Highlights Defined a class of nonlinear inverse optimization problems using KKT conditions. Applied method as parameter estimation for freight assignment models. Formulated a commodity-vehicle-decoupled variation of STAN model. Conducted parameter recovery and sensitivity tests with a small network. Estimated airport capacity parameters from prior data and cross-validated them.
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.
Nonlinear inverse optimization for parameter estimation of commodity-vehicle-decoupled freight assignment
2014-04-17
21 pages
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
Engineering Index Backfile | 1928
Freight Commodity Flow in Kentucky
NTIS | 1999
|Commodity values and freight rates
Engineering Index Backfile | 1930
|Freight commodity statistics for 1928
Engineering Index Backfile | 1929