Using Machine Learning to Emulate Agent-Based Simulations

In this paper, we evaluate the performance of multiple machine-learning methods in the emulation of agent-based models (ABMs). ABMs are a popular methodology for modelling complex systems composed of multiple interacting processes. The analysis of ABM outputs is often not straightforward, as the relationships between input parameters can be non-linear or even chaotic, and each individual model run can require significant CPU time. Statistical emulation, in which a statistical model of the ABM is constructed to allow for more in-depth model analysis, has proven valuable for some applications. Here we compare multiple machine-learning methods for ABM emulation in order to determine the approaches best-suited to replicating the complex and non-linear behaviour of ABMs. Our results suggest that, in most scenarios, artificial neural networks (ANNs) and support vector machines outperform Gaussian process emulators, currently the most commonly used method for the emulation of complex computational models. ANNs produced the most accurate model replications in scenarios with high numbers of model runs, although training times for these emulators were considerably longer than for any other method. We propose that users of complex ABMs would benefit from using machine-learning methods for emulation, as this can facilitate more robust sensitivity analyses for their models as well as reducing CPU time consumption when calibrating and analysing the simulation.