Dynamic Spatiotemporal Graph Convolutional Neural Networks for Traffic Data Imputation with Complex Missing Patterns

TL;DR

This paper introduces DSTGCN, a deep learning framework that captures dynamic spatiotemporal dependencies in traffic data to effectively impute missing values, especially under complex missing patterns.

Contribution

The paper proposes a novel DSTGCN model combining recurrent and graph convolutions with a graph structure estimation technique for dynamic traffic data imputation.

Findings

Outperforms state-of-the-art models across various missing patterns

Graph structure estimation improves model accuracy

Effective in complex missing scenarios

Abstract

Missing data is an inevitable and ubiquitous problem for traffic data collection in intelligent transportation systems. Despite extensive research regarding traffic data imputation, there still exist two limitations to be addressed: first, existing approaches fail to capture the complex spatiotemporal dependencies in traffic data, especially the dynamic spatial dependencies evolving with time; second, prior studies mainly focus on randomly missing patterns while other more complex missing scenarios are less discussed. To fill these research gaps, we propose a novel deep learning framework called Dynamic Spatiotemporal Graph Convolutional Neural Networks (DSTGCN) to impute missing traffic data. The model combines the recurrent architecture with graph-based convolutions to model the spatiotemporal dependencies. Moreover, we introduce a graph structure estimation technique to model the dynamic spatial dependencies from real-time traffic information and road network structure. Extensive experiments based on two public traffic speed datasets are conducted to compare our proposed model with state-of-the-art deep learning approaches in four types of missing patterns. The results show that our proposed model outperforms existing deep learning models in all kinds of missing scenarios and the graph structure estimation technique contributes to the model performance. We further compare our proposed model with a tensor factorization model and find distinct behaviors across different model families under different training schemes and data availability.