变分模态分解与自适应图卷积门控循环网络的交通流量组合预测模型  

A Combined Traffic Flow Prediction Model Based on Variational Mode Decomposition and Adaptive Graph Convolutional Gated Recurrent Network

作　　者：龚循强[1,2] 邱万锦 吕开云[1,2] 张通 张瑞[4] 罗升 GONG Xunqiang;QIU Wanjin;LÜKaiyun;ZHANG Tong;ZHANG Rui;LUO Sheng(Key Laboratory of Mine Environmental Monitoring and Improving Around Poyang Lake of Ministry of Natural Resources,East China University of Technology,Nanchang 330013,China;School of Surveying and Geoinformation Engineering,East China University of Technology,Nanchang 330013,China;Institute of Basic Geological Survey,Jiangxi Geological Survey and Exploration Institute,Nanchang 330025,China;State-Province Joint Engineering Laboratory of Spatial Information Technology for High-Speed Railway Safety,Southwest Jiaotong University,Chengdu 611756,China)

机构地区：[1]东华理工大学自然资源部环鄱阳湖区域矿山环境监测与治理重点实验室,江西南昌330013 [2]东华理工大学测绘与空间信息工程学院,江西南昌330013 [3]江西省地质调查勘查院基础地质调查所,江西南昌330025 [4]西南交通大学高速铁路安全运营空间信息技术国家地方联合工程实验室,四川成都611756

出　　处：《武汉大学学报（信息科学版）》2024年第12期2329-2341,共13页Geomatics and Information Science of Wuhan University

基　　金：国家自然科学基金(42101457);自然资源部环鄱阳湖区域矿山环境监测与治理重点实验室开放基金(MEMI-2021-2022-14)。

摘　　要：准确的交通流量预测可以有效地提高交通效率和安全性,是智慧交通系统的一个研究热点话题。然而,传统的静态图结构在捕捉交通流量的全局时空信息存在局限性,交通流量短时间内的波动造成流量的非平稳性也会影响交通流量预测的准确性。为此,提出了一种结合变分模态分解(variational mode decomposition,VMD)和自适应图卷积门控循环网络的交通流量预测模型。首先,考虑到交通流量的非平稳性,利用VMD对时间序列进行分解,得到平稳的本征模态函数(intrinsic mode function,IMF)交通流量分量。然后,模型通过自适应邻接矩阵和图卷积门控单元动态地学习节点IMF分量间复杂的时空特性,从而更好地表征交通流量的变化趋势。最后,重构模型对IMF分量的预测值,得到实际的交通流量预测结果。在PeMS04数据集的实验结果表明,所提模型在平均绝对误差、均方根误差和平均绝对百分比误差等指标上均优于基线次优模型,提升幅度超过33%,与消融模型相比,性能提升也达到15%以上。因此,所提模型在交通流量预测任务中具有显著的优势和应用前景。Objectives:Accurate traffic flow prediction plays a crucial role in enhancing traffic efficiency and safety,making it a prominent research focus in intelligent transportation systems.However,traditional static graph structures struggle to capture the global spatiotemporal dynamics of traffic flow,while short-term fluctuations in traffic introduce non-stationarity,further complicating accurate predictions.Methods:To ad-dress these challenges,this paper proposes a traffic flow prediction model that integrates variational mode decomposition(VMD)with an adaptive graph convolutional gated recurrent network.First,considering the non-stationarity of traffic flow,VMD is employed to decompose the time series into stable intrinsic mode function(IMF)components.Then,the model leverages an adaptive adjacency matrix and graph convolutional gated units to dynamically learn the complex spatiotemporal interactions among the IMF components,enabling a more precise characterization of traffic flow trends.Finally,the reconstructed model predicts the IMF components,yielding the overall traffic flow forecast.Results:The experiments conducted on the PeMS04 dataset demonstrate that the proposed model significantly outperforms baseline models in metrics such as mean absolute error,root mean square error,and mean absolute percentage error,achieving over 33%improvement.Compared to the ablation models,the performance of the proposed model improves over 15%.Conclusions:The results highlight the substantial advantages and the promising potential of the proposed model for applications in traffic flow prediction tasks.

关 键 词：智能交通 交通流量预测 变分模态分解 自适应图卷积网络 门控循环单元 

分 类 号：P237[天文地球—摄影测量与遥感] U491[天文地球—测绘科学与技术]