CALIBRATION OF CELLULAR AUTOMATA BY USING NEURAL NETWORKS FOR THE SIMULATION OF COMPLEX URBAN SYSTEMS

摘要: This paper presents a new cellular automata (CA) model which uses artificial neural networks for both calibration and simulation. A critical issue urban CA simulation is how to determine parameter values define structures. The of real cities involves the use many variables parameters. models very difficult when there large set In proposed model, most are automatically determined by training networks. from then imported into also based on algorithm With networks, users do not need provide detailed transition rules define. study shows that has better accuracy than traditional in nonlinear complex systems.