With growing developments in marine tidal energy, coupled with high densities of marine species in suitable installation locations, there is concern about marine wildlife colliding with underwater devices. Methods are needed to predict such collisions when assessing environmental impacts of underwater turbines. Agent-Based Models (ABMs) in the field of ecology: simulate interactions between organisms; assess how they live (i.e. grow, reproduce, function, adapt) and die in a dynamic physical environment; consider a population from the point of view of the individuals, or agents with population level behaviours emerging from the behaviour of the individuals; have individual within a system that are defined by traits (e.g. size, age or sensitivity to a stressor) and behaviours they can perform (e.g. migration or avoidance). To better predict collisions with underwater devices, HR Wallingford has developed an Agent-Based Model (ABM) to predict the probability of marine animals colliding with an underwater device.