Intelligent delineation algorithm of urban development boundary based on graph neural network

Yu Li; Xinzi Ma

doi:10.71451/ISTAER2606

Authors

Yu Li Department of Art and Design, Beijing City University, Shunyi District, Beijing, China Author https://orcid.org/0009-0005-1817-3211
Xinzi Ma Department of Art and Design, Beijing City University, Shunyi District, Beijing, China Author https://orcid.org/0009-0007-3752-9118

DOI:

https://doi.org/10.71451/ISTAER2606

Keywords:

Urban growth boundary; Graph neural network; Urban expansion prediction; Spatial planning; Multi-source data fusion

Abstract

The Urban Growth Boundary (UGB) is essential for controlling urban sprawl and optimizing land use, yet traditional delineation methods struggle with modeling complex spatial relationships and fusing multi-source data. This study proposes an intelligent UGB delineation algorithm based on a Graph Neural Network (GNN). The study area is discretized into uniform spatial units to construct an urban graph, with node features integrating remote sensing imagery, land use types, transportation networks, and population-economic data. A spatially constrained graph convolution structure with an improved attention mechanism is designed to jointly model spatial structures and expansion driving factors, enhanced by multi-scale feature aggregation and spatial consistency constraints. Experimental validation in a 1,250 km² urban area (5,024 nodes, approximately 3.8×10⁴ edges) demonstrates that the proposed model achieves 0.912 accuracy and 0.900 F1-score in UGB recognition—3.4% and 3.8% higher than traditional GCN—with a 7.2% improvement in spatial consistency. The model remains stable across 250–1000 m spatial scales, indicating strong generalization ability and spatial adaptability. This GNN-based UGB delineation method effectively captures urban spatial structure characteristics and expansion patterns, providing a high-precision, data-driven technical pathway for territorial spatial planning and sustainable urban growth management.

References

[1] Ma, S., Zhao, Y., & Tan, X. (2020). Exploring smart growth boundaries of urban agglomeration with land use spatial optimization: A case study of Changsha-Zhuzhou-Xiangtan city group, China. Chinese Geographical Science, 30(4), 665-676. DOI: https://doi.org/10.1007/s11769-020-1140-1

[2] Liu, X., Shi, W., & Zhang, S. (2022). Progress of research on urban growth boundary and its implications in Chinese studies based on bibliometric analysis. International Journal of Environmental Research and Public Health, 19(24), 16644. DOI: https://doi.org/10.5604/01.3001.0055.2685

[3] Wei, J., Yue, W., Li, M., Liu, Y., & Song, Y. (2025). Multi-scenario urban growth boundaries and trade-offs among land use functions. Cities, 159, 105752. DOI: https://doi.org/10.1016/j.cities.2025.105752

[4] Li, Z., Luan, W., Zhang, Z., & Su, M. (2020). Relationship between urban construction land expansion and population/economic growth in Liaoning Province, China. Land Use Policy, 99, 105022. DOI: https://doi.org/10.1016/j.landusepol.2020.105022

[5] Colsaet, A., Laurans, Y., & Levrel, H. (2018). What drives land take and urban land expansion? A systematic review. Land Use Policy, 79, 339-349. DOI: https://doi.org/10.1016/j.landusepol.2018.08.017

[6] Mahtta, R., Fragkias, M., Güneralp, B., Mahendra, A., Reba, M., Wentz, E. A., & Seto, K. C. (2022). Urban land expansion: the role of population and economic growth for 300+ cities. Npj Urban Sustainability, 2(1), 5. DOI: https://doi.org/10.1038/s42949-022-00048-y

[7] Zhang, T., Wu, K., Wang, X., Li, X., Li, L., & Chen, L. (2025). Impact of land use patterns on flood risk in the Chang-Zhu-Tan urban agglomeration, China. Remote Sensing, 17(16), 2889. DOI: https://doi.org/10.3390/rs17162889

[8] Wang, Z., & Ren, F. (2025). Developing a decision support system for sustainable urban planning using machine learning-based scenario modeling. Scientific Reports, 15(1), 13210. DOI: https://doi.org/10.1038/s41598-025-90057-5

[9] Wagner, M., & de Vries, W. T. (2019). Comparative review of methods supporting decision-making in urban development and land management. Land, 8(8), 123. DOI: https://doi.org/10.3390/land8080123

[10] Wu, Z., Pan, S., Chen, F., Long, G., Zhang, C., & Yu, P. S. (2020). A comprehensive survey on graph neural networks. IEEE transactions on neural networks and learning systems, 32(1), 4-24. DOI: https://doi.org/10.55041/IJSREM55073

[11] Khemani, B., Patil, S., Kotecha, K., & Tanwar, S. (2024). A review of graph neural networks: concepts, architectures, techniques, challenges, datasets, applications, and future directions. Journal of Big Data, 11(1), 18. DOI: https://doi.org/10.1007/978-3-032-04315-3_1

[12] Chen, Y., Zhao, P., Lin, Y., Sun, Y., Chen, R., Yu, L., & Liu, Y. (2024). Semantic-enhanced graph convolutional neural networks for multi-scale urban functional-feature identification based on human mobility. ISPRS International Journal of Geo-Information, 13(1), 27. DOI: https://doi.org/10.3390/ijgi13010027

[13] Liu, Y., Guo, Q., & Zheng, C. (2025). Urban street network morphology classification through street-block based graph neural networks and multi-model fusion. International Journal of Digital Earth, 18(1), 2497490. DOI: https://doi.org/10.1080/17538947.2025.2497490

[14] Wu, P., Zhang, Z., Peng, X., & Wang, R. (2024). Deep learning solutions for smart city challenges in urban development. Scientific Reports, 14(1), 5176. DOI: https://doi.org/10.1038/s41598-024-55928-3

[15] Wang, S., Zhao, C., Jiang, Q., Zhu, D., Ma, J., & Sun, Y. (2025). Application of Graph Convolutional Neural Networks and multi-sources data on urban functional zones identification, A case study of Changchun, China. Sustainable Cities and Society, 119, 106116. DOI: https://doi.org/10.1016/j.scs.2024.106116

[16] Cai, C., Guo, Z., Zhang, B., Wang, X., Li, B., & Tang, P. (2021). Urban morphological feature extraction and multi-dimensional similarity analysis based on deep learning approaches. Sustainability, 13(12), 6859. DOI: https://doi.org/10.3390/su13126859

[17] Liang, Y., Zhu, J., Ye, W., & Gao, S. (2022, November). Region2Vec: community detection on spatial networks using graph embedding with node attributes and spatial interactions. In Proceedings of the 30th international conference on advances in geographic information systems (pp. 1-4). DOI: https://doi.org/10.1145/3557915.3560974

[18] Xie, X., Mao, W., Yang, Z., Hu, S., Xu, Y., Wu, L., & Xie, Z. (2025). A hybrid spatial learning method integrating graph neural networks and explainable AI to understand urban vitality. Sustainable Cities and Society, 106920. DOI: https://doi.org/10.1016/j.scs.2025.106920

[19] Chen, D., Feng, Y., Li, X., Qu, M., Luo, P., & Meng, L. (2025). Interpreting core forms of urban morphology linked to urban functions with explainable graph neural network. Computers, Environment and Urban Systems, 118, 102267. DOI: https://doi.org/10.1016/j.compenvurbsys.2025.102267

[20] Ding, C., Tang, J., Zhang, M., Wu, H., & Wang, B. (2026). Identifying dynamic functions of urban areas with a multi-temporal collaborative graph neural network model. International Journal of Geographical Information Science, 40(1), 78-111. DOI: https://doi.org/10.1080/13658816.2025.2517195

[21] Corso, G., Cavalleri, L., Beaini, D., Liò, P., & Veličković, P. (2020). Principal neighbourhood aggregation for graph nets. Advances in neural information processing systems, 33, 13260-13271. DOI: https://dl.acm.org/doi/10.5555/3495724.3496836

[22] Dong, W., Wu, J., Luo, Y., Ge, Z., & Wang, P. (2022). Node representation learning in graph via node-to-neighbourhood mutual information maximization. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 16620-16629). DOI: https://doi.org/10.1109/CVPR52688.2022.01612

[23] Wang, P., Han, J., Li, C., & Pan, R. (2019, July). Logic attention based neighborhood aggregation for inductive knowledge graph embedding. In Proceedings of the AAAI conference on artificial intelligence (Vol. 33, No. 01, pp. 7152-7159). DOI: https://doi.org/10.1609/aaai.v33i01.33017152

[24] You, Y., Chen, T., Wang, Z., & Shen, Y. (2020). L2-gcn: Layer-wise and learned efficient training of graph convolutional networks. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 2127-2135). DOI: https://doi.org/10.1109/CVPR42600.2020.00220

[25] Miao, X., Zhang, W., Shao, Y., Cui, B., Chen, L., Zhang, C., & Jiang, J. (2021). Lasagne: A multi-layer graph convolutional network framework via node-aware deep architecture. IEEE Transactions on Knowledge and Data Engineering, 35(2), 1721-1733. DOI: https://doi.org/10.1109/TKDE.2021.3103984

[26] Zhang, S., Tong, H., Xu, J., & Maciejewski, R. (2019). Graph convolutional networks: a comprehensive review. Computational Social Networks, 6(1), 1-23. DOI: https://doi.org/10.1186/s40649-019-0069-y

[27] Diao, Z., Wang, X., Zhang, D., Liu, Y., Xie, K., & He, S. (2019, July). Dynamic spatial-temporal graph convolutional neural networks for traffic forecasting. In Proceedings of the AAAI conference on artificial intelligence (Vol. 33, No. 01, pp. 890-897). DOI: https://doi.org/10.1609/aaai.v33i01.3301890

[28] Shi, G., Shan, J., Ding, L., Ye, P., Li, Y., & Jiang, N. (2019). Urban road network expansion and its driving variables: a case study of Nanjing City. International journal of environmental research and public health, 16(13), 2318. DOI: https://doi.org/10.3390/ijerph16132318

[29] Karimi, F., & Sultana, S. (2024). Urban expansion prediction and land use/land cover change modeling for sustainable urban development. Sustainability, 16(6), 2285. DOI: https://doi.org/10.3390/su16062285

[30] Zhao, W., Wu, J., Shen, Q., Liu, L., Lin, J., & Yang, J. (2022). Estimation of the net primary productivity of winter wheat based on the near-infrared radiance of vegetation. Science of the Total Environment, 838, 156090. DOI: https://doi.org/10.1016/j.scitotenv.2022.156090

[31] Tian, Q., Jin, H., Fensholt, R., Tagesson, T., Feng, L., & Tian, F. (2026). Varying sensitivities of RED-NIR-based vegetation indices to the input reflectance affect the detected long-term trends. ISPRS Journal of Photogrammetry and Remote Sensing, 233, 247-265. DOI: https://doi.org/10.1016/j.isprsjprs.2026.01.028

[32] Açıkkar, M., & Tokgöz, S. (2025). Improving multi-class classification: scaled extensions of harmonic mean-based adaptive k-nearest neighbors: M. Açıkkar and S. Tokgöz. Applied Intelligence, 55(3), 168. DOI: https://doi.org/10.1007/s10489-024-06109-2

[33] Seredin, O. S., & Kopylov, A. V. (2024). Harmonic Averaging in Classifier Quality Assessment. Pattern Recognition and Image Analysis, 34(4), 1160-1171. DOI: https://doi.org/10.1134/S1054661824701220