Integrating trajectory data and demographic characteristics: a trajectory semantic model for predicting travel flow and conducting interaction analysis

Changjian Liu, Shuhui Gong, Hui Su, Jifeng He

Abstract: With urbanisation and population growth, understanding spatial interactions in cities is increasingly important for urban management. However, anonymous trajectory data often lack semantic details, limiting the ability to predict travel flow and understand mobility behavior. This paper proposes a Semantic-Integrated Mobility Trajectory Model (SMTM), which integrates social media check-in data, remote sensing imagery, and taxi trajectory data to predict spatial interaction intensity. The model uses deep learning components to extract demographic, visual, and trajectory-related information, and supports interaction analysis for understanding the semantic factors that influence urban travel flows.