PARALLEL MODELING AND NEURAL NETWORKS - AN OVERVIEW FOR TRANSPORTATION LAND-USE SYSTEMS

We provide in this conceptual paper an overview of a parallel transpor tation/land use modelling environment. We argue that sequential urban modelling does not well represent complex urban dynamics. Instead, we suggest a parallel distributed processing structure composed of proces sors and links between processors. Each processor is a set of neurons and weights between neurons forming a neural network. For spatial syst ems neural networks have two main paradigms which are processes simula tion and pattern association. Parallel distributed processing offers a new methodology to represent the relational structure between element s of a transportation/land use system and thus helping to model those systems. We also provide a set of advantages, drawbacks and some resea rch directions about the usage of neural networks for spatial analysis and modelling. (C) 1997 Elsevier Science Ltd. All rights reserved.