From Model-Based Screening to Data-Driven Surrogates: A Multi-Stage Workflow for Exploring Stochastic Agent-Based Models
For modelers of stochastic agent-based systems, this provides a hands-off framework to handle high-dimensional parameter spaces, though the approach is incremental as it integrates existing techniques.
This work presents a multi-stage pipeline that combines systematic design of experiments with machine learning surrogates to explore stochastic agent-based models. Applied to a predator-prey case study, the method automates the discovery of unstable regions where outcomes depend on nonlinear interactions, enabling rigorous sensitivity analysis and policy testing.
Systematic exploration of Agent-Based Models (ABMs) is challenged by the curse of dimensionality and their inherent stochasticity. We present a multi-stage pipeline integrating the systematic design of experiments with machine learning surrogates. Using a predator-prey case study, our methodology proceeds in two steps. First, an automated model-based screening identifies dominant variables, assesses outcome variability, and segments the parameter space. Second, we train Machine Learning models to map the remaining nonlinear interaction effects. This approach automates the discovery of unstable regions where system outcomes are highly dependent on nonlinear interactions between many variables. Thus, this work provides modelers with a rigorous, hands-off framework for sensitivity analysis and policy testing, even when dealing with high-dimensional stochastic simulators.