EN中文

Journal of Geo-information Science >

2025 , Vol. 27 >Issue 9: 2052 - 2069

DOI: https://doi.org/10.12082/dqxxkx.2025.240465

Road Network Pattern Recognition Using Graph Representation Learning of Geometric Similarity

  • HOU Yang , 1, 2 ,
  • YANG Jian , 3, * ,
  • FANG Li 4 ,
  • ZHANG Bianying 5 ,
  • ZHANG Meng 6 ,
  • XIE Xiao 7 ,
  • ZHENG Chenghao 8, 4
Expand
  • 1. Fujian Institute of Research on the Structure of Matter, Chinese Academy of Sciences, Fuzhou 350002, China
  • 2. University of Chinese Academy of Sciences, Beijing 100049, China
  • 3. School of Geospatial Information, Information Engineering University, Zhengzhou 450052, China
  • 4. Quanzhou Institute of Equipment Manufacturing, Haixi Institute, Chinese Academy of Sciences, Quanzhou 362216, China
  • 5. China Centre for Resources Satellite Data and Application, Beijing 100094, China
  • 6. School of Human Settlements and Civil Engineering, Xi'an Jiaotong University, Xi'an 712000, China
  • 7. Institute of Applied Ecology, Chinese Academy of Sciences, Shenyang 110116, China
  • 8. College of Software, Liaoning Technical University, Huludao 125105, China
*YANG Jian, E-mail:

Received date: 2024-08-23

  Revised date: 2024-11-14

  Online published: 2025-09-09

Supported by

National Natural Science Foundation of China(42130112)

National Natural Science Foundation of China(42371479)

National Natural Science Foundation of China(41901335)

Key Laboratory of Smart Earth(KF2023ZD04-02)

Fold

Abstract

[Objectives] Abstract: As a fundamental geographic feature, road networks play a crucial role in spatial analysis and various applications. This paper studies vector data embedding models for road networks and their application in road network pattern recognition. These models not only facilitate the analysis of the spatial structure of road networks but also provide computational methods for information representation and processing in the digital twin of the Earth system. However, most existing road network pattern recognition methods are computationally complex, lack intelligent reasoning capabilities, rely heavily on large amounts of labeled data, and exhibit limited generalization ability. These limitations constrain their performance in pattern recognition under complex road network structures. [Methods] To address these challenges, this paper proposes a novel identification method based on geometric similarity graph representation learning, tailored for road network pattern recognition tasks. Firstly, the road network is modeled using spatial dual graphs, with graph node features designed based on cognitive heuristics to capture the intrinsic characteristics of the road network. Next, the model is trained in an unsupervised manner. Subgraph Isomorphism Counting (SIC) is introduced during road embedding learning to capture local structural patterns, while a Global Context Attention mechanism (GCA) is incorporated during graph embedding generation to capture global context, thereby enhancing the model's representation performance. Finally, geometric similarity in graph-level embeddings was utilized to effectively recognize road network patterns. To validate the effectiveness of the proposed method, a dataset containing five types of road network patterns was constructed, and extensive experiments were conducted. [Results] The SUGAR-3 model proposed in this paper achieved a classification accuracy of 93.18%, representing an improvement of more than 12% over classical road network pattern recognition methods and significantly outperforming baseline models such as Graph Convolutional Neural Networks (GCNN). Furthermore, an in-depth analysis of the graph embeddings and the model's expressive power was performed. The results demonstrate that the road network patterns represented by our model can be effectively clustered, forming clear boundaries between different patterns. [Conclusions] This verifies the effectiveness of SIC and GCA in enhancing road network pattern recognition performance and provides a new approach for further improving the expressive power of graph embeddings for road networks.

Key words： road network pattern recognition; geo-embedding; subgraph isomorphism counting; global context attention; graph neural network

Cite this article

HOU Yang , YANG Jian , FANG Li , ZHANG Bianying , ZHANG Meng , XIE Xiao , ZHENG Chenghao . Road Network Pattern Recognition Using Graph Representation Learning of Geometric Similarity[J]. Journal of Geo-information Science, 2025 , 27(9) : 2052 -2069 . DOI: 10.12082/dqxxkx.2025.240465

利益冲突：Conflicts of Interest 所有作者声明不存在利益冲突。

All authors disclose no relevant conflicts of interest.

References

Publishing order | Descend order by publishing year | Descend order by cited within
[1]
Li X, Feng M, Ran Y H, et al. Big Data in Earth system science and progress towards a digital twin[J]. Nature Reviews Earth & Environment, 2023, 4(5):319-332. DOI: 10.1038/s43017-023-00409-w

[2]
Kang C G, Ma X J, Tong D Q, et al. Intra-urban human mobility patterns: An urban morphology perspective[J]. Physica A: Statistical Mechanics and Its Applications, 2012, 391(4):1702-1717. DOI:10.1016/j.physa.2011.11.005

[3]
Yang B S, Luan X C, Li Q Q. Generating hierarchical strokes from urban street networks based on spatial pattern recognition[J]. International Journal of Geographical Information Science, 2011, 25(12):2025-2050. DOI:10.1080/13658816.2011.570270

[4]
马超, 孙群, 陈换新, 等. 利用路段分类识别复杂道路交叉口[J]. 武汉大学学报(信息科学版), 2016, 41(9):1232-1237.

[ Ma C, Sun Q, Chen H X, et al. Recognition of road junctions based on road classification method[J]. Geomatics and Information Science of Wuhan University, 2016, 41(9):1232-1237. ] DOI:10.13203/j.whugis20160073

[5]
何亚坤, 艾廷华, 杜欣, 等. 网络空间向量剖分法识别城市路网网格模式[J]. 武汉大学学报(信息科学版), 2018, 43(1):138-144.

[ He Y K, Ai T H, Du X, et al. Grid pattern recognition in street network space by vector tessellation method[J]. Geomatics and Information Science of Wuhan University, 2018, 43(1):138-144. ] DOI:10.13203/j.whugis20150757

[6]
徐云滔, 张圆, 李精忠, 等. 使用LightGBM识别城市道路格网模式[J]. 测绘科学技术, 2020, 8(1):1-8.

[ Xu Y T, Zhang Y, Li J Z, et al. Identifying grid pattern of urban road networks using LightGBM[J]. Geomatics Science and Technology, 2020, 8(1):1-8. ] DOI:10.12677/GST.2020.81001

[7]
王安东, 武芳, 巩现勇, 等. 一种城市路网多层次复合网格模式识别方法[J]. 测绘学报, 2023, 52(11):1994-2006.

DOI

[ Wang A D, Wu F, Gong X Y, et al. A recognition approach for compound grid pattern of urban road networks[J]. Acta Geodaetica et Cartographica Sinica, 2023, 52(11):1994-2006. ] DOI:10.11947/j.AGCS.2023.20220528

[8]
Jiang B, Claramunt C. A structural approach to the model generalization of an urban street network[J]. GeoInformatica, 2004, 8(2):157-171. DOI:10.1023/B:GEIN.0000017746.44824.70

[9]
Zhang Y Y, Wang X S, Zeng P, et al. Centrality characteristics of road network patterns of traffic analysis zones[J]. Transportation Research Record: Journal of the Transportation Research Board, 2011, 2256(1):16-24. DOI: 10.3141/2256-03

[10]
徐柱, 蒙艳姿, 李志林, 等. 基于有向属性关系图的典型道路交叉口结构识别方法[J]. 测绘学报, 2011, 40(1):125-131.

[ Xu Z, Meng Y Z, Li Z L, et al. Recognition of structures of typical road junctions based on directed attributed relational graph[J]. Acta Geodaetica et Cartographica Sinica, 2011, 40(1):125-131. ] DOI:CNKI:SUN:CHXB.0.2011-01-026

[11]
Jiang B, Claramunt C. Topological analysis of urban street networks[J]. Environment and Planning B: Planning and Design, 2004, 31(1):151-162. DOI:10.1068/b306

[12]
李豪, 郭黎, 王云阁, 等. 利用路段连接图识别道路网中的格网模式[J]. 武汉大学学报(信息科学版), 2022, 47(1):126-132.

[ Li H, Guo L, Wang Y G, et al. Grid pattern recognition in road networks using link graph[J]. Geomatics and Information Science of Wuhan University, 2022, 47(1):126-132. ] DOI:10.13203/j.whugis20190300

[13]
Gilmer J, Schoenholz S S, Riley P F, et al. Neural message passing for quantum chemistry[C]// Proceedings of the 34th International Conference on Machine Learning. Sydney, Australia, 2017:1263-1272. DOI:10.5555/3305381.3305512

[14]
Rahimi A, Cohn T, Baldwin T. Semi-supervised user geolocation via graph convolutional networks[C]// Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, 2018, 1(1):2009-2019. DOI: 10.18653/v1/P18-1187

[15]
杨铭, 杨剑, 侯洋, 等. 一种基于改进邻域聚合的路网图嵌入匹配方法[J]. 地球信息科学学报, 2024, 26(10):2335-2351.

DOI

[ Yang M, Yang J, Hou Y, et al. A method of road network matching using graph embedding via improved neighbor aggregations[J]. Journal of Geo-information Science, 2024, 26(10):2335-2351. ] DOI:10.12082/dqxxkx.2024.240005

[16]
Yan X F, Ai T H, Yang M, et al. A graph convolutional neural network for classification of building patterns using spatial vector data[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2019, 150:259-273. DOI: 10.1016/j.isprsjprs.2019.02.010

[17]
Yu H F, Ai T H, Yang M, et al. A graph autoencoder network to measure the geometric similarity of drainage networks in scaling transformation[J]. International Journal of Digital Earth, 2023, 16(1):1828-1852. DOI:10.1080/17538947.2023.2212920

[18]
Yu H F, Ai T H, Yang M, et al. Automatic segmentation of parallel drainage patterns supported by a graph convolution neural network[J]. Expert Systems with Applications, 2023, 211:118639. DOI:10.1016/j.eswa.2022.118639

[19]
Yang M, Jiang C J, Yan X F, et al. Detecting interchanges in road networks using a graph convolutional network approach[J]. International Journal of Geographical Information Science, 2022, 36(6):1119-1139. DOI:10.1080/13658816.2021.2024195

[20]
Yang M, Cao M J, Cheng L Y, et al. Classification of urban interchange patterns using a model combining shape context descriptor and graph convolutional neural network[J]. Geo-spatial Information Science, 2024, 27(5):1622-1637. DOI:10.1080/10095020.2023.2264337

[21]
王米琪, 艾廷华, 晏雄锋, 等. 图卷积网络模型识别道路正交网格模式[J]. 武汉大学学报(信息科学版), 2020, 45(12):1960-1969.

[ Wang M Q, Ai T H, Yan X F, et al. Grid pattern recognition in road networks based on graph convolution network model[J]. Geomatics and Information Science of Wuhan University, 2020, 45(12):1960-1969. ] DOI:10.13203/j.whugis20200022

[22]
Chang Y C, Tanin E, Cao X, et al. Spatial structure-aware road network embedding via graph contrastive learning[C]// EDBT. 2023:144-156. DOI:10.48786/edbt.2023.12

[23]
Pan S R, Hu R Q, Long G D, et al. Adversarially regularized graph autoencoder for graph embedding[C]// Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence. Saarland: DBLP, 2018:2609-2615 DOI:10.48550/arXiv.1802.04407

[24]
Tian J, Fang H Q, Wang Y H, et al. On the degree correlation of urban road networks[J]. Transactions in GIS, 2018, 22(1):119-148. DOI:10.1111/tgis.12299

[25]
Yu H F, Ai T H, Yang M, et al. A recognition method for drainage patterns using a graph convolutional network[J]. International Journal of Applied Earth Observation and Geoinformation, 2022, 107:102696. DOI:10.1016/j.jag.2022.102696

[26]
Yuan H T, Li G L, Bao Z F, et al. Effective travel time estimation: When historical trajectories over road networks matter[C]// Proceedings of the 2020 ACM SIGMOD International Conference on Management of Data. ACM, 2020:10.1145/3318464.3389771. DOI:10.1145/3318464.3389771

[27]
Köhler W. Gestalt psychology[J]. Psychologische Forschung, 1967, 31(1): XVIII-XXX. DOI:10.1007/BF00422382

[28]
LeCun Y, Boser B, Denker J S, et al. Backpropagation applied to handwritten zip code recognition[J]. Neural Computation, 1989, 1(4):541-551. DOI:10.1162/neco.1989.1.4.541

[29]
Sukhbaatar S, Weston J, Fergus R. End-to-end memory networks[J]. Advances in Neural Information Processing Systems, 2015,2440-2448. DOI:10.48550/arXiv.1503.08895

[30]
Gehring J, Auli M, Grangier D, et al. Convolutional sequence to sequence learning[C]// International Conference on Machine Learning. PMLR, 2017:1243-1252. DOI: 10.5555/3305381.3305510

[31]
Chen Z, Chen L, Villar S, et al. Can graph neural networks count substructures?[J]. Advances in Neural Information Processing Systems, 2020, 33:10383-10395. DOI: 10.48550/arXiv.2002.04025

[32]
Bouritsas G, Frasca F, Zafeiriou S, et al. Improving graph neural network expressivity via subgraph isomorphism counting[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 45(1):657-668. DOI:10.1109/TPAMI.2022.3154319

[33]
Kanatsoulis C, Ribeiro A. Counting Graph Substructures with Graph Neural Networks[C]// The Twelfth International Conference on Learning Representations.

[34]
Wang C, Pan S R, Long G D, et al. MGAE: Marginalized graph autoencoder for graph clustering[C]// Proceedings of the 2017 ACM on Conference on Information and Knowledge Management. ACM, 2017: 10.1145/3132847.3132967. DOI:10.1145/3132847.3132967

[35]
高原, 王洁, 李钢, 等. 城市用地功能精细化识别方法:时序动态图嵌入深度学习模型[J]. 地球信息科学学报, 2022, 24(10):1968-1981.

DOI

[ Gao Y, Wang J, Li G, et al. Time series dynamic graph embedding: A method for precision identification of urban functions[J]. Journal of Geo-Information Science, 2022, 24(10):1968-1981. ] DOI:10.12082/dqxxkx.2022.220057

[36]
Bai Y S, Ding H, Bian S, et al. SimGNN: A neural network approach to fast graph similarity computation[C]// Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining. ACM, 2019: 10.1145/3289600.3290967. DOI:10.1145/3289600.3290967

[37]
唐曾杨, 艾廷华, 徐海江. 地理知识图谱下的建筑群空间分布模式推理[J]. 地球信息科学学报, 2023, 25(6):1202-1214.

DOI

[ Tang Z Y, Ai T H, Xu H J. Reasoning of spatial distribution pattern of building cluster based on geographic knowledge graph[J]. Journal of Geo-information Science, 2023, 25(6):1202-1214. ] DOI:10.12082/dqxxkx.2023.220761

[38]
何海威, 钱海忠, 谢丽敏, 等. 立交桥识别的CNN卷积神经网络法[J]. 测绘学报, 2018, 47(3):385-395.

DOI

[ He H W, Qian H Z, Xie L M, et al. Interchange recognition method based on CNN[J]. Acta Geodaetica et Cartographica Sinica, 2018, 47(3):385-395. ] DOI:10.11947/j.AGCS.2018.20170265

[39]
Li C M, Zhang H G, Wu P D, et al. A complex junction recognition method based on GoogLeNet model[J]. Transactions in GIS, 2020, 24(6):1756-1778. DOI:10.1111/tgis.12681

[40]
Kipf T N, Welling M. Semi-supervised classification with graph convolutional networks[C]// Proceedings of the 5th International Conference on Learning Representations (ICLR). Toulon, France, 2017:1-14. DOI:10.48550/arXiv.1609.02907

[41]
Yang Z C, Yang D Y, Dyer C, et al. Hierarchical attention networks for document classification[C]// Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies. Stroudsburg, PA, USA: Association for Computational Linguistics, 2016:1480-1489. DOI: 10.18653/v1/n16-1174

Options
Outlines

/

〈 〉