ST-CopulaGNN : A Multi-View Spatio-Temporal Graph Neural Network for Traffic Forecasting

Pitikorn Khlaisamniang, S. Phoomvuthisarn
{"title":"ST-CopulaGNN : A Multi-View Spatio-Temporal Graph Neural Network for Traffic Forecasting","authors":"Pitikorn Khlaisamniang, S. Phoomvuthisarn","doi":"10.1145/3603719.3603740","DOIUrl":null,"url":null,"abstract":"Modern cities heavily rely on complex transportation, making accurate traffic speed prediction crucial for traffic management authorities. Classical methods, including statistical techniques and traditional machine learning techniques, fail to capture complex relationships, while deep learning approaches may have weaknesses such as error accumulation, difficulty in handling long sequences, and overlooking spatial correlations. Graph neural networks (GNNs) have shown promise in extracting spatial features from non-Euclidean graph structures, but they usually initialize the adjacency matrix based on distance and may fail to detect hidden statistical correlations. The choice of correlation measure can have a significant impact on the resulting adjacency matrix and the effectiveness of graph-based models. This paper proposes a novel approach for accurately forecasting traffic patterns by utilizing a multi-view spatio-temporal graph neural network that captures data from both realistic and statistical domains. Unlike traditional correlation measures such as Pearson correlation, copula models are utilized to extract hidden statistical correlations and construct multivariate distribution functions to obtain the correlation relationship among traffic nodes. A two-step approach is adopted, which involves selecting and testing different types of bivariate copulas to identify the ones that best fit the traffic data, and utilizing these copulas to create multi-weight adjacency matrices. The second step involves utilizing a graph convolutional network to extract spatial information and capturing temporal trends using dilated causal convolutions. The proposed ST-CopulaGNN model outperforms other models in spatio-temporal traffic forecasting that solely rely on distance-based adjacency matrices, such as DCRNN and Graph WaveNet. It also achieves the lowest MAE for 30 and 60 minutes ahead and the lowest MAPE for 15 minutes ahead on the PEMS-BAY dataset. The model incorporates copulas, and the study explores copula function selection and the impact of using paired time-series with a time lag. The findings suggest that using copula-based adjacency matrix configurations, particularly those including Clayton and Gumbel copulas, can enhance traffic forecasting accuracy.","PeriodicalId":314512,"journal":{"name":"Proceedings of the 35th International Conference on Scientific and Statistical Database Management","volume":"58 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 35th International Conference on Scientific and Statistical Database Management","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3603719.3603740","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Modern cities heavily rely on complex transportation, making accurate traffic speed prediction crucial for traffic management authorities. Classical methods, including statistical techniques and traditional machine learning techniques, fail to capture complex relationships, while deep learning approaches may have weaknesses such as error accumulation, difficulty in handling long sequences, and overlooking spatial correlations. Graph neural networks (GNNs) have shown promise in extracting spatial features from non-Euclidean graph structures, but they usually initialize the adjacency matrix based on distance and may fail to detect hidden statistical correlations. The choice of correlation measure can have a significant impact on the resulting adjacency matrix and the effectiveness of graph-based models. This paper proposes a novel approach for accurately forecasting traffic patterns by utilizing a multi-view spatio-temporal graph neural network that captures data from both realistic and statistical domains. Unlike traditional correlation measures such as Pearson correlation, copula models are utilized to extract hidden statistical correlations and construct multivariate distribution functions to obtain the correlation relationship among traffic nodes. A two-step approach is adopted, which involves selecting and testing different types of bivariate copulas to identify the ones that best fit the traffic data, and utilizing these copulas to create multi-weight adjacency matrices. The second step involves utilizing a graph convolutional network to extract spatial information and capturing temporal trends using dilated causal convolutions. The proposed ST-CopulaGNN model outperforms other models in spatio-temporal traffic forecasting that solely rely on distance-based adjacency matrices, such as DCRNN and Graph WaveNet. It also achieves the lowest MAE for 30 and 60 minutes ahead and the lowest MAPE for 15 minutes ahead on the PEMS-BAY dataset. The model incorporates copulas, and the study explores copula function selection and the impact of using paired time-series with a time lag. The findings suggest that using copula-based adjacency matrix configurations, particularly those including Clayton and Gumbel copulas, can enhance traffic forecasting accuracy.
ST-CopulaGNN:一种用于交通预测的多视图时空图神经网络
现代城市严重依赖复杂的交通,因此准确的交通速度预测对交通管理部门至关重要。包括统计技术和传统机器学习技术在内的经典方法无法捕捉复杂的关系,而深度学习方法可能存在诸如错误积累、难以处理长序列以及忽略空间相关性等弱点。图神经网络(gnn)在从非欧几里得图结构中提取空间特征方面显示出前景,但它们通常基于距离初始化邻接矩阵,并且可能无法检测到隐藏的统计相关性。相关度量的选择对生成的邻接矩阵和基于图的模型的有效性有重要影响。本文提出了一种利用从现实和统计领域捕获数据的多视图时空图神经网络来准确预测交通模式的新方法。与Pearson相关等传统的相关度量不同,利用copula模型提取隐含的统计相关性,构建多元分布函数,获得交通节点之间的相关关系。该方法采用两步法,即选择和测试不同类型的二元copula,以识别最适合交通数据的copula,并利用这些copula创建多权重邻接矩阵。第二步涉及利用图卷积网络提取空间信息,并使用扩展因果卷积捕获时间趋势。ST-CopulaGNN模型在仅依赖基于距离的邻接矩阵的时空交通预测方面优于其他模型,如DCRNN和Graph WaveNet。它还在PEMS-BAY数据集上实现了30分钟和60分钟前的最低MAE,以及15分钟前的最低MAPE。该模型引入了联结函数,并探讨了联结函数的选择和使用带时滞的配对时间序列的影响。研究结果表明,使用基于copula的邻接矩阵配置,特别是包括Clayton和Gumbel copula的邻接矩阵配置,可以提高交通预测的准确性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信