文献类型：期刊文献

英文题名：An Adaptive Spatiotemporal Graph Convolutional Method for Highway Traffic Flow Prediction Based on Multi-Period Modalities

作者：Li, Guozheng[1,2];Wu, Baijing[1];Gao, Ke[1];Yan, Guanghui[1]

第一作者：李国正;Li, Guozheng

通信作者：Yan, GH[1]

机构：[1]Lanzhou Jiaotong Univ, Sch Elect & Informat Engn, Lanzhou 730070, Peoples R China;[2]Gansu Univ Tradit Chinese Med, Informat Engn Coll, Lanzhou 730013, Peoples R China

第一机构：Lanzhou Jiaotong Univ, Sch Elect & Informat Engn, Lanzhou 730070, Peoples R China

通信机构：[1]corresponding author), Lanzhou Jiaotong Univ, Sch Elect & Informat Engn, Lanzhou 730070, Peoples R China.

年份：2026

卷号：8

期号：6

外文期刊名：VEHICLES

收录：EI(收录号：20262620994192);Scopus(收录号：2-s2.0-105043117662);WOS:【ESCI(收录号:WOS:001803813300001)】；

基金：This document is supported by National Natural Science Foundation of China under Grant 624661032, Project Fund of Gansu Water Resources Research Institute under Grant LZJT524289, and the Gansu Provincial Department of Education "Innovation Star" Project for Outstanding Postgraduates under Grant 2026CXZX-633.

语种：英文

外文关键词：traffic flow prediction; spatiotemporal graph convolution; time series graph; adaptive; attention

摘要：To address the limited prediction accuracy caused by neglecting the inherent periodicity of spatiotemporal traffic flows during spatial feature extraction, this study develops an adaptive spatiotemporal graph convolutional method for highway traffic flow prediction. Firstly, an adaptive temporal graph generation layer with multiple time periods is constructed to dynamically generate traffic flow temporal graphs with rich representations, enabling accurate characterization of spatiotemporal traffic patterns. Secondly, a lightweight Transformer architecture is introduced to design an efficient feature extraction module, which refines both global and local spatiotemporal variations as well as their interactions. Finally, a multi-head self-attention module integrating different temporal scales is designed to capture the intrinsic correlations and dynamic dependencies across multi-scale traffic data, thereby enhancing prediction accuracy and generalization capability. Extensive experiments on two publicly available datasets, PEMSBAY and PEMSM, demonstrate the effectiveness of the proposed method. Compared with the baseline approaches, the proposed model achieves average reductions of 14% in MAE, 19% in MAPE, and 15% in RMSE. These results indicate that the proposed framework improves forecasting accuracy and provides a reliable methodological foundation for intelligent transportation systems.