SPATIOTEMPORAL GRAPH CONVOLUTIONAL NEURAL NETWORKS FOR METRO FLOW PREDICTION
Forecasting urban metro flow accurately plays an important role for station management and passenger safety. Owing to the limitations of non-linearity and complexity of traffic flow data, traditional methods cannot satisfy the requirements of effectively capturing spatiotemporal dependencies at the...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Copernicus Publications
2022-06-01
|
| Series: | The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| Online Access: | https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLIII-B4-2022/403/2022/isprs-archives-XLIII-B4-2022-403-2022.pdf |
| _version_ | 1818533909799895040 |
|---|---|
| author | S. Jin C. Jing Y. Wang X. Lv |
| author_facet | S. Jin C. Jing Y. Wang X. Lv |
| author_sort | S. Jin |
| collection | DOAJ |
| description | Forecasting urban metro flow accurately plays an important role for station management and passenger safety. Owing to the limitations of non-linearity and complexity of traffic flow data, traditional methods cannot satisfy the requirements of effectively capturing spatiotemporal dependencies at the metro network level, which makes it difficult to demonstrate high performance. In this paper, a novel deep learning method is proposed based on Graph Neural Networks (GNN), named STGCN-Metro (SpatioTemporal Graph Convolutional Network based on Metro network), to forecast the short-term inflow and outflow volumes of metro passengers. The proposed model is composed of two spatiotemporal convolutional blocks, which is integrated with the Dilated Convolutional Neural Network (DCNN) and Cluster-Graph Convolutional Network (Cluster-GCN). The DCNN is employed with different dilation rates to capture temporal dependence in larger receptive field. In addition, compare with GCN, the Cluster-GCN is applied the graph clustering algorithms to reduce computational resources considering spatial heterogeneity. A real-world dataset collected in Shanghai metro stations is conducted for validation, and the results demonstrate that the proposed model achieves higher performance, outperforming some well-known baseline models. |
| first_indexed | 2024-12-11T18:04:56Z |
| format | Article |
| id | doaj.art-9cf610bcc6c149f688e41cc8dffb0e2d |
| institution | Directory Open Access Journal |
| issn | 1682-1750 2194-9034 |
| language | English |
| last_indexed | 2024-12-11T18:04:56Z |
| publishDate | 2022-06-01 |
| publisher | Copernicus Publications |
| record_format | Article |
| series | The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| spelling | doaj.art-9cf610bcc6c149f688e41cc8dffb0e2d2022-12-22T00:55:45ZengCopernicus PublicationsThe International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences1682-17502194-90342022-06-01XLIII-B4-202240340910.5194/isprs-archives-XLIII-B4-2022-403-2022SPATIOTEMPORAL GRAPH CONVOLUTIONAL NEURAL NETWORKS FOR METRO FLOW PREDICTIONS. Jin0C. Jing1Y. Wang2X. Lv3School of Geomatics and Urban Spatial Informatics, Beijing University of Civil Engineering and Architecture, Beijing 100044, ChinaSchool of Geomatics and Urban Spatial Informatics, Beijing University of Civil Engineering and Architecture, Beijing 100044, ChinaSchool of Geomatics and Urban Spatial Informatics, Beijing University of Civil Engineering and Architecture, Beijing 100044, ChinaSchool of Geomatics and Urban Spatial Informatics, Beijing University of Civil Engineering and Architecture, Beijing 100044, ChinaForecasting urban metro flow accurately plays an important role for station management and passenger safety. Owing to the limitations of non-linearity and complexity of traffic flow data, traditional methods cannot satisfy the requirements of effectively capturing spatiotemporal dependencies at the metro network level, which makes it difficult to demonstrate high performance. In this paper, a novel deep learning method is proposed based on Graph Neural Networks (GNN), named STGCN-Metro (SpatioTemporal Graph Convolutional Network based on Metro network), to forecast the short-term inflow and outflow volumes of metro passengers. The proposed model is composed of two spatiotemporal convolutional blocks, which is integrated with the Dilated Convolutional Neural Network (DCNN) and Cluster-Graph Convolutional Network (Cluster-GCN). The DCNN is employed with different dilation rates to capture temporal dependence in larger receptive field. In addition, compare with GCN, the Cluster-GCN is applied the graph clustering algorithms to reduce computational resources considering spatial heterogeneity. A real-world dataset collected in Shanghai metro stations is conducted for validation, and the results demonstrate that the proposed model achieves higher performance, outperforming some well-known baseline models.https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLIII-B4-2022/403/2022/isprs-archives-XLIII-B4-2022-403-2022.pdf |
| spellingShingle | S. Jin C. Jing Y. Wang X. Lv SPATIOTEMPORAL GRAPH CONVOLUTIONAL NEURAL NETWORKS FOR METRO FLOW PREDICTION The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| title | SPATIOTEMPORAL GRAPH CONVOLUTIONAL NEURAL NETWORKS FOR METRO FLOW PREDICTION |
| title_full | SPATIOTEMPORAL GRAPH CONVOLUTIONAL NEURAL NETWORKS FOR METRO FLOW PREDICTION |
| title_fullStr | SPATIOTEMPORAL GRAPH CONVOLUTIONAL NEURAL NETWORKS FOR METRO FLOW PREDICTION |
| title_full_unstemmed | SPATIOTEMPORAL GRAPH CONVOLUTIONAL NEURAL NETWORKS FOR METRO FLOW PREDICTION |
| title_short | SPATIOTEMPORAL GRAPH CONVOLUTIONAL NEURAL NETWORKS FOR METRO FLOW PREDICTION |
| title_sort | spatiotemporal graph convolutional neural networks for metro flow prediction |
| url | https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLIII-B4-2022/403/2022/isprs-archives-XLIII-B4-2022-403-2022.pdf |
| work_keys_str_mv | AT sjin spatiotemporalgraphconvolutionalneuralnetworksformetroflowprediction AT cjing spatiotemporalgraphconvolutionalneuralnetworksformetroflowprediction AT ywang spatiotemporalgraphconvolutionalneuralnetworksformetroflowprediction AT xlv spatiotemporalgraphconvolutionalneuralnetworksformetroflowprediction |