STSGAN: Spatial-Temporal Global Semantic Graph Attention Convolution Networks for Urban Flow Prediction
Accurate urban traffic flow prediction plays a vital role in Intelligent Transportation System (ITS). The complex long-term and long-range spatiotemporal correlations of traffic flow pose a significant challenge to the prediction task. Most current research methods focus only on spatial correlations...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-07-01
|
| Series: | ISPRS International Journal of Geo-Information |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2220-9964/11/7/381 |
| _version_ | 1797433505158791168 |
|---|---|
| author | Junwei Zhou Xizhong Qin Kun Yu Zhenhong Jia Yan Du |
| author_facet | Junwei Zhou Xizhong Qin Kun Yu Zhenhong Jia Yan Du |
| author_sort | Junwei Zhou |
| collection | DOAJ |
| description | Accurate urban traffic flow prediction plays a vital role in Intelligent Transportation System (ITS). The complex long-term and long-range spatiotemporal correlations of traffic flow pose a significant challenge to the prediction task. Most current research methods focus only on spatial correlations in local areas, ignoring global geographic contextual information. It is challenging to capture spatial information from distant nodes using shallow graph neural networks (GNNs) to model long-range spatial correlations. To handle this problem, we design a novel spatiotemporal global semantic graph-attentive convolutional network model (STSGAN), which is a deep-level network to achieve the simultaneous modelling of spatiotemporal correlations. First, we propose a graph-attentive convolutional network (GACN) to extract the importance of different spatial features and learn the spatial correlation of local regions and the global spatial semantic information. The temporal causal convolution structure (TCN) is utilized to capture the causal relationships between long-short times, thus enabling an integrated consideration of local and overall spatiotemporal correlations. Several experiments are conducted on two real-world traffic flow datasets, and the results show that our approach outperforms several state-of-the-art baselines. |
| first_indexed | 2024-03-09T10:17:55Z |
| format | Article |
| id | doaj.art-03f0cd74f891440e8a07e325e378e8c2 |
| institution | Directory Open Access Journal |
| issn | 2220-9964 |
| language | English |
| last_indexed | 2024-03-09T10:17:55Z |
| publishDate | 2022-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | ISPRS International Journal of Geo-Information |
| spelling | doaj.art-03f0cd74f891440e8a07e325e378e8c22023-12-01T22:13:33ZengMDPI AGISPRS International Journal of Geo-Information2220-99642022-07-0111738110.3390/ijgi11070381STSGAN: Spatial-Temporal Global Semantic Graph Attention Convolution Networks for Urban Flow PredictionJunwei Zhou0Xizhong Qin1Kun Yu2Zhenhong Jia3Yan Du4College of Information Science and Engineering, Xinjiang University, Urumqi 830000, ChinaCollege of Information Science and Engineering, Xinjiang University, Urumqi 830000, ChinaCollege of Information Science and Engineering, Xinjiang University, Urumqi 830000, ChinaCollege of Information Science and Engineering, Xinjiang University, Urumqi 830000, ChinaCollege of Information Science and Engineering, Xinjiang University, Urumqi 830000, ChinaAccurate urban traffic flow prediction plays a vital role in Intelligent Transportation System (ITS). The complex long-term and long-range spatiotemporal correlations of traffic flow pose a significant challenge to the prediction task. Most current research methods focus only on spatial correlations in local areas, ignoring global geographic contextual information. It is challenging to capture spatial information from distant nodes using shallow graph neural networks (GNNs) to model long-range spatial correlations. To handle this problem, we design a novel spatiotemporal global semantic graph-attentive convolutional network model (STSGAN), which is a deep-level network to achieve the simultaneous modelling of spatiotemporal correlations. First, we propose a graph-attentive convolutional network (GACN) to extract the importance of different spatial features and learn the spatial correlation of local regions and the global spatial semantic information. The temporal causal convolution structure (TCN) is utilized to capture the causal relationships between long-short times, thus enabling an integrated consideration of local and overall spatiotemporal correlations. Several experiments are conducted on two real-world traffic flow datasets, and the results show that our approach outperforms several state-of-the-art baselines.https://www.mdpi.com/2220-9964/11/7/381traffic flow predictionspatial–temporal modelinggraph convolutional networkattention mechanism |
| spellingShingle | Junwei Zhou Xizhong Qin Kun Yu Zhenhong Jia Yan Du STSGAN: Spatial-Temporal Global Semantic Graph Attention Convolution Networks for Urban Flow Prediction ISPRS International Journal of Geo-Information traffic flow prediction spatial–temporal modeling graph convolutional network attention mechanism |
| title | STSGAN: Spatial-Temporal Global Semantic Graph Attention Convolution Networks for Urban Flow Prediction |
| title_full | STSGAN: Spatial-Temporal Global Semantic Graph Attention Convolution Networks for Urban Flow Prediction |
| title_fullStr | STSGAN: Spatial-Temporal Global Semantic Graph Attention Convolution Networks for Urban Flow Prediction |
| title_full_unstemmed | STSGAN: Spatial-Temporal Global Semantic Graph Attention Convolution Networks for Urban Flow Prediction |
| title_short | STSGAN: Spatial-Temporal Global Semantic Graph Attention Convolution Networks for Urban Flow Prediction |
| title_sort | stsgan spatial temporal global semantic graph attention convolution networks for urban flow prediction |
| topic | traffic flow prediction spatial–temporal modeling graph convolutional network attention mechanism |
| url | https://www.mdpi.com/2220-9964/11/7/381 |
| work_keys_str_mv | AT junweizhou stsganspatialtemporalglobalsemanticgraphattentionconvolutionnetworksforurbanflowprediction AT xizhongqin stsganspatialtemporalglobalsemanticgraphattentionconvolutionnetworksforurbanflowprediction AT kunyu stsganspatialtemporalglobalsemanticgraphattentionconvolutionnetworksforurbanflowprediction AT zhenhongjia stsganspatialtemporalglobalsemanticgraphattentionconvolutionnetworksforurbanflowprediction AT yandu stsganspatialtemporalglobalsemanticgraphattentionconvolutionnetworksforurbanflowprediction |