Predictability of short-term passengers’ origin and destination demands in urban rail transit

Fang Yang (), Chunyan Shuai (), Qian Qian (), Wencong Wang (), Mingwei He (), Min He () and Jaeyoung Lee ()
Additional contact information
Fang Yang: Kunming University of Science and Technology
Chunyan Shuai: Kunming University of Science and Technology
Qian Qian: Kunming University of Science and Technology
Wencong Wang: Kunming University of Science and Technology
Mingwei He: Kunming University of Science and Technology
Min He: Kunming University of Science and Technology
Jaeyoung Lee: Central South University

Transportation, 2023, vol. 50, issue 6, No 10, 2375-2401

Abstract: Abstract Accurate prediction of short-term passengers’ origin and destination (OD) demands is key to efficient operation and management of urban rail transit (URT), especially in the case of congestion or an incident. However, short-term OD demand forecasting is more challenging than passenger flow forecasting, due to its uncertainty and high dimensions. So far, most OD prediction models capture the spatio-temporal dependencies of OD flow by means of training models on historical data, but what characteristics and laws influence the performance of OD prediction are still unknown. In this paper, we propose temporal Pearson correlation coefficients and approximate entropy, as well as spatial correlations, as indicators to reflect the inherent time–space correlations and complexity of the OD flow. Then, by analyzing automatic fare collection data of the Beijing and Shanghai URT system, this paper deeply discusses the relationships between the spatio-temporal correlations and complexity of the OD flow and the predictive performances of different models with regard to different intervals. Finally, this paper proposes the predictable problem of travel demands and points out that the spatial correlations of the OD matrix are more important than the temporal correlations and complexity in the short-term prediction of travel demands. In particular, the number of principal components of the OD flow can be a key indicator to measure the forecasting performance of a model. A reasonable interval is very important for short-term OD forecasting, and in the Beijing URT system, 30 min is a preferable choice for workdays and 50 min for weekends. All these findings are beneficial to guide users to build a suitable model or improve the existing model to obtain better prediction performances.

Keywords: Predictability of travel demand; Spatio-temporal correlation; Temporal complexity (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s11116-022-10313-9 Abstract (text/html)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:kap:transp:v:50:y:2023:i:6:d:10.1007_s11116-022-10313-9

Ordering information: This journal article can be ordered from
http://www.springer. ... ce/journal/11116/PS2

DOI: 10.1007/s11116-022-10313-9

Access Statistics for this article

Transportation is currently edited by Kay W. Axhausen

More articles in Transportation from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().