Spatio-temporal graph convolutional network for stochastic traffic speed imputation

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

4 Citations (Scopus)
62 Downloads (Pure)

Abstract

The rapid increase of traffic data generated by different sensing systems opens many opportunities to improve transportation services. An important opportunity is to enable stochastic routing that computes the arrival time probabilities for each suggested route instead of only the expected travel time. However, traffic datasets typically have many missing values, which prevents the construction of stochastic speeds. To address this limitation, we propose the Stochastic Spatio-Temporal Graph Convolutional Network (SST-GCN) architecture that accurately imputes missing speed distributions in a road network. SST-GCN combines Temporal Convolutional Networks and Graph Convolutional Networks into a single framework to capture both spatial and temporal correlations between road segments and time intervals. Moreover, to cope with datasets with many missing values, we propose a novel self-adaptive context-aware diffusion process that regulates the propagated information around the network, avoiding the spread of false information. We extensively evaluate the effectiveness of SST-GCN on real-world datasets, showing that it achieves from 4.6% to 50% higher accuracy than state-of-the-art baselines using three different evaluation metrics. Furthermore, multiple ablation studies confirm our design choices and scalability to large road networks.

Original languageEnglish
Title of host publication30th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2022
EditorsMatthias Renz, Mohamed Sarwat, Mario A. Nascimento, Shashi Shekhar, Xing Xie
PublisherAssociation for Computing Machinery (ACM)
Publication date1 Nov 2022
Pages1-12
Article number14
ISBN (Electronic)9781450395298
DOIs
Publication statusPublished - 1 Nov 2022
Event30th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, SIGSPATIAL GIS 2022 - Seattle, United States
Duration: 1 Nov 20224 Nov 2022

Conference

Conference30th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, SIGSPATIAL GIS 2022
Country/TerritoryUnited States
CitySeattle
Period01/11/202204/11/2022
SponsorApple, Esri, Google, Oracle, Wherobots
SeriesGIS: Proceedings of the ACM International Symposium on Advances in Geographic Information Systems

Bibliographical note

Publisher Copyright:
© 2022 Owner/Author.

Keywords

  • data imputation
  • graph convolutional networks
  • spatio-temporal

Fingerprint

Dive into the research topics of 'Spatio-temporal graph convolutional network for stochastic traffic speed imputation'. Together they form a unique fingerprint.

Cite this