Nonlinear inverse optimization for parameter estimation of commodity-vehicle-decoupled freight assignment

Joseph Ying Jun Chow, Stephen G. Ritchie, Kyungsoo Jeong

Research output: Contribution to journalArticle

Abstract

A systematic approach to estimate parameters from noisy priors is proposed for traffic assignment problems. It extends inverse optimization theory to nonlinear problems, and defines a new class of parameter estimation problems in the transportation literature for networks under congestion. The approach is used to systematically calibrate a new link-based variation of the STAN model which decouples commodity flows and vehicle flows. The models are tested on a small network and then a case study with real data from California statewide implementation. Cross-validation shows 15% CV of the RMSE.

Original languageEnglish (US)
Pages (from-to)71-91
Number of pages21
JournalTransportation Research Part E: Logistics and Transportation Review
Volume67
DOIs
StatePublished - 2014

Fingerprint

Parameter estimation
commodity
traffic
Commodities
Assignment
Freight
Assignment problem
Cross-validation
Congestion
literature

Keywords

  • Freight forecast
  • Inverse optimization
  • Network assignment
  • Nonlinear optimization
  • Transshipment

ASJC Scopus subject areas

  • Business and International Management
  • Management Science and Operations Research
  • Transportation

Cite this

@article{052a89979ce545098a7b1ba9fe9e7600,
title = "Nonlinear inverse optimization for parameter estimation of commodity-vehicle-decoupled freight assignment",
abstract = "A systematic approach to estimate parameters from noisy priors is proposed for traffic assignment problems. It extends inverse optimization theory to nonlinear problems, and defines a new class of parameter estimation problems in the transportation literature for networks under congestion. The approach is used to systematically calibrate a new link-based variation of the STAN model which decouples commodity flows and vehicle flows. The models are tested on a small network and then a case study with real data from California statewide implementation. Cross-validation shows 15{\%} CV of the RMSE.",
keywords = "Freight forecast, Inverse optimization, Network assignment, Nonlinear optimization, Transshipment",
author = "Chow, {Joseph Ying Jun} and Ritchie, {Stephen G.} and Kyungsoo Jeong",
year = "2014",
doi = "10.1016/j.tre.2014.04.004",
language = "English (US)",
volume = "67",
pages = "71--91",
journal = "Transportation Research, Part E: Logistics and Transportation Review",
issn = "1366-5545",
publisher = "Elsevier Limited",

}

TY - JOUR

T1 - Nonlinear inverse optimization for parameter estimation of commodity-vehicle-decoupled freight assignment

AU - Chow, Joseph Ying Jun

AU - Ritchie, Stephen G.

AU - Jeong, Kyungsoo

PY - 2014

Y1 - 2014

N2 - A systematic approach to estimate parameters from noisy priors is proposed for traffic assignment problems. It extends inverse optimization theory to nonlinear problems, and defines a new class of parameter estimation problems in the transportation literature for networks under congestion. The approach is used to systematically calibrate a new link-based variation of the STAN model which decouples commodity flows and vehicle flows. The models are tested on a small network and then a case study with real data from California statewide implementation. Cross-validation shows 15% CV of the RMSE.

AB - A systematic approach to estimate parameters from noisy priors is proposed for traffic assignment problems. It extends inverse optimization theory to nonlinear problems, and defines a new class of parameter estimation problems in the transportation literature for networks under congestion. The approach is used to systematically calibrate a new link-based variation of the STAN model which decouples commodity flows and vehicle flows. The models are tested on a small network and then a case study with real data from California statewide implementation. Cross-validation shows 15% CV of the RMSE.

KW - Freight forecast

KW - Inverse optimization

KW - Network assignment

KW - Nonlinear optimization

KW - Transshipment

UR - http://www.scopus.com/inward/record.url?scp=84900023872&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84900023872&partnerID=8YFLogxK

U2 - 10.1016/j.tre.2014.04.004

DO - 10.1016/j.tre.2014.04.004

M3 - Article

AN - SCOPUS:84900023872

VL - 67

SP - 71

EP - 91

JO - Transportation Research, Part E: Logistics and Transportation Review

JF - Transportation Research, Part E: Logistics and Transportation Review

SN - 1366-5545

ER -