From Model-Based Screening to Data-Driven Surrogates: A Multi-Stage Workflow for Exploring Stochastic Agent-Based Models

TL;DR

This paper introduces a multi-stage workflow combining systematic experiment design and machine learning surrogates to efficiently explore high-dimensional stochastic agent-based models, demonstrated on a predator-prey case study.

Contribution

It presents a novel multi-stage pipeline that automates sensitivity analysis and identifies unstable regions in complex stochastic models.

Findings

Automated screening identifies dominant variables and outcome variability.

ML models effectively map nonlinear interaction effects.

Framework enables sensitivity analysis in high-dimensional stochastic ABMs.

Abstract

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.