Uncertainty-Aware Trip Purpose Inference from GPS Trajectories via POI Semantic Zones and Pareto Calibration

2026-05-02

AI Summary

Inferring trip purposes from GPS trajectories is challenged by missing labels, location noise, incomplete POI coverage, and behavioral heterogeneity. This work proposes a weakly supervised framework that, for the first time, integrates POI semantic zoning, distance-weighted spatial likelihood, and uncertainty-aware modeling to distinguish between essential and non-essential activities. A multi-stage Pareto optimization strategy is designed to jointly minimize the distributional discrepancies—measured by Jensen-Shannon divergence (JSD)—between inferred results and survey-based statistics across activity type, start time, and duration, without requiring manual annotations. Evaluated on 81 million staypoints in Los Angeles, the method achieves significant improvements in inference accuracy and reliability, reducing JSD by 23%, 48%, and 12% respectively for the three dimensions.

Abstract

Large-scale GPS trajectory data offer rich observations of human mobility, yet assigning trip purposes to detected stops remains challenging due to the absence of individual-level ground truth, spatial uncertainty from GPS noise and incomplete points of interest (POIs) coverage, and fundamental behavioral differences across trip purposes. We propose a weakly supervised framework integrating neighborhood-level POI semantic zones with distance-weighted spatial likelihoods, differentiated inference strategies for mandatory and non-mandatory activities, and a multi-phase Pareto optimization that jointly minimizes distributional divergence from household travel survey statistics and maximizes inference reliability without requiring annotated labels. Evaluated on over 81 million staypoints in Los Angeles, the framework reduces activity type frequency Jensen-Shannon distance (JSD) by 23%, start time JSD by 48%, and duration JSD by 12% respectively relative to a comparable baseline. The proposed approach provides a scalable and uncertainty-aware path from raw GPS trajectories to semantically annotated mobility data for travel demand modeling and transportation policy analysis.

Problem

• trip purpose inference
• GPS trajectories
• spatial uncertainty
• POI coverage
• weak supervision

Innovation

• Uncertainty-Aware Inference
• POI Semantic Zones
• Weakly Supervised Learning
• Pareto Calibration
• Trip Purpose Inference