Using machine learning as a surrogate model for agent-based simulations

Angione, C., Silverman, E. and Yaneske, E. (2022) Using machine learning as a surrogate model for agent-based simulations. PLoS ONE, 17(2), e0263150. (doi: 10.1371/journal.pone.0263150) (PMID:35143521) (PMCID:PMC8830643)

[img] Text
263122.pdf - Published Version
Available under License Creative Commons Attribution.

1MB

Abstract

In this proof-of-concept work, we evaluate the performance of multiple machine-learning methods as surrogate models for use in the analysis of agent-based models (ABMs). Analysing agent-based modelling outputs can be challenging, as the relationships between input parameters can be non-linear or even chaotic even in relatively simple models, and each model run can require significant CPU time. Surrogate modelling, in which a statistical model of the ABM is constructed to facilitate detailed model analyses, has been proposed as an alternative to computationally costly Monte Carlo methods. Here we compare multiple machine-learning methods for ABM surrogate modelling in order to determine the approaches best suited as a surrogate for modelling the complex behaviour of ABMs. Our results suggest that, in most scenarios, artificial neural networks (ANNs) and gradient-boosted trees outperform Gaussian process surrogates, currently the most commonly used method for the surrogate modelling of complex computational models. ANNs produced the most accurate model replications in scenarios with high numbers of model runs, although training times were longer than the other methods. We propose that agent-based modelling would benefit from using machine-learning methods for surrogate modelling, as this can facilitate more robust sensitivity analyses for the models while also reducing CPU time consumption when calibrating and analysing the simulation.

Item Type:Articles
Status:Published
Refereed:Yes
Glasgow Author(s) Enlighten ID:Silverman, Dr Eric
Creator Roles:
Silverman, E.Conceptualization, Data curation, Formal analysis, Funding acquisition, Investigation, Methodology, Project administration, Software, Validation, Visualization, Writing – original draft, Writing – review and editing
Authors: Angione, C., Silverman, E., and Yaneske, E.
College/School:College of Medical Veterinary and Life Sciences > Institute of Health and Wellbeing > MRC/CSO SPHSU
Journal Name:PLoS ONE
Publisher:Public Library of Science
ISSN:1932-6203
ISSN (Online):1932-6203
Copyright Holders:Copyright © 2022 Angione et al.
First Published:First published in PLoS ONE 17(2): e0263150
Publisher Policy:Reproduced under a Creative Commons License
Related URLs:

University Staff: Request a correction | Enlighten Editors: Update this record

Project CodeAward NoProject NamePrincipal InvestigatorFunder's NameFunder RefLead Dept
3048231Complexity in healthSharon SimpsonMedical Research Council (MRC)MC_UU_00022/1HW - MRC/CSO Social and Public Health Sciences Unit
3048231Complexity in healthSharon SimpsonChief Scientist Office (CSO)SPHSU16HW - MRC/CSO Social and Public Health Sciences Unit
303087PHASE: The Population HeAlth Simulation nEtworkLaurence MooreMedical Research Council (MRC)MR/S037594/1HW - MRC/CSO Social and Public Health Sciences Unit