Multistep Traffic Speed Prediction from Spatial–Temporal Dependencies Using Graph Neural Networks

Wu, Xuesong; Fang, Jie; Liu, Zhijia; Wu, Xiongwei

doi:10.1061/jtepbs.0000600

Cited by 6 publications

(1 citation statement)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Zhang et al focused on obtaining the richer spatial information by introducing the content similarity adjacency matrix, the transportation neighborhood adjacency matrix, and the graph betweenness adjacency matrix to represent spatial correlations in traffic flow graph as the geography correlation, region similarity, and the road connectivity [34]. Li et al proposed a multiscale graph convolutional layer to assign different weights to three kinds of spatial dependencies [88]. The three spatial features referred to the normalized adjacency matrix with the self-connected unit that is represented by the geographic adjacency matrix, the extraction of hidden spatial dependencies that are represented by the self-adaptive matrix, and the similarity of the traffic patterns that is represented by the similarity matrix.…”

Section: B Feature Engineering On Spatial Perspectivementioning

confidence: 99%

Spatio-Temporal Feature Engineering for Deep Learning Models in Traffic Flow Forecasting

Mu,

Aljeri,

Boukerche

2024

IEEE Access

View full text Add to dashboard Cite

In the past decade, modern transportation systems have employed various cutting-edge deeplearning approaches for traffic flow prediction. Due to its significant temporal correlations, researchers have mainly focused on extracting temporal features from traffic flow data. As a result, time-series models based on deep learning methods like Gated Recurrent Unit (GRU), Long-Term Short-Term Memory (LSTM), and Temporal Convolutional Networks (TCN) have been introduced as solutions for traffic flow prediction. However, the spatial features of the road network have also shown an impact on the prediction, leading to the application of deep learning methods on spatial dependency modeling for this problem. This paper defines the traffic flow forecasting problem, considering both time-series information with and without spatial information and the corresponding techniques of current solutions to depict spatio-temporal traffic dependency. We propose a new taxonomy of spatial and temporal dependencies in the fine-grained subcategory and the methods depicting them based on neural network-based models. Furthermore, we highlight the architecture of spatial and temporal ensembles in Spatio-temporal modelling based on the finegrained categories obtained. We point out several open issues and future directions of traffic flow forecasting, such as graph reconstruction, temporal and spatial information data balance, and multi-model spatial and temporal correlations.

show abstract

Section: B Feature Engineering On Spatial Perspectivementioning

confidence: 99%