基于图耦合残差流匹配的时空交通流量概率预测模型研究

沈文文; 鲍福光; ‌琚春华‌

doi:10.11959/j.issn.1000-0801.DXKX260236

您当前的位置：

首页 >

文章列表页 >

基于图耦合残差流匹配的时空交通流量概率预测模型研究

研究与开发 | 更新时间：2026-07-21

- 基于图耦合残差流匹配的时空交通流量概率预测模型研究
- Spatiotemporal Traffic Flow Probabilistic Prediction Model Based on Graph-Coupled Residual Flow Matching
- 电信科学 2026年
- 作者机构：
  
  1.浙江工商大学管理工程与电子商务学院，浙江杭州 3100018
  2.浙江工商大学现代商贸研究中心，浙江杭州 310018
- 作者简介：
  
  沈文文（2005-），女，浙江工商大学在读，主要研究方向为数据挖掘、深度学习。
  鲍福光，bfg@zjgsu.edu.cn
- 基金信息：
  
  国家自然科学基金项目(71571162);浙江省自然科学基金资助项目(LQ20G010002)
- DOI：10.11959/j.issn.1000-0801.DXKX260236
  中图分类号： TP181
- 收稿：2026-04-17，
  
  修回：2026-06-19，
  
  录用：2026-07-03，
- 稿件说明：
移动端阅览
沈文文, 鲍福光, ‌琚春华‌. 基于图耦合残差流匹配的时空交通流量概率预测模型研究[J/OL]. 电信科学, 2026.

SHEN Wenwen, BAO Fuguang, JU Chunhua. Spatiotemporal Traffic Flow Probabilistic Prediction Model Based on Graph-Coupled Residual Flow Matching[J/OL]. Telecommunications Science, 2026.
沈文文, 鲍福光, ‌琚春华‌. 基于图耦合残差流匹配的时空交通流量概率预测模型研究[J/OL]. 电信科学, 2026. DOI： 10.11959/j.issn.1000-0801.DXKX260236.

SHEN Wenwen, BAO Fuguang, JU Chunhua. Spatiotemporal Traffic Flow Probabilistic Prediction Model Based on Graph-Coupled Residual Flow Matching[J/OL]. Telecommunications Science, 2026. DOI： 10.11959/j.issn.1000-0801.DXKX260236.

摘要

为兼顾交通流点预测精度与概率校准表现，提出图耦合残差流匹配（ST-RFM）框架，将连续流匹配引入图结构时序建模。首先，设计多尺度时序条件模块，解耦提取趋势、周期与波动特征；其次，构建图耦合反应-扩散向量场，在生成动力学内部显式分离节点演化与空间校正，增强对路网动态演化的捕捉能力；最后，采用残差流匹配目标，通过锚定最近观测学习变化量，保留连续性先验。在 PEMS03、04 和 08 数据集上的实验结果表明，该算法在维持高精度点预测的同时显著提升了概率校准性能，其中 PEMS08 的 CRPS 和 MIS95 指标分别降低 3.8% 与 43.9%，该研究为生成式时空交通预测中的不确定性量化提供了有效的技术方案。

Abstract

To strike a balance between point prediction accuracy and probabilistic calibration performance in traffic flow forecasting

a Graph-Coupled Residual Flow Matching (ST-RFM) framework was proposed

which integrated continuous flow matching into graph-structured spatiotemporal modeling. First

a lightweight multi-scale temporal condition module was designed to decouple and extract trend

periodicity

and volatility features. Second

a graph-coupled reaction-diffusion vector field was constructed to explicitly separate node-level evolution and spatial correction within the generative dynamics

thereby enhancing the capability to capture the dynamic evolution of road networks. Finally

a residual flow matching objective was adopted to learn future variations by anchoring to recent observations

which effectively preserved the continuity prior of traffic evolution. Experimental results on PEMS03

and 08 datasets demonstrated that the proposed algorithm significantly improved probabilistic calibration performance while maintaining high point prediction accuracy. Specifically

the CRPS and MIS95 metrics on PEMS08 were reduced by 3.8% and 43.9%

respectively. This research provides an effective technical solution for uncertainty quantification in generative spatiotemporal traffic forecasting.

关键词

Keywords

references

廖熙雯 , 冷甦鹏 , 明昱君 , 等 . 基于数字孪生的城市交通流智能预测与导引策略 [J ] . 电信科学 , 2023 , 39 ( 3 ): 70 - 79 .

LIAO X W , LENG S P , MING Y J , et al . Digital twin based intelligent urban traffic forecasting and guidance strategy [J ] . Telecommunications Science , 2023 , 39 ( 3 ): 70 - 79 .

熊章友 , 李卫军 , 朱晓娟 , 等 . 基于深度学习的短时交通流预测研究综述 [J ] . 计算机工程与应用 , 2025 , 61 ( 11 ): 67 - 82 .

XIONG Z Y , LI W J , ZHU X J , et al . Short-term traffic flow prediction based on deep learning [J ] . Computer Engineering and Applications , 2025 , 61 ( 11 ): 67 - 82 .

AN H , LI Y . Generative AI for intelligent transportation systems: Road transportation perspective [J ] . ACM Computing Surveys , 2025 , 57 ( 12 ): 1 - 45 .

WILLIAMS B M , HOEL L A . Modeling and forecasting vehicular traffic flow as a seasonal ARIMA process: Theoretical basis and empirical results [J ] . Journal of Transportation Engineering , 2003 , 129 ( 6 ): 664 - 672 .

CHANDRA S R , AL-DEEK H . Predictions of freeway traffic speeds and volumes using vector autoregressive models [J ] . Journal of Intelligent Transportation Systems , 2009 , 13 ( 2 ): 53 - 72 .

