Deep Spatial–Temporal 3D Convolutional Neural Networks for Traffic Data Forecasting

By Shengna Guo, Youfang Lin, Shijie Li, Zhaoming Chen, Huaiyu Wan. IEEE transactions on intelligent transportation systems (Print), 2019

385 citations recorded by the source corpus.

Reliable traffic prediction is critical to improve safety, stability, and efficiency of intelligent transportation systems. However, traffic prediction is a very challenging problem because traffic data are a typical type of spatio-temporal data, which simultaneously shows correlation and heterogeneity both in space and time. Most existing works can only capture the partial properties of traffic data and even assume that the effect of correlation on traffic prediction is globally invariable, resulting in inadequate modeling and unsatisfactory prediction performance. In this paper, we propose a novel end-to-end deep learning model, called ST-3DNet, for traffic raster data prediction. ST-3DNet introduces 3D convolutions to automatically capture the correlations of traffic data in both spatial and temporal dimensions. A novel recalibration (Rc) block is proposed to explicitly quantify the difference of the contributions of the correlations in space. Considering two kinds of temporal properties of traffic data, i.e., local patterns and long-term patterns, ST-3DNet employs two components consisting of 3D convolutions and Rc blocks to, respectively, model the two kinds of patterns and then aggregates them together in a weighted way for the final prediction. The experiments on several real-world traffic datasets, viz., traffic congestion data and crowd flows data, demonstrate that our ST-3DNet outperforms the state-of-the-art baselines.

Subfields: Building and Construction, Control and Systems Engineering, Ocean Engineering

View Paper: https://www.semanticscholar.org/paper/9781b19f7f737a80c1ca034d9a2792c7a2525a6b

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Building and Construction

In Control and Systems Engineering

Citations in the corpus

Artificial Intelligence for the Metaverse: A Survey (2022, methodology): “A supervised learning framework by combining CNN and LSTM with two-stage training mechanism [116] Forecasting intelligent cellular traffic.”
Traffic Graph Convolutional Recurrent Neural Network: A Deep Learning Framework for Network-Scale Traffic Learning and Forecasting (2018, background): “Recent studies [41], [44], [45] also attempted to convert traffic state data into three-dimensional (3D) matrices and use the 3D convolutional network to extract more effective features.”
High-Order Graph Convolutional Recurrent Neural Network: A Deep Learning Framework for Network-Scale Traffic Learning and Forecasting (2018, background): “Recent studies [42][45][46] also attempted to convert traffic state data into three-dimensional (3D) matrices and use the 3D convolutional network to extract more effective features.”
Learning Dynamics and Heterogeneity of Spatial-Temporal Graph Data for Traffic Forecasting (2021, methodology): “In particular, the proposals [21], [22], [23], [26], [32], [33], [34], [35] partition the region into 2D or 3D cells,”
Spatial-Temporal Synchronous Graph Convolutional Networks: A New Framework for Spatial-Temporal Network Data Forecasting (2020, methodology): “DCRNN, STGCN, ASTGCN(r), STG2Seq and our STSGCN all take advantages of spatial information, so they have better performance than the methods only for time series prediction.”