City-scale synthetic individual-level vehicle trip data

Area of Science:

• Transportation Science
• Urban Planning
• Data Science

Background:

• Individual-level vehicle trip data is crucial for understanding urban traffic dynamics.
• Existing trip data is often inaccessible to researchers due to privacy concerns.
• There is an urgent need for privacy-preserving, accessible urban mobility data.

Purpose of the Study:

• To generate a city-scale synthetic individual-level vehicle trip dataset.
• To balance data availability with robust privacy protection for trip data.
• To validate the performance and reliability of the synthetic dataset.

Main Methods:

• Generation of synthetic individual trip data based on historical trip records.
• Implementation of privacy-preserving techniques to protect individual mobility information.
• Extensive experimental validation across various dimensions and granularities.

Main Results:

• The synthetic dataset maintains consistency with real (historical) data at an aggregated level.
• The generated individual trip data is deemed reasonable and useful from an individual perspective.
• Experimental results demonstrate the performance and reliability of the synthetic data.

Conclusions:

• The developed synthetic trip dataset successfully balances data privacy and availability.
• This synthetic data offers a viable solution for transportation research requiring individual-level trip information.
• Users can confidently utilize the synthetic data for various transportation analysis tasks.