Unsupervised Plot Morphology Classification via Graph Attention Networks: Evidence from Nanjing’s Walled City

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 aim...

Full description

Saved in:
Bibliographic Details
Main Authors: Ziyu Liu, Yacheng Song
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Land
Subjects:
Online Access:https://www.mdpi.com/2073-445X/14/7/1469
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849408984390303744
author Ziyu Liu
Yacheng Song
author_facet Ziyu Liu
Yacheng Song
author_sort Ziyu Liu
collection DOAJ
description 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.
format Article
id doaj-art-015241a41e574843bd9b1d61dcb5907d
institution Kabale University
issn 2073-445X
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Land
spelling doaj-art-015241a41e574843bd9b1d61dcb5907d2025-08-20T03:35:38ZengMDPI AGLand2073-445X2025-07-01147146910.3390/land14071469Unsupervised Plot Morphology Classification via Graph Attention Networks: Evidence from Nanjing’s Walled CityZiyu Liu0Yacheng Song1School of Architecture, Southeast University, Nanjing 210096, ChinaSchool of Architecture, Southeast University, Nanjing 210096, ChinaUrban 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.https://www.mdpi.com/2073-445X/14/7/1469urban morphologyplot classificationgraph attention networkspatial relationshipsurban renewal
spellingShingle Ziyu Liu
Yacheng Song
Unsupervised Plot Morphology Classification via Graph Attention Networks: Evidence from Nanjing