The practice of numerical simulation of flows and other processes occurring in water has now matured into an established and efficient part of hydraulics. At the same time, however, the models themselves often become very extended. In many situations, given the divergence between the response-time requirements and the computational-time requirements of numerical models, the need arises to reduce the time needed to simulate the impact of given input events on hydraulics systems. In this study the possibility of using systems composed of agents consisting only of artificial neural networks (ANNs) as modelling tools for the simulation of tidal flow in a two-dimensional flow field is investigated. In particular this involves the modelling of a process that evolves in time and the ANNs themselves function as non-linear dynamic systems that effectively reproduce the behaviour of the fluid at any one place and any one time from the behavior at other places at earlier times. Different types of ANN-agent architectures are investigated in order to asses their ability and relative performance in encapsulating the site-specific knowledge and data necessary to reproduce the temporal sequence of states observed in a modelled area.
