Dealing with uncertainty in agent-based models for short-term predictions

TL;DR

This paper introduces a dynamic optimization framework for agent-based models that combines parameter calibration and data assimilation to improve real-time short-term predictions in complex social systems, exemplified by bus route systems.

Contribution

It presents a novel method integrating parameter calibration and data assimilation to enhance ABM accuracy for real-time predictions, demonstrated through bus system modeling.

Findings

Enhanced prediction accuracy with dynamic ABM optimization.

Effective integration of data assimilation in agent-based models.

Potential applications in intelligent transport systems.

Abstract

Agent-based models (ABM) are gaining traction as one of the most powerful modelling tools within the social sciences. They are particularly suited to simulating complex systems. Despite many methodological advances within ABM, one of the major drawbacks is their inability to incorporate real-time data to make accurate short-term predictions. This paper presents an approach that allows ABMs to be dynamically optimised. Through a combination of parameter calibration and data assimilation (DA), the accuracy of model-based predictions using ABM in real time is increased. We use the exemplar of a bus route system to explore these methods. The bus route ABMs developed in this research are examples of ABMs that can be dynamically optimised by a combination of parameter calibration and DA. The proposed model and framework can also be used in an passenger information system, or in an Intelligent Transport Systems to provide forecasts of bus locations and arrival times.