XU Y , HAN L , ZHU T , et al . Generic Dynamic Graph Convolutional Network for traffic flow forecasting [J ] . Information Fusion , 2023 , 100 : 101946 .

ZHANG X , CHEN X , TANG H , et al . AdpSTGCN: Adaptive spatial-temporal graph convolutional network for traffic forecasting [J ] . Knowledge-Based Systems , 2024 , 301 : 112295 .

张雄涛 , 郑景玉 , 申情 , 等 . 基于混合图卷积的多通道时空交通流预测模型 [J ] . 电信科学 , 2023 , 39 ( 09 ): 97 - 110 .

ZHANG Xiong-tao , ZHENG Jing-yu , SHEN Qing , et al . Multi-channel Spatial-temporal Traffic Flow Prediction Based on Hybrid Static-dynamic Graph Convolution [J ] . Telecommunications Science ， 2023 ， 39 ( 09 ) : 97 － 110 ．

SALINAS D , FLUNKERT V , GASTHAUS J , et al . DeepAR: Probabilistic forecasting with autoregressive recurrent networks [J ] . International Journal of Forecasting , 2020 , 36 ( 3 ): 1181 - 1191 .

WANG B , VU H L , KIM I , et al . Distributional prediction of short-term traffic using neural networks [J ] . Engineering Applications of Artificial Intelligence , 2023 , 126 : 107061 .

SENGUPTA A , MONDAL S , DAS A , et al . A Bayesian approach to quantifying uncertainties and improving generalizability in traffic prediction models [J ] . Transportation Research Part C: Emerging Technologies , 2024 , 162 : 104585 .

FU J , ZHOU W , CHEN Z . Bayesian graph convolutional network for traffic prediction [J ] . Neurocomputing , 2024 , 582 : 127507 .

KHALED A , TAG ELSIR A M , SHEN Y . TFGAN: Traffic forecasting using generative adversarial network with multi-graph convolutional network [J ] . Knowledge-Based Systems , 2022 , 249 : 108990 .

LIU M Z , HUANG H , FENG H , et al . PriSTI: A conditional diffusion framework for spatiotemporal imputation [C ] // 2023 IEEE 39th International Conference on Data Engineering (ICDE) . Piscataway : IEEE Press , 2023 : 1927 - 1939 .

WEN H M , LIN Y F , XIA Y T , et al . DiffSTG: Probabilistic spatio-temporal graph forecasting with denoising diffusion models [C ] // Proceedings of the 31st ACM International Conference on Advances in Geographic Information Systems . New York : ACM Press , 2023 : 1 - 12 .

KOLLOVIEH M , ANSARI A F , BOHLKE-SCHNEIDER M , et al . Predict, refine, synthesize: Self-guiding diffusion models for probabilistic time series forecasting [EB/OL ] . arXiv: 2307.11494 , 2023 .

LIN L , SHI D , HAN A , et al . SpecSTG: A fast spectral diffusion framework for probabilistic spatio-temporal traffic forecasting [EB/OL ] . arXiv: 2401.08119 , 2024 .

LIPMAN Y , CHEN R T Q , BEN-HAMU H , et al . Flow matching for generative modeling [C ] // Proceedings of the International Conference on Learning Representations . 2023 .

KOLLOVIEH M , LIENEN M , LUDKE D , et al . Flow matching with Gaussian process priors for probabilistic time series forecasting [EB/OL ] . arXiv: 2410.03024 , 2024 .

GAL Y , GHAHRAMANI Z . Dropout as a bayesian approximation: Representing model uncertainty in deep learning [C ] // International Conference on Machine Learning , New York : PMLR , 2016 : 1050 - 1059 .

KHOSRAVI A , NAHAVANDI S , CREIGHTON D , et al . Comprehensive review of neural network-based prediction intervals and new advances [J ] . IEEE Transactions on Neural Networks , 2011 , 22 ( 9 ): 1341 - 1356 .

AMINI A , SCHWARTING W , SOLEIMANY A , et al . Deep evidential regression [C ] // Proceedings of the 34th International Conference on Neural Information Processing Systems . Red Hook : Curran Associates, Inc. , 2020 : 14927 - 14937 .

RUBANOVA Y , CHEN R T , DUVENAUD D K . Latent ordinary differential equations for irregularly-sampled time series [C ] // Proceedings of the 33rd International Conference on Neural Information Processing Systems . Red Hook : Curran Associates, Inc. , 2019 : 1 - 11 .

FANG Z , LONG Q , SONG G , et al . Spatial-temporal graph ODE networks for traffic flow forecasting [C ] // Proceedings of the 27th ACM SIGKDD conference on knowledge discovery & data mining , New York : ACM Press , 2021 : 364 - 373 .

LI F , FENG J , YAN H , et al . Dynamic graph convolutional recurrent network for traffic prediction: Benchmark and solution [J ] . ACM Transactions on Knowledge Discovery from Data , 2023 , 17 ( 1 ): 1 - 21 .

LI M , ZHU Z . Spatial-temporal fusion graph neural networks for traffic flow forecasting [C ] // Proceedings of the AAAI conference on artificial intelligence , Palo Alto : AAAI Press , 2021 , 35 ( 5 ): 4189 - 4196 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

面向异常场景的分段注意与异常感知时空交通流预测网络

基于Transformer-双Q网络的太赫兹NOMA通信网络即时功率分配

企业AI智能体基础设施的层次化架构：基于云计算实践的分析框架

基于机器学习的SRv6动态性能优化方法研究

算网融合背景下的异构算力调度系统和应用