Spatial logic of Ming Great Wall beacon tower siting in Yansui Garrison using graph-based modeling
Beacon towers were warning and communication nodes in the Ming Great Wall defense system. We developed an interpretable graph learning framework combining a graph attention network (GAT) with random forest (RF) for Yansui Garrison. The GAT learned graph embeddings by integrating 11 node variables with spatial neighborhood relations, and RF used these embeddings to predict relative siting propensity. Connection weights, component correlations, and partial dependence plots characterized how siting relationships differed between individual and neighborhood scales. GAT-RF achieved a test R ² of 0.896, outperforming RF on original variables (0.842) and GAT alone (0.561), with stable performance across distance thresholds. Individual modes declined from east to west, while neighborhood modes increased. This shift reflected route differences between individual and neighborhood scales. Beacon tower siting can be understood in terms of a scale-dependent spatial logic, in which node attributes and neighborhood relations are jointly associated with the spatial organization of networked heritage.
Authors
- Qian-Cheng Wang (ORCID: https://orcid.org/0000-0003-1445-5578)
- Yuan Li (ORCID: https://orcid.org/0000-0002-9513-4233)
- Zhaoyi Li (ORCID: https://orcid.org/0009-0003-3761-3951)
- Chunlei Yu
- Kanhua Yu
Institutions
- Xi'an University of Architecture and Technology (CN)
- City University of Hong Kong (HK)
- Chang'an University (CN)
- Institute of Archaeology (CN)
Publication Details
- Journal
- npj Heritage Science
- Published
- 2026-11-12
- DOI
- https://doi.org/10.1038/s40494-026-03095-1
- Primary Topic
- Urban Design and Spatial Analysis
- Type
- article
- Field-Weighted Citation Impact
- 0.00