VISUAL NEURAL MAPPING TECHNIQUE FOR LOCATING FINE AIRBORNE PARTICLES SOURCES

A combination of two pattern recognition methods has been developed th at allows the generation of geographical emission maps from multivaria te environmental data. During such a projection into a visually interp retable subspace by a Kohonen self-organizing feature map, the topolog y of the higher dimensional variables space can be preserved, but part s of the information about the correct neighborhood among the sample v ectors are lost. This loss can partly be compensated for by the additi onal projection of Prim's minimal spanning tree onto the trained neura l network. This new environmental receptor site modeling technique is theoretically discussed for measurements from single sampling sites. I n order to obtain a further quantitative evaluation of such a combined mapping of minimal spanning tree and Kohonen neural network, the conc ept of a geographic unit circle (GUC) is introduced as well. The GUC a round the single sampling site in Granite City, IL, yielded estimates of the emission levels, the trace element profiles, and the geographic directions for a number of airborne particle sources.