Graph-enhanced clustering of late modern churches via multi-dimensional semantic feature integration
Source abstract
Abstract
Typological classification of late-modern church buildings provides a basis for understanding the spatial evolution of religious architecture and heritage characteristics. In densely distributed regions like Shanxi, church forms, locations, and institutional backgrounds are highly heterogeneous, making single-attribute clustering inadequate. This study proposes a graph-enhanced clustering method integrating GIS-based spatial adjacency, architectural configuration, and institutional affiliation, with graph neural networks extracting node embeddings for single- and multi-relation clustering. Three representative types—Standardized Basilica Expansion, Localized Hybrid Adaptation, and Highland Western Composite—reflect Shanxi’s historical transition from isolation to openness and from traditional to hybrid local-imported forms, highlighting interactions among religious dissemination, topography, and construction practices. The findings demonstrate the value of combining spatial adjacency and semantic information in graph-based models, providing a transferable approach for typological classification and supporting pattern recognition in heritage studies.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Cultural Heritage Management and Preservation · Urban Design and Spatial Analysis · 3D Surveying and Cultural Heritage
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (45)
Show source-provided references
1. Jokilehto, J. Considerations on authenticity and integrity in the world heritage context. City Time 2, 1–16 (2006).
2. De Jong, S. Experiencing the Gothic style. Archit. Hist. 7, 25 (2019).10.5334/ah.351 ↗
3. Zhao, L. et al. Research on measuring methods and influencing factors of spatial damage degree of historic sites: a case study of three ancient cities in Shanxi, China. Buildings 13, 2957 (2023).10.3390/buildings13122957 ↗
4. Coomans, T., Xu, Y. & Zhang, J. “Imposing and provocative”: The design, style, construction and significance of Saint Anthony’s Cathedral, Xinjiang (Shanxi, China), 1936–40. In History of Construction Cultures Volume 1, 85–92 (CRC Press, 2021).10.1201/9781003173359-12 ↗
5. Coomans, T. Church architecture and church buildings: China. In The Palgrave Handbook of the Catholic Church in East Asia, 1–80 (Springer, 2023).10.1007/978-981-15-9365-9_8-1 ↗
6. Sideris, N. Spatial decision support in urban environments using machine learning, 3D geo-visualization and semantic integration of multi-source data. PhD thesis (Université de Limoges, 2019).
7. Kazmi, S. S. A., Ahmed, M., Mumtaz, R. & Anwar, Z. Spatiotemporal clustering and analysis of road accident hotspots by exploiting GIS technology and kernel density estimation. Comput. J. 65, 155–176 (2022).10.1093/comjnl/bxz158 ↗
8. Ma, X., Zhang, Y., Li, Y., Li, Y. & Lin, F. Spatial-temporal distribution and evolution of the socialist built heritage in China, 1949-1978. Herit. Sci. 11, 214 (2023).10.1186/s40494-023-01060-w ↗
9. Fu, J. & Mao, H. Study on the spatiotemporal distribution patterns and influencing factors of cultural heritage: a case study of Fujian Province. Herit. Sci. 12, 324 (2024).10.1186/s40494-024-01437-5 ↗
10. Yao, Y., Wang, X., Luo, L., Wan, H. & Ren, H. An overview of GIS-RS applications for archaeological and cultural heritage under the DBAR-heritage mission. Remote Sens. 15, 5766 (2023).10.3390/rs15245766 ↗
11. Agustina, I. H. GIS approach to spatial analysis of heritage settlement: case study of Magersari Kasepuhan palace, Indonesia. J. Eng. Sci. Technol. 16, 1614–1629 (2021).
12. Wu, Z. et al. A comprehensive survey on graph neural networks. IEEE Trans. Neural Netw. Learn. Syst. 32, 4–24 (2020).10.1109/TNNLS.2020.2978386 ↗
13. Chen, W. et al. Identifying the spatial differentiation factors of traditional villages in China. Herit. Sci. 11, 149 (2023).10.1186/s40494-023-00994-5 ↗
14. Wang, X., Tang, P. & Cai, C. Traditional Chinese village morphological feature extraction and cluster analysis based on multi-source data and machine learning. In Proc. Conf. on Computer Aided Architectural Design Research in Asia (CAADRIA), 179–188 (2023).10.52842/conf.caadria.2023.1.179 ↗
15. Lei, B., Liu, P., Milojevic-Dupont, N. & Biljecki, F. Predicting building characteristics at urban scale using graph neural networks and street-level context. Comput. Environ. Urban Syst. 111, 102129 (2024).10.1016/j.compenvurbsys.2024.102129 ↗
16. Yang, L. & Huang, W. Representation and assessment of spatial design using a hierarchical graph neural network: classification of shopping center types. Autom. Constr. 147, 104727 (2023).10.1016/j.autcon.2022.104727 ↗
17. Wang, Y. et al. Construction of cultural heritage knowledge graph based on graph attention neural network. Appl. Sci. 14, 8231 (2024).10.3390/app14188231 ↗
18. Huang, Y. Y. et al. Using knowledge graphs and deep learning algorithms to enhance digital cultural heritage management. Herit. Sci. 11, 204 (2023).10.1186/s40494-023-01042-y ↗
19. Zhang, R., Cheng, Y., Huang, J., Zhang, Y. & Yan, H. Unsupervised weathering identification of grottoes sandstone via statistical features of acoustic emission signals and graph neural network. Herit. Sci. 12, 323 (2024).10.1186/s40494-024-01432-w ↗
20. Liu, Y. et al. Integrating deformable CNN and attention mechanism into multi-scale graph neural network for few-shot image classification. Sci. Rep. 15, 1306 (2025).10.1038/s41598-025-85467-4 ↗
21. Ziazet, J. M., Boudreau, C., Delgado, O. & Jaumard, B. Designing graph neural networks training data with limited samples and small network sizes. ITU J. Future Evol. Technol. 4, 492–502 (2023).10.52953/AFYW5455 ↗
22. Wang, J., Mae, M. & Taniguchi, K. Risk control of energy performance fluctuation in multi-unit housing for weather uncertainty. Buildings 13, 1616 (2023).10.3390/buildings13071616 ↗
23. Chen, Y. et al. Exploring the spatial distribution characteristics and formation mechanisms of Hakka folk settlements: a case study of Hakka traditional architecture in southeastern China. Humanit. Soc. Sci. Commun. 12, 1–19 (2025).
24. Fan, T., Tang, X. & Li, K. Image clustering algorithm and psychological perception in historical building colour rating research: a case study of Guangzhou, China. Front. Archit. Res. 14, 1415–1435 (2025).10.1016/j.foar.2025.01.003 ↗
25. Xie, J., Girshick, R. & Farhadi, A. Unsupervised deep embedding for clustering analysis. In Int. Conf. on Machine Learning, 478–487 (PMLR, 2016).
26. Guo, X., Gao, L., Liu, X. & Yin, J. Improved deep embedded clustering with local structure preservation. IJCAI 17, 1753–1759 (2017).
27. Wu, J. et al. Deep comprehensive correlation mining for image clustering. In Proc. IEEE/CVF Int. Conf. on Computer Vision, 8150–8159 (2019).10.1109/ICCV.2019.00824 ↗
28. Elfarra, B. K., Salaha, M. A. A. & Ashour, W. M. Black hole clustering: gravity-based approach with no predetermined parameters. Data Sci. J. 23, 1 (2024).10.5334/dsj-2024-027 ↗
29. Trachtenberg, M. & Hyman, I. Architecture: From Prehistory to Postmodernity, 2nd edn. (H.N. Abrams, 2002).
30. Wang, Y. & Feng, K. Keeping Faith in Architecture: Catholic Church Architecture in Shanxi during the Period of Missionary Domination (American Academic Press, 2019).
31. Gilmer, J. et al. Neural message passing for quantum chemistry. In Int. Conf. on Machine Learning, 1263–1272 (PMLR, 2017).
32. Reiser, P. et al. Graph neural networks for materials science and chemistry. Commun. Mater. 3, 93 (2022).10.1038/s43246-022-00315-6 ↗
33. Chaudhari, K. & Thakkar, A. Neural network systems with an integrated coefficient of variation-based feature selection for stock price and trend prediction. Expert Syst. Appl. 219, 119527 (2023).10.1016/j.eswa.2023.119527 ↗
34. Hamilton, W., Ying, Z. & Leskovec, J. Inductive representation learning on large graphs. In Advances in Neural Information Processing Systems 30 (Curran Associates, Inc., 2017).
35. Van Zyl, J. J. The shuttle radar topography mission (SRTM): a breakthrough in remote sensing of topography. Acta Astronaut. 48, 559–565 (2001).10.1016/S0094-5765(01)00020-0 ↗
36. Xu, K., Hu, W., Leskovec, J. & Jegelka, S. How powerful are graph neural networks? In International Conference on Learning Representations (2019).
37. Bardes, A., Ponce, J. & LeCun, Y. VICReg: variance-invariance-covariance regularization for self-supervised learning. In Advances in Neural Information Processing Systems (2021).
38. Zbontar, J. et al. Barlow twins: self-supervised learning via redundancy reduction. In Int. Conf. on Machine Learning, 12310–12320 (PMLR, 2021).
39. Kipf, T. N. & Welling, M. Semi-supervised classification with graph convolutional networks. arXiv 1609.02907 (2016).
40. Li, Q., Han, Z. & Wu, X.-M. Deeper insights into graph convolutional networks for semi-supervised learning. Proc. AAAI Conf. Artif. Intell. 32, 1 (2018).
41. Lloyd, S. Least squares quantization in PCM. IEEE Trans. Inf. Theory 28, 129–137 (1982).10.1109/TIT.1982.1056489 ↗
42. Scarselli, F. et al. The graph neural network model. IEEE Trans. Neural Netw. 20, 61–80 (2008).10.1109/TNN.2008.2005605 ↗
43. Ketchen, D. J. & Shook, C. L. The application of cluster analysis in strategic management research: an analysis and critique. Strategic Manag. J. 17, 441–458 (1996).10.1002/(SICI)1097-0266(199606)17:6<441::AID-SMJ819>3.0.CO;2-G ↗
44. Khemani, B., Patil, S., Kotecha, K. & Tanwar, S. A review of graph neural networks: concepts, architectures, techniques, challenges, datasets, applications, and future directions. J. Big Data 11, 18 (2024).10.1186/s40537-023-00876-4 ↗
45. Oono, K. & Suzuki, T. Graph neural networks exponentially lose expressive power for node classification. In International Conference on Learning Representations (2020).