@article{ZHANG2025, 
author = {Jin ZHANG and Yu PI and Cheng SUN and Yehua WEI and Fei YU and Wei YAO},
title = {Spatial-temporal encoder-decoder model for traffic flow prediction},
year = {2025},
journal = {Journal of National University of Defense Technology},
volume = {47},
number = {3},
pages = {173-182},
keywords = {attention mechanism, graph convolutional neural network, traffic flow prediction, encoder-decoder},
url = {https://www.sciopen.com/article/10.11887/j.cn.202503018},
doi = {10.11887/j.cn.202503018},
abstract = {In order to solve the problem that many traffic flow prediction research methods are unable to comprehensively explore the dynamic hidden correlations in traffic data, the dynamic spatio-temporal variation characteristics were studied and an encoder-decoder-based traffic prediction model was proposed. In the model, both encoder and decoder mainly consisted of multi-head spatio-temporal attention mechanism modules, and a connection attention mechanism was added in between to analyze the spatio-temporal correlations of the road network. The model also used a dynamic embedding module consisting of a combination of both spatio-temporal embedding coding and adaptive graph convolution to analyze the dynamic and static information of nodes. Experiments on two real datasets demonstrate that the spatio-temporal model outperform other models for long- and short-term traffic prediction. Thus, the spatio-temporal encoder-decoder model can effectively handle complex spatio-temporal sequences and improve the traffic flow prediction accuracy.}
}