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

Authors

  • Richard Vong,

    1. Group for Statistical Analysis of Natural Resources Data (SAND). Norwegian Computing Centre, N-0314 Blindern, Oslo 3, Norway
    Current affiliation:
    1. EPA Environmental Research Lab., 200 S.W. 35th Street, Corvallis, OR 97333, U.S.A.
    Search for more papers by this author
    • NTNF Senior Visiting Scientist.

  • Paul Geladi,

    1. Group for Statistical Analysis of Natural Resources Data (SAND). Norwegian Computing Centre, N-0314 Blindern, Oslo 3, Norway
    2. Group for Statistical Analysis of Natural Resources Data (SAND). Chemometrics Research Group, Umeå University, S-901 87 Umeå, Sweden
    Search for more papers by this author
  • Svante Wold,

    1. Group for Statistical Analysis of Natural Resources Data (SAND). Chemometrics Research Group, Umeå University, S-901 87 Umeå, Sweden
    Search for more papers by this author
  • Kim Esbensen

    1. Group for Statistical Analysis of Natural Resources Data (SAND). Norwegian Computing Centre, N-0314 Blindern, Oslo 3, Norway
    Search for more papers by this author

Abstract

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.

Ancillary