Lane-Changing Risk Prediction on Urban Expressways: A Mixed Bayesian Approach for Sustainable Traffic Management

Quantao Yang, Peikun Li (), Fei Yang and Wenbo Lu
Additional contact information
Quantao Yang: Department of Public Security, Shaanxi Police College, Xi’an 710021, China
Peikun Li: College of Energy and Transportation Engineering, Inner Mongolia Agricultural University, Hohhot 010018, China
Fei Yang: Department of Public Security, Shaanxi Police College, Xi’an 710021, China
Wenbo Lu: School of Transportation, Southeast University, Nanjing 214135, China

Sustainability, 2025, vol. 17, issue 15, 1-14

Abstract: This study addresses critical safety challenges in sustainable urban mobility by developing a probabilistic framework for lane-change risk prediction on congested expressways. Utilizing unmanned aerial vehicle (UAV)-captured trajectory data from 784 validated lane-change events, we construct a Bayesian network model integrated with an I-CH scoring-enhanced MMHC algorithm. This approach quantifies risk probabilities while accounting for driver decision dynamics and input data uncertainties—key gaps in conventional methods like time-to-collision metrics. Validation via the Asia network paradigm demonstrates 80.5% reliability in forecasting high-risk maneuvers. Crucially, we identify two sustainability-oriented operational thresholds: (1) optimal lane-change success occurs when trailing-vehicle speeds in target lanes are maintained at 1.0–3.0 m/s (following-gap < 4.0 m) or 3.0–6.0 m/s (gap ≥ 4.0 m), and (2) insertion-angle change rates exceeding 3.0°/unit-time significantly elevate transition probability. These evidence-based parameters enable traffic management systems to proactively mitigate collision risks by 13.26% while optimizing flow continuity. By converting behavioral insights into adaptive control strategies, this research advances resilient transportation infrastructure and low-carbon mobility through congestion reduction.

Keywords: mixed Bayesian network; lane-change behavior; traffic safety (search for similar items in EconPapers)
JEL-codes: O13 Q Q0 Q2 Q3 Q5 Q56 (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2071-1050/17/15/7061/pdf (application/pdf)
https://www.mdpi.com/2071-1050/17/15/7061/ (text/html)

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:gam:jsusta:v:17:y:2025:i:15:p:7061-:d:1717183

Access Statistics for this article

Sustainability is currently edited by Ms. Alexandra Wu

More articles in Sustainability from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().