Journal of Computer Applications ›› 2023, Vol. 43 ›› Issue (9): 2760-2765.DOI: 10.11772/j.issn.1001-9081.2022081146

• Artificial intelligence • Previous Articles     Next Articles

Spatial-temporal traffic flow prediction model based on gated convolution

Li XU, Xiangyuan FU(), Haoran LI   

  1. College of Information Engineering,Chang’an University,Xi’an Shaanxi 710064,China
  • Received:2022-08-04 Revised:2022-11-03 Accepted:2022-11-14 Online:2023-01-11 Published:2023-09-10
  • Contact: Xiangyuan FU
  • About author:XU Li, born in 1977, Ph. D., associate professor. Her research interests include object detection.
    LI Haoran, born in 1998, M. S. candidate. His research interests include three-dimensional reconstruction of infrastructure.
  • Supported by:
    National Key Research and Development Program of China(2019YFE0108300);National Natural Science Foundation of China(62001058)


徐丽, 符祥远(), 李浩然   

  1. 长安大学 信息工程学院,西安 710064
  • 通讯作者: 符祥远
  • 作者简介:徐丽(1977—),女,江西上饶人,副教授,博士,主要研究方向:目标检测
  • 基金资助:


Concerning the problems that the existing traffic flow prediction models cannot accurately capture the spatio-temporal features of traffic data, and most models show good prediction performance in single-step prediction, and the prediction performance of models in multi-step prediction is not ideal, a Spatio-Temporal Traffic Flow Prediction Model based on Gated Convolution (GC-STTFPM) was proposed. Firstly, the Graph Convolution Network (GCN) combining with Gated Recurrent Unit (GRU) was used to capture the spatio-temporal features of traffic flow data. Then, a method of splicing and filtering the original data and spatio-temporal feature data by using gated convolution unit was proposed to verify the validity of spatio-temporal feature data. Finally, GRU was used as the decoder to make accurate and reliable prediction of future traffic flow. Experimental results on traffic dataset of Los Angeles Highway show that compared with Attention based Spatial-Temporal Graph Neural Network (ASTGNN) and Diffusion Convolutional Recurrent Neural Network (DCRNN) under single step prediction (5 min), GC-STGCN model has the Mean Absolute Error (MAE) reduced by 5.9% and 9.9% respectively, and the Root Mean Square Error (RMSE) reduced by 1.7% and 5.8% respectively. At the same time, it is found that the prediction accuracy of this model is better than those of most existing benchmark models under three multi-step scales of 15, 30 and 60 min, demonstrating strong adaptability and robustness.

Key words: intelligent transportation, time series, encoder, decoder, Graph Convolution Network (GCN), Gated Recurrent Unit (GRU)


针对现有的交通流预测模型未能精确捕获交通数据的时空特征,以及大部分模型都是在单步预测中体现出良好的预测性能,在多步预测中模型的预测性能显得并不理想的问题,提出了一种基于门控卷积的时空交通流预测模型(GC-STTFPM)。首先,利用图卷积网络(GCN)结合门控循环单元(GRU)来捕获交通流数据的时空特征;然后提出了一种利用卷积门控单元对原始数据和时空特征数据进行拼接与筛选处理的方法来对时空特征数据的有效性进行校验;最后,将GRU作为解码器来对未来交通流作出准确可靠的预测。在洛杉矶公路的交通数据集上的实验结果表明,GC-STTFPM在单步预测(5 min)中与基于注意力的时空图神经网络(ASTGNN)和扩散卷积递归神经网络(DCRNN)相比,平均绝对误差(MAE)分别降低了5.9%和9.9%,均方根误差(RMSE)分别降低了1.7%和5.8%。同时,GC-STTFPM在15、30、60 min三个多步尺度下的预测精度优于大多数现有基准模型,具有较强的适应性和鲁棒性。

关键词: 智能交通, 时间序列, 编码器, 解码器, 图卷积网络, 门控循环单元

CLC Number: