Reconstruction of human movement trajectories from large-scale low-frequency mobile phone data

Authors: Mingxiao Li, State Key Lab of Resources and Environmental Information System, Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Song Gao*, Geospatial Data Science Lab, Department of Geography, University of Wisconsin, Madison, Feng Lu, State Key Laboratory of Resources and Environmental Information System, Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Hengcai Zhang, State Key Laboratory of Resources and Environmental Information System, Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences
Topics: Geographic Information Science and Systems
Keywords: GeoAI, Deep Learning, Road Networks, GIS
Session Type: Paper
Day: 4/5/2019
Start / End Time: 3:05 PM / 4:45 PM
Room: Washington 6, Marriott, Exhibition Level
Presentation File: No File Uploaded


Understanding human mobility is significant in many fields such as geography, transportation, and public health. Due to the wide spatiotemporal coverage and low operational cost, mobile phone data have been recognized as a major source for human mobility research. However, because of the conflict between the data sparsity problem of mobile phone data and the requirement for fine-scale solutions, trajectory reconstruction is of considerable importance. Although this problem has been given initial study, existing methods rarely consider the effect of similarities among individuals and the patterns of missing data. To address this issue, we propose a multi-criterion data partitioning trajectory reconstruction (MDP-TR) method for large-scale mobile phone data. In the proposed method, the multi-criterion data partitioning (MDP) technique is used to measure the similarity among individuals in near real time and investigate the spatiotemporal patterns of missing data. With this technique, the trajectory reconstruction from mobile phone data is then conducted with machine learning models. We validated the method using a real mobile phone dataset in a large city. Results indicate that the MDP-TR method outperforms competing methods in both accuracy and robustness. We argue that the MDP-TR method can be effectively utilized for grasping highly dynamic human movement status and improving the spatiotemporal resolution of human mobility research.

Abstract Information

This abstract is already part of a session. View the session here.

To access contact information login