Implementing behaviour in individual-based models using neural networks and genetic algorithms

Even though individual-based models (IBMs) have become very popular in ecol ogy during the last decade, there have been few attempts to implement behav ioural aspects in IBMs. This is partly due to lack of appropriate technique s. Behavioural and life history aspects can be implemented in IBMs through adaptive models based on genetic algorithms and neural networks (individual -based-neural network-genetic algorithm, ING). To investigate the precision of the adaptation process, we present three cases where solutions can be f ound by optimisation. These cases include a state-dependent patch selection problem, a simple game between predators and prey, and a more complex vert ical migration scenario for a planktivorous fish. In all cases, the optimal solution is calculated and compared with the solution achieved using ING. The results show that the ING method finds optimal or close to optimal solu tions for the problems presented. In addition it has a wider range of poten tial application areas than conventional techniques in behavioural modellin g. Especially the method is well suited for complex problems where other me thods fail to provide answers.