Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Paul Saves, Matthieu Mastio, Nicolas Verstaevel, Benoit Gaudou

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.

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

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.

Paper Structure

This paper contains 17 sections, 8 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Related works
  3. Model Description
  4. Baseline Model.
  5. Spatial extensions.
  6. Multi-Stage Exploration Pipeline
  7. Domain Knowledge and Assumptions
  8. Model-based Analysis
  9. Initial Experimental Design and Data Analysis
  10. Leveraging ANOVA for Linear Global Sensitivity Analysis.
  11. Leveraging a Decision Tree for Threshold Identification.
  12. First Refinement of the Search Space.
  13. Data-based analysis
  14. Leveraging Sobol' indices for nonlinear global sensitivity analysis.
  15. Leveraging PDP and ICE for Threshold Identification.
  16. ...and 2 more sections

Figures (8)

  • Figure 1: Multi-stage exploration workflow.
  • Figure 2: PDP/ICE and Uncertainties variations for the 6 most important features.
  • Figure 3: Simulation results showing the relationship between variables X and Y.
  • Figure 4: Global Regime Dynamics. Comparison of simulation outcome distributions between the initial broad exploration (V1) and the refined sampling strategy (V2). The dominance of the Extinction regime highlights the system's structural vulnerability.
  • Figure 5: Model-Based Screening (Phase 1). A Decision Tree (CART) trained on the initial dataset. It identifies the primary anthropogenic tipping point: a deterministic shift toward extinction when the Proportion of Hunting Zones ($PH$) exceeds $\approx 31\%$.
  • ...and 3 more figures