Presenting a model for generalizing and simplifying road networks using graph-based deep learning methods

Zarei, marzie; karimi, Mohammad; Pilehforooshha, parastoo

doi:10.66224/jgst.15.3.71

[Home ] [Archive]

[ فارسی ]

Journal of Geomatics Science and Technology

Main Menu

Home

Browse

Journal Info

Guide for Authors

Submit Manuscript

Articles archive

For Reviewers

Contact us

Site Facilities

Reviewers

Search in website

Receive site information

Volume 15, Issue 3 (3-2026)

JGST 2026, 15(3): 71-90

Back to browse issues page

Presenting a model for generalizing and simplifying road networks using graph-based deep learning methods

Marzie Zarei

, Mohammad Karimi ^*

, Parastoo Pilehforooshha

Abstract: (338 Views)

One of the core responsibilities of national mapping organizations is the production of maps at multiple scales, a task that is inherently time-consuming and costly. An effective approach to reducing both time and expense is the generation of small-scale maps through the generalization and simplification of large-scale maps. In this research, considering the crucial role of road networks in topographic databases, a three-step framework was developed for modeling the generalization and simplification of road networks. In the first step, to address the limitations of existing methods, a hybrid structure was proposed that integrates the Mesh, Stroke, and building-block approaches. In this stage, the road network was decomposed into linear and surface-linear structures, and their topological relationships were extracted using a dual graph. In the second step, thematic, geometric, and topological features of the structures were extracted and standardized, after which classification was performed using the Random Forest algorithm for linear structures and the TAGCN method for surface-linear structures. Based on the classification results, less significant or isolated roads were eliminated, and the remaining lines were simplified and smoothed according to the target scale. In the third step, to finalize the generalization and simplification process, building blocks were generalized to the target scale, and spatial conflicts between them and the resulting road network were detected and resolved. The results demonstrated that the overall classification accuracy was 88% for linear structures and 93% for surface-linear structures. Furthermore, the evaluation revealed that major alterations compared to the original network were limited to approximately 8% of the network’s length and density.

Article number: 5

Keywords: Generalization and Simplification, Road Networks, Topographic Database, Graph-based Deep Learning, Elimination–Selection Operator

Full-Text [PDF 1734 kb] (72 Downloads)

Type of Study: Research | Subject: GIS
Received: 2025/10/5 | Accepted: 2026/02/7

References

1. Stoter, J., Post, M. andVan Altena, V. Fully automated generalization of a 1: 50k map from 1: 10k data. Cartography and Geographic Information Science, 2014. 41(1): p. 1-13. [DOI:10.1080/15230406.2013.824637]

2. Guo, X., Liu, J., Wu, F. and Qian, H. A Method for Intelligent Road Network Selection Based on Graph Neural Network. ISPRS International Journal of Geo-Information, 2023. 12(8): p. 336. [DOI:10.3390/ijgi12080336]

3. Yan, X. and M. Yang, A deep learning approach for polyline and building simplification based on graph autoencoder with flexible constraints. Cartography and Geographic Information Science, 2023: p. 1-18. [DOI:10.1080/15230406.2023.2218106]

4. Yu, W., Zhang, Y., Ai, T., Guan, Q., Chen, Z. and Li, H. Road network generalization considering traffic flow patterns. International Journal of Geographical Information Science, 2020. 34(1): p. 119-149. [DOI:10.1080/13658816.2019.1650936]

5. Li, Z., Algorithmic foundation of multi-scale spatial representation. 2006: CRC Press. [DOI:10.1201/9781420008432]

6. Regnauld, N. and R.B. McMaster, A synoptic view of generalisation operators, in Generalisation of geographic information. 2007, Elsevier. p. 37-66. [DOI:10.1016/B978-008045374-3/50005-3]

7. Gülgen, F., and Gökgöz, T. A block-based selection method for road network generalization. International Journal of Digital Earth, 2011. 4(2): p. 133-153. [DOI:10.1080/17538947.2010.489972]

8. Benz, S.A. and Weibel, R., Road network selection for medium scales using an extended stroke-mesh combination algorithm. Cartography and Geographic Information Science, 2014. 41(4): p. 323-339. [DOI:10.1080/15230406.2014.928482]

9. Han, Y., Wang, Z., Lu, X. and Hu, B. Application of AHP to road selection. ISPRS International Journal of Geo-Information, 2020. 9(2): p. 86. [DOI:10.3390/ijgi9020086]

10. Li, C., Wu, W., Wu, P., Yin, J. and Guo, P. An elimination method for isolated meshes in a road network considering stroke edge feature. Plos one, 2020. 15(11): p. e0239828. [DOI:10.1371/journal.pone.0239828]

11. Mackaness, W.A. and Beard, K.M. Use of graph theory to support map generalization. Cartography and Geographic Information Systems, 1993. 20(4): p. 210-221. [DOI:10.1559/152304093782637479]

12. Richardson, D. and Thomson, R. Integrating thematic, geometric, and topological information in the generalization of road networks. Cartographica: The International Journal for Geographic Information and Geovisualization, 1996. 33(1): p. 75-83. [DOI:10.3138/F150-7678-5Q15-8N06]

13. Morisset, B. and Ruas, A. Simulation and agent modelling for road selection in generalisation. in Proceedings of the ICA 18th international cartographic conference. 1997.

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

15. Jiang, B. and Harrie, L. Selection of streets from a network using self‐organizing maps. Transactions in GIS, 2004. 8(3): p. 335-350. [DOI:10.1111/j.1467-9671.2004.00186.x]

16. Thomson, R.C. and Richardson, D.E. The 'good continuation'principle of perceptual organization applied to the generalization of road networks. in Proceedings of the ICA 19th International Cartographic Conference. 1999. Ottawa, Canada.

17. Thomson, R.C. The'stroke'concept in geographic network generalization and analysis. in Progress in Spatial Data Handling: 12th International Symposium on Spatial Data Handling. 2006. Springer.

18. Hu, Y.G., Chen, J., Li, Z. and Zhao, R.L. Selective omission of road features based on mesh density for digital map generalization. Acta Geodaetica et Cartographica Sinica, 2007. 36(3): p. 351-357.

19. Chen, J., Hu, Y., Li, Z., Zhao, R. and Meng, L. Selective omission of road features based on mesh density for automatic map generalization. International Journal of Geographical Information Science, 2009. 23(8): p. 1013-1032. [DOI:10.1080/13658810802070730]

20. Li, Z. and Zhou, Q., Integration of linear and areal hierarchies for continuous multi-scale representation of road networks. International Journal of Geographical Information Science, 2012. 26(5): p. 855-880. [DOI:10.1080/13658816.2011.616861]

21. Wu, P., Yin, Y., Wu, C., Bai, X., Zhang, C. and Dai, Z. An Automatic Generalization Method for a Dense Road Network Area Considering Spatial Structural Features as Constraints. ISPRS International Journal of Geo-Information, 2022. 11(12): p. 599. [DOI:10.3390/ijgi11120599]

22. Peng, W. and Muller, J.C. A dynantic decision tree structure supporting urban road network automated generalization. The Cartographic Journal, 1996. 33(1): p. 5-10. [DOI:10.1179/caj.1996.33.1.5]

23. Zhou, Q. and Li, Z. A comparative study of various supervised learning approaches to selective omission in a road network. The Cartographic Journal, 2017. 54(3): p. 254-264. [DOI:10.1179/1743277414Y.0000000083]

24. Karsznia, I., K. Wereszczyńska, and Weibel, R. Make it simple: effective road selection for small-scale map design using decision-tree-based models. ISPRS International Journal of Geo-Information, 2022. 11(8): p. 457. [DOI:10.3390/ijgi11080457]

25. Karsznia, I., Adolf, A., Leyk, S. and Weibel, R. Using machine learning and data enrichment in the selection of roads for small-scale maps. Cartography and Geographic Information Science, 2024. 51(1): p. 60-78. [DOI:10.1080/15230406.2023.2283075]

26. Zheng, J., Gao, Z., Ma, J., Shen, J. and Zhang, K. Deep graph convolutional networks for accurate automatic road network selection. ISPRS International Journal of Geo-Information, 2021. 10(11): p. 768. [DOI:10.3390/ijgi10110768]

27. Xiao, T., Ai, T., Burghardt, D., Liu, P., Yang, M., Gao, A., Kong, B. and Yu, H. A road generalization method using graph convolutional network based on mesh-line structure unit. Geocarto International, 2024. 39(1): p. 2413549. [DOI:10.1080/10106049.2024.2413549]

28. PilehForousha, P. and Karimi, M. "A local adaptive density based algorithm for clustering polygonal buildings in urban block polygons". Geocarto International, 2020, 35(2). pp. 141-167. [DOI:10.1080/10106049.2018.1508313]

29. Chaudhry, O. and Mackaness, W. Rural and urban road network generalisation: Deriving 1: 250,000 from OS MasterMap. 2006.

30. Jiang, B., S. Zhao, and Yin, J. Self-organized natural roads for predicting traffic flow: a sensitivity study. Journal of statistical mechanics: Theory and experiment, 2008. 2008(07): p. P07008. [DOI:10.1088/1742-5468/2008/07/P07008]

31. Tian, J., Xiong, F., Lei, Y. and Zhan, Y. Revising self-best-fit strategy for stroke generating. in Advances in Spatial Data Handling and Analysis: Select Papers from the 16th IGU Spatial Data Handling Symposium. 2015. Springer. [DOI:10.1007/978-3-319-19950-4_11]

32. Liu, Y. and Li, W. A new algorithms of stroke generation considering geometric and structural properties of road network. ISPRS International Journal of Geo-Information, 2019. 8(7): p. 304. [DOI:10.3390/ijgi8070304]

33. Xu, Z., Liu, C., Zhang, H., Huang, Z. and Li, Z. Road selection based on evaluation of stroke network functionality. Cehui Xuebao/Acta Geodaetica et Cartographica Sinica, 2012. 41(5): p. 769-776.

34. Du, J., Zhang, S., Wu, G., Moura, J.M. and Kar, S. arXiv preprint arXiv:1710.10370, 2017.

Send email to the article author

Add your comments about this article

‎ 10.66224/jgst.15.3.71

Mendeley

Zotero

RefWorks

Zarei M, karimi M, Pilehforooshha P. Presenting a model for generalizing and simplifying road networks using graph-based deep learning methods. JGST 2026; 15 (3) : 5
URL: http://jgst.issgeac.ir/article-1-1238-en.html

Rights and permissions
	This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

Volume 15, Issue 3 (3-2026)

Back to browse issues page