Cargando…
Using machine learning as a surrogate model for agent-based simulations
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 eve...
Autores principales: | , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Public Library of Science
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8830643/ https://www.ncbi.nlm.nih.gov/pubmed/35143521 http://dx.doi.org/10.1371/journal.pone.0263150 |
_version_ | 1784648316565323776 |
---|---|
author | Angione, Claudio Silverman, Eric Yaneske, Elisabeth |
author_facet | Angione, Claudio Silverman, Eric Yaneske, Elisabeth |
author_sort | Angione, Claudio |
collection | PubMed |
description | 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. |
format | Online Article Text |
id | pubmed-8830643 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | Public Library of Science |
record_format | MEDLINE/PubMed |
spelling | pubmed-88306432022-02-11 Using machine learning as a surrogate model for agent-based simulations Angione, Claudio Silverman, Eric Yaneske, Elisabeth PLoS One Research Article 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. Public Library of Science 2022-02-10 /pmc/articles/PMC8830643/ /pubmed/35143521 http://dx.doi.org/10.1371/journal.pone.0263150 Text en © 2022 Angione et al https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. |
spellingShingle | Research Article Angione, Claudio Silverman, Eric Yaneske, Elisabeth Using machine learning as a surrogate model for agent-based simulations |
title | Using machine learning as a surrogate model for agent-based simulations |
title_full | Using machine learning as a surrogate model for agent-based simulations |
title_fullStr | Using machine learning as a surrogate model for agent-based simulations |
title_full_unstemmed | Using machine learning as a surrogate model for agent-based simulations |
title_short | Using machine learning as a surrogate model for agent-based simulations |
title_sort | using machine learning as a surrogate model for agent-based simulations |
topic | Research Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8830643/ https://www.ncbi.nlm.nih.gov/pubmed/35143521 http://dx.doi.org/10.1371/journal.pone.0263150 |
work_keys_str_mv | AT angioneclaudio usingmachinelearningasasurrogatemodelforagentbasedsimulations AT silvermaneric usingmachinelearningasasurrogatemodelforagentbasedsimulations AT yaneskeelisabeth usingmachinelearningasasurrogatemodelforagentbasedsimulations |