-Validatory Estimation of the Number of Components in Factor and Principal Components Models , 1978 .

[3]  J. Watson.  Chemical element balance receptor model methodology for assessing the sources of fine and total suspended particulate matter in Portland, Oregon , 1979 .

[4]  D. J. Alpert,et al.  A quantitative determination of sources in the Boston urban aerosol. , 1980, Atmospheric environment.

[5]  Harald Martens,et al.  A multivariate calibration problem in analytical chemistry solved by partial least-squares models in latent variables , 1983 .

[6]  S. Wold,et al.  The Collinearity Problem in Linear Regression. The Partial Least Squares (PLS) Approach to Generalized Inverses , 1984 .

[7]  K. Sjoedin.  Minimizing effects of closure on analytical data , 1984 .

[8]  H. J. Williamson,et al.  Interlaboratory comparison of Receptor Model results for Houston aerosol , 1984 .

[9]  P. Hopke,et al.  A comparison of R- and Q-modes in target transformation factor analysis for resolving environmental data∗ , 1984 .

[10]  L. A. Currie,et al.  Interlaboratory comparison of source apportionment procedures: Results for simulated data sets☆☆☆ , 1984 .

[11]  S. Wold,et al.  Multivariate Data Analysis in Chemistry , 1984 .

[12]  B. Kowalski,et al.  Statistical Receptor Models Solved by Partial Least Squares , 1985 .

[13]  B. Kowalski,et al.  Partial least-squares regression: a tutorial , 1986 .

[14]  L. E. Wangen,et al.  A theoretical foundation for the PLS algorithm , 1987 .

[15]  Using discriminant analysis to estimate linear mixing proportions , 1987 .

[16]  S. Wold,et al.  Partial least squares analysis with cross‐validation for the two‐class problem: A Monte Carlo study , 1987 .

[17]  H. Hansson,et al.  Northeastern Pacific submicrometer aerosol and rainwater composition: A multivariate analysis , 1988 .