ABSTRACT
This chapter describes two GIS applications of a parallel genetic programming approach to model discovery. It is noted that GIS has resulted in the creation of extremely data-rich environments but it is proving very difficult to exploit this situation because of the lack of suitable models and the difficulties of model creation by more traditional hypotheticodeductive routes. The chapter describes how to develop computer models of spatial systems via a machine-based inductive approach. A Cray T3D parallel supercomputer with 512 processors is used to investigate the potential of a new approach to building computer models. A series of results are described which allude to the potential power of the method for those applications where there are considerable data but no suitable existing models and no good theoretical framework on which to base their development.
