Unsupervised Plot Morphology Classification via Graph Attention Networks: Evidence from Nanjing’s Walled City
Open Access
Abstract
Urban plots are pivotal links between individual buildings and the city fabric, yet conventional plot classification methods often overlook how buildings interact within each plot. This oversight is particularly problematic in the irregular fabrics typical of many Global South cities. This study aims to create a plot classification method that jointly captures metric and configurational characteristics. Our approach converts each cadastral plot into a graph whose nodes are building centroids and whose edges reflect Delaunay-based proximity. The model then learns unsupervised graph embeddings with a two-layer Graph Attention Network guided by a triple loss that couples building morphology with spatial topology. We then cluster the embeddings together with normalized plot metrics. Applying the model to 8973 plots in Nanjing’s historic walled city yields seven distinct plot morphological types. The framework separates plots that share identical FAR–GSI values but differ in internal organization. The baseline and ablation experiments confirm the indispensability of both configurational and metric information. Each type aligns with specific renewal strategies, from incremental upgrades of courtyard slabs to skyline management of high-rise complexes. By integrating quantitative graph learning with classical typo-morphology theory, this study not only advances urban form research but also offers planners a tool for context-sensitive urban regeneration and land-use management.Keywords
This publication has 48 references indexed in Scilit:
- Interpreting core forms of urban morphology linked to urban functions with explainable graph neural networkComputers, Environment and Urban Systems, 2025
- Graph theory applications for advanced geospatial modelling and decision-makingApplied Geomatics, 2024
- Predicting building characteristics at urban scale using graph neural networks and street-level contextComputers, Environment and Urban Systems, 2024
- Deciphering built form complexity of Chinese cities through plot recognition: A case study of Nanjing, ChinaFrontiers of Architectural Research, 2022
- Unsupervised machine learning in urban studies: A systematic review of applicationsCities, 2022
- Towards a morphogenesis of informal settlementsHabitat International, 2020
- An enhanced support vector machine model for urban expansion predictionComputers, Environment and Urban Systems, 2019
- Street Network Studies: from Networks to Models and their RepresentationsNetworks and Spatial Economics, 2018
- Assessing contextual descriptive features for plot-based classification of urban areasLandscape and Urban Planning, 2012
- Two algorithms for constructing a Delaunay triangulationInternational Journal of Parallel Programming, 1980