This chapter is intended as a convenient resource for regional scientists interestedin a statistical view of the neural spatial interaction modelling approach. We view neural spatial interaction models as an example of non-parametric estimation that makes few, if any, a priori assumptions about the nature of the data-generating process to approximate the true, but unknown spatial interaction function of interest. We limit the scope of this chapter to unconstrained spatial interaction and use appropriate statistical arguments to gain important insights into the problems and properties of this modelling approach that may be useful for those interested in application development. The remainder of this chapter is structured as follows. The next section introduces the class of neural spatial interaction models of interest, and sets forth the context in which spatial interaction modelling will be considered. The sections that follow present important components of a methodology for neural spatial interaction modelling.
CITATION STYLE
Fischer, M. M. (2009). Principles of neural spatial interaction modeling. In Advances in Spatial Science (pp. 199–214). Springer International Publishing. https://doi.org/10.1007/978-3-642-00627-2_8
Mendeley helps you to discover research relevant for your work.