Bayesian precalibration of a large stochastic microsimulation model

Alexis Boukouvalas, Pete Sykes, Dan Cornford, Hugo Maruri-Aguilar

Research output: Contribution to journalArticle

Abstract

Calibration of stochastic traffic microsimulation models is a challenging task. This paper proposes a fast iterative probabilistic precalibration framework and demonstrates how it can be successfully applied to a real-world traffic simulation model of a section of the M40 motorway and its surrounding area in the U.K. The efficiency of the method stems from the use of emulators of the stochastic microsimulator, which provides fast surrogates of the traffic model. The use of emulators minimizes the number of microsimulator runs required, and the emulators' probabilistic construction allows for the consideration of the extra uncertainty introduced by the approximation. It is shown that automatic precalibration of this real-world microsimulator, using turn-count observational data, is possible, considering all parameters at once, and that this precalibrated microsimulator improves on the fit to observations compared with the traditional expertly tuned microsimulation.
Original languageEnglish
Pages (from-to)1337-1347
Number of pages11
JournalIEEE Transactions on Intelligent Transportation Systems
Volume15
Issue number3
Early online date4 Mar 2014
DOIs
Publication statusPublished - Jun 2014

Fingerprint

Stochastic models
Calibration

Bibliographical note

© 2014 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

Funding: EPSRC - Managing Uncertainty in Complex Models Project under Grant D048893/1 and by the Aston Research Centre for Healthy Ageing.

Cite this

Boukouvalas, Alexis ; Sykes, Pete ; Cornford, Dan ; Maruri-Aguilar, Hugo. / Bayesian precalibration of a large stochastic microsimulation model. In: IEEE Transactions on Intelligent Transportation Systems. 2014 ; Vol. 15, No. 3. pp. 1337-1347.
@article{b7c86c364ecf4a42a4019ccf3235a5fc,
title = "Bayesian precalibration of a large stochastic microsimulation model",
abstract = "Calibration of stochastic traffic microsimulation models is a challenging task. This paper proposes a fast iterative probabilistic precalibration framework and demonstrates how it can be successfully applied to a real-world traffic simulation model of a section of the M40 motorway and its surrounding area in the U.K. The efficiency of the method stems from the use of emulators of the stochastic microsimulator, which provides fast surrogates of the traffic model. The use of emulators minimizes the number of microsimulator runs required, and the emulators' probabilistic construction allows for the consideration of the extra uncertainty introduced by the approximation. It is shown that automatic precalibration of this real-world microsimulator, using turn-count observational data, is possible, considering all parameters at once, and that this precalibrated microsimulator improves on the fit to observations compared with the traditional expertly tuned microsimulation.",
author = "Alexis Boukouvalas and Pete Sykes and Dan Cornford and Hugo Maruri-Aguilar",
note = "{\circledC} 2014 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. Funding: EPSRC - Managing Uncertainty in Complex Models Project under Grant D048893/1 and by the Aston Research Centre for Healthy Ageing.",
year = "2014",
month = "6",
doi = "10.1109/TITS.2014.2304394",
language = "English",
volume = "15",
pages = "1337--1347",
journal = "IEEE Transactions on Intelligent Transportation Systems",
issn = "1524-9050",
publisher = "IEEE",
number = "3",

}

Bayesian precalibration of a large stochastic microsimulation model. / Boukouvalas, Alexis; Sykes, Pete; Cornford, Dan; Maruri-Aguilar, Hugo.

In: IEEE Transactions on Intelligent Transportation Systems, Vol. 15, No. 3, 06.2014, p. 1337-1347.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Bayesian precalibration of a large stochastic microsimulation model

AU - Boukouvalas, Alexis

AU - Sykes, Pete

AU - Cornford, Dan

AU - Maruri-Aguilar, Hugo

N1 - © 2014 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. Funding: EPSRC - Managing Uncertainty in Complex Models Project under Grant D048893/1 and by the Aston Research Centre for Healthy Ageing.

PY - 2014/6

Y1 - 2014/6

N2 - Calibration of stochastic traffic microsimulation models is a challenging task. This paper proposes a fast iterative probabilistic precalibration framework and demonstrates how it can be successfully applied to a real-world traffic simulation model of a section of the M40 motorway and its surrounding area in the U.K. The efficiency of the method stems from the use of emulators of the stochastic microsimulator, which provides fast surrogates of the traffic model. The use of emulators minimizes the number of microsimulator runs required, and the emulators' probabilistic construction allows for the consideration of the extra uncertainty introduced by the approximation. It is shown that automatic precalibration of this real-world microsimulator, using turn-count observational data, is possible, considering all parameters at once, and that this precalibrated microsimulator improves on the fit to observations compared with the traditional expertly tuned microsimulation.

AB - Calibration of stochastic traffic microsimulation models is a challenging task. This paper proposes a fast iterative probabilistic precalibration framework and demonstrates how it can be successfully applied to a real-world traffic simulation model of a section of the M40 motorway and its surrounding area in the U.K. The efficiency of the method stems from the use of emulators of the stochastic microsimulator, which provides fast surrogates of the traffic model. The use of emulators minimizes the number of microsimulator runs required, and the emulators' probabilistic construction allows for the consideration of the extra uncertainty introduced by the approximation. It is shown that automatic precalibration of this real-world microsimulator, using turn-count observational data, is possible, considering all parameters at once, and that this precalibrated microsimulator improves on the fit to observations compared with the traditional expertly tuned microsimulation.

UR - http://www.scopus.com/inward/record.url?scp=84902083472&partnerID=8YFLogxK

U2 - 10.1109/TITS.2014.2304394

DO - 10.1109/TITS.2014.2304394

M3 - Article

AN - SCOPUS:84902083472

VL - 15

SP - 1337

EP - 1347

JO - IEEE Transactions on Intelligent Transportation Systems

JF - IEEE Transactions on Intelligent Transportation Systems

SN - 1524-9050

IS - 3

ER -