Share Email Print

Proceedings Paper

Multiple site receptor modeling with a minimal spanning tree combined with a Kohonen neural network
Author(s): Philip K. Hopke
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

A combination of two pattern recognition methods has been developed that allows the generation of geographical emission maps form multivariate environmental data. In such a projection into a visually interpretable subspace by a Kohonen Self-Organizing Feature Map, the topology of the higher dimensional variables space can be preserved, but parts of the information about the correct neighborhood among the sample vectors will be lost. This can partly be compensated for by an additional projection of Prim's Minimal Spanning Tree into the trained neural network. This new environmental receptor modeling technique has been adapted for multiple sampling sites. The behavior of the method has been studied using simulated data. Subsequently, the method has been applied to mapping data sets from the Southern California Air Quality Study. The projection of a 17 chemical variables measured at up to 8 sampling sites provided a 2D, visually interpretable, geometrically reasonable arrangement of air pollution source sin the South Coast Air Basin.

Paper Details

Date Published: 16 December 1999
PDF: 6 pages
Proc. SPIE 3854, Pattern Recognition, Chemometrics, and Imaging for Optical Environmental Monitoring, (16 December 1999); doi: 10.1117/12.372897
Show Author Affiliations
Philip K. Hopke, Clarkson Univ. (United States)

Published in SPIE Proceedings Vol. 3854:
Pattern Recognition, Chemometrics, and Imaging for Optical Environmental Monitoring
Khalid J. Siddiqui; DeLyle Eastwood, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?