Human mobility prediction from region functions with taxi trajectories

Area of Science:

• Urban Planning
• Human Mobility Studies
• Geographic Information Science

Background:

• Increasing urban traffic congestion highlights a gap in understanding collective human mobility's link to urban planning.
• The influence of region functions on human mobility is crucial for business planning but remains poorly understood.

Purpose of the Study:

• To investigate the association between urban region functions and human mobility patterns.
• To develop a predictive model for human mobility based on region characteristics.

Main Methods:

• A linear regression model was employed to predict traffic flows in Beijing.
• The model utilized a 'bag of Points of Interest' (POIs) as input data.
• Sparse representation techniques were used to solve the predictor.

Main Results:

• The model achieved an average prediction precision exceeding 74% for traffic flow.
• Different types of POIs demonstrated varying contributions to the prediction model.
• The findings indicate specific factors and mechanisms through which region functions attract human movement.

Conclusions:

• Understanding the relationship between region functions and human mobility is vital for effective urban planning.
• Predictive human mobility models can inform the design of new urban regions and the strategic placement of region functions.