ESTNet: Embedded Spatial-Temporal Network for Modeling Traffic Flow Dynamics
- 13 May 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 23 (10) , 19201-19212
Abstract
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
Funding Information
- National Natural Science Foundation of China (62102041, 61876023, 61902035)
This publication has 36 references indexed in Scilit:
- Learning from Multiple Cities: A Meta-Learning Approach for Spatial-Temporal Prediction2019
- Deep and Embedded Learning Approach for Traffic Flow Prediction in Urban InformaticsIEEE Transactions on Intelligent Transportation Systems, 2019
- Flow Prediction in Spatio-Temporal Networks Based on Multitask Deep LearningIEEE Transactions on Knowledge and Data Engineering, 2019
- An End-to-End Load Balancer Based on Deep Learning for Vehicular Network Traffic ControlIEEE Internet of Things Journal, 2018
- Cooperative vehicular content distribution in edge computing assisted 5G-VANETChina Communications, 2018
- Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting2018
- Consensus Ensemble System for Traffic Flow PredictionIEEE Transactions on Intelligent Transportation Systems, 2018
- Short-term traffic flow prediction with LSTM recurrent neural network2017
- Short-term traffic flow prediction with Conv-LSTM2017
- LINE2015