Surrogate Assisted Methods for the Parameterisation of Agent-Based Models

TL;DR

This paper introduces a surrogate-assisted framework for calibrating parameters in complex agent-based models, demonstrating improved performance over traditional methods and identifying optimal surrogate models like XGBoost and Decision Trees.

Contribution

The paper presents a novel framework integrating sampling methods and surrogate models to enhance parameter calibration in high-dimensional agent-based models.

Findings

Surrogate-assisted methods outperform standard sampling techniques.

XGBoost and Decision Tree surrogate models are most effective.

Framework improves calibration efficiency in complex ABMs.

Abstract

Parameter calibration is a major challenge in agent-based modelling and simulation (ABMS). As the complexity of agent-based models (ABMs) increase, the number of parameters required to be calibrated grows. This leads to the ABMS equivalent of the \say{curse of dimensionality}. We propose an ABMS framework which facilitates the effective integration of different sampling methods and surrogate models (SMs) in order to evaluate how these strategies affect parameter calibration and exploration. We show that surrogate assisted methods perform better than the standard sampling methods. In addition, we show that the XGBoost and Decision Tree SMs are most optimal overall with regards to our analysis.