ESTNet: Embedded Spatial-Temporal Network for Modeling Traffic Flow Dynamics

Guiyang Luo

doi:10.1109/TITS.2022.3167019

ESTNet: Embedded Spatial-Temporal Network for Modeling Traffic Flow Dynamics

2022-10-01

61

PRE

AI

DOI：10.1109/TITS.2022.3167019

Original

Original request for help

Save

Abstract

En 中文

Accurate spatial-temporal prediction is a fundamental building block of many real-world applications such as traffic scheduling and management, environment policy making, and public safety. This problem is still challenging due to nonlinear, complicated, and dynamic spatial-temporal dependencies. To address these challenges, we propose a novel embedded spatial-temporal network (ESTNet), which extracts efficient features to model the dynamic correlations and then exploits three-dimension convolution to synchronously model the spatial-temporal dependencies. Specifically, we propose multi-range graph convolution networks for extracting multi-scale static features from the fine-grained road network. Meanwhile, dynamic features are extracted from real-time traffic using a gated recurrent unit network. These features can be applied to identify the dynamic and flexible correlations among sensors and make it possible to exploit a three-dimension convolution unit (3DCon) to simultaneously model the spatial-temporal dependencies. Furthermore, we propose a residual network by stacking multiple 3DCon to capture the nonlinear and complicated dependencies. The effectiveness and superiority of ESTNet are verified on two real-world datasets, and experiments show ESTNet outperforms the state-of-the-art with a significant margin. The code and models will be publicly available.

Keywords:

Roads

Correlation

Feature extraction

Sensors

Deep learning

Convolution

Sensor phenomena and characterization

Traffic forecasting

graph convolutional network

spatial-temporal networks

ESTNet: Embedded Spatial-Temporal Network for Modeling Traffic Flow Dynamics

Abstract

Journal

Organization