Data Science for Transportation· 2026Q2
A Hybrid Neural Network for Real-Time OD Demand Calibration Under Disruptions
- 3citations
- Q2SCImago
- 2026year
Short summary
A novel hybrid framework integrates data-driven OD demand calibration with microscopic traffic simulators, using a metamodel-based backpropagation scheme to enable real-time adaptation to traffic disruptions.
AI-generated from the title and abstract; the full text is not read.
Key points
- Proposes a hybrid framework for real-time OD demand calibration integrating data-driven models and traffic simulators.
- Introduces a metamodel-based backpropagation scheme for bi-directional information exchange and simultaneous parameter updates.
- Offline pre-training of the data-driven model accelerates the initial calibration process.
- Framework demonstrated capability to dynamically adapt to evolving traffic conditions under disruption scenarios in case studies.
AI-generated from the title and abstract; the full text is not read.
Abstract
Abstract This study proposes a real-time OD demand calibration framework that integrates data-driven origin–destination (OD) demand calibration with black-box microscopic stochastic traffic simulators. To enable bi-directional information exchange between the data-driven OD calibration and the non-differentiable traffic simulator, a metamodel-based backpropagation scheme is developed, allowing simultaneous updates of both the data-driven model and simulator parameters. In addition, the data-driven model is pre-trained offline using the metamodel to accelerate the initial calibration process. Validation through two toy networks and a Tokyo expressway corridor case study demonstrates the framework’s capability to dynamically adapt to evolving traffic conditions under various disruption scenarios. The results highlight the potential of hybrid approaches that couple data-driven and model-based techniques to support proactive traffic management, offering substantial improvements over conventional reactive systems.
The authors' abstract, as published at the source. Data Science for Transportation, 2026 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Building and Construction
Building and ConstructionEngineering