Citation:
Weir-Smith, G. & Schwabe, C.A. (2001) Spatial interpolation vs neural network propagation as a method of extrapolating from field surveys. (Paper delivered at the Fourth Biennial International conference of Society of South African Geographers, Rawsonville, July).
Abstract:
Field surveys are costly exercises and the use of such data is often limited to a predefined geographic area. The spatial value of field survey results is regularly under-utilised on account of restricted application by users. The Human Sciences Research Council (HSRC) conducts several surveys a year and in the past couple of years artificial neural network propagation was also used to extrapolate survey results to a more representative or national level. The aim of this paper is to examine the methodology of both models and to compare the results of spatial interpolation in a recent substance abuse survey.
Description:
Paper delivered at the Fourth Biennial International conference of Society of South African Geographers, Rawsonville, July
If you are interested in obtaining a copy of an output which is not immediately available for download, please contact Hanlie Baudin at
researchoutputs@hsrc.ac.za