Deep Graph Convolutional Networks for Accurate Automatic Road Network Selection
The selection of road networks is very important for cartographic generalization. Traditional artificial intelligence methods have improved selection efficiency but cannot fully extract the spatial features of road networks. However, current selection methods, which are based on the theory of graphs...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-11-01
|
| Series: | ISPRS International Journal of Geo-Information |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2220-9964/10/11/768 |
| _version_ | 1827676452329357312 |
|---|---|
| author | Jing Zheng Ziren Gao Jingsong Ma Jie Shen Kang Zhang |
| author_facet | Jing Zheng Ziren Gao Jingsong Ma Jie Shen Kang Zhang |
| author_sort | Jing Zheng |
| collection | DOAJ |
| description | The selection of road networks is very important for cartographic generalization. Traditional artificial intelligence methods have improved selection efficiency but cannot fully extract the spatial features of road networks. However, current selection methods, which are based on the theory of graphs or strokes, have low automaticity and are highly subjective. Graph convolutional networks (GCNs) combine graph theory with neural networks; thus, they can not only extract spatial information but also realize automatic selection. Therefore, in this study, we adopted GCNs for automatic road network selection and transformed the process into one of node classification. In addition, to solve the problem of gradient vanishing in GCNs, we compared and analyzed the results of various GCNs (GraphSAGE and graph attention networks [GAT]) by selecting small-scale road networks under different deep architectures (JK-Nets, ResNet, and DenseNet). Our results indicate that GAT provides better selection of road networks than other models. Additionally, the three abovementioned deep architectures can effectively improve the selection effect of models; JK-Nets demonstrated more improvement with higher accuracy (88.12%) than other methods. Thus, our study shows that GCN is an appropriate tool for road network selection; its application in cartography must be further explored. |
| first_indexed | 2024-03-10T05:26:20Z |
| format | Article |
| id | doaj.art-228e322f366f4c72b9d81525a0efd174 |
| institution | Directory Open Access Journal |
| issn | 2220-9964 |
| language | English |
| last_indexed | 2024-03-10T05:26:20Z |
| publishDate | 2021-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | ISPRS International Journal of Geo-Information |
| spelling | doaj.art-228e322f366f4c72b9d81525a0efd1742023-11-22T23:36:33ZengMDPI AGISPRS International Journal of Geo-Information2220-99642021-11-01101176810.3390/ijgi10110768Deep Graph Convolutional Networks for Accurate Automatic Road Network SelectionJing Zheng0Ziren Gao1Jingsong Ma2Jie Shen3Kang Zhang4Department of Geographic Information Science, Nanjing University, Nanjing 210023, ChinaDepartment of Geographic Information Science, Nanjing University, Nanjing 210023, ChinaDepartment of Geographic Information Science, Nanjing University, Nanjing 210023, ChinaJiangsu Center for Collaborative Innovation in Geographical Information Resource Development and Application, Nanjing 210023, ChinaDepartment of Geographic Information Science, Nanjing University, Nanjing 210023, ChinaThe selection of road networks is very important for cartographic generalization. Traditional artificial intelligence methods have improved selection efficiency but cannot fully extract the spatial features of road networks. However, current selection methods, which are based on the theory of graphs or strokes, have low automaticity and are highly subjective. Graph convolutional networks (GCNs) combine graph theory with neural networks; thus, they can not only extract spatial information but also realize automatic selection. Therefore, in this study, we adopted GCNs for automatic road network selection and transformed the process into one of node classification. In addition, to solve the problem of gradient vanishing in GCNs, we compared and analyzed the results of various GCNs (GraphSAGE and graph attention networks [GAT]) by selecting small-scale road networks under different deep architectures (JK-Nets, ResNet, and DenseNet). Our results indicate that GAT provides better selection of road networks than other models. Additionally, the three abovementioned deep architectures can effectively improve the selection effect of models; JK-Nets demonstrated more improvement with higher accuracy (88.12%) than other methods. Thus, our study shows that GCN is an appropriate tool for road network selection; its application in cartography must be further explored.https://www.mdpi.com/2220-9964/10/11/768road network selectiongraph convolutional networks (GCNs)deep architecturescartographic generalization |
| spellingShingle | Jing Zheng Ziren Gao Jingsong Ma Jie Shen Kang Zhang Deep Graph Convolutional Networks for Accurate Automatic Road Network Selection ISPRS International Journal of Geo-Information road network selection graph convolutional networks (GCNs) deep architectures cartographic generalization |
| title | Deep Graph Convolutional Networks for Accurate Automatic Road Network Selection |
| title_full | Deep Graph Convolutional Networks for Accurate Automatic Road Network Selection |
| title_fullStr | Deep Graph Convolutional Networks for Accurate Automatic Road Network Selection |
| title_full_unstemmed | Deep Graph Convolutional Networks for Accurate Automatic Road Network Selection |
| title_short | Deep Graph Convolutional Networks for Accurate Automatic Road Network Selection |
| title_sort | deep graph convolutional networks for accurate automatic road network selection |
| topic | road network selection graph convolutional networks (GCNs) deep architectures cartographic generalization |
| url | https://www.mdpi.com/2220-9964/10/11/768 |
| work_keys_str_mv | AT jingzheng deepgraphconvolutionalnetworksforaccurateautomaticroadnetworkselection AT zirengao deepgraphconvolutionalnetworksforaccurateautomaticroadnetworkselection AT jingsongma deepgraphconvolutionalnetworksforaccurateautomaticroadnetworkselection AT jieshen deepgraphconvolutionalnetworksforaccurateautomaticroadnetworkselection AT kangzhang deepgraphconvolutionalnetworksforaccurateautomaticroadnetworkselection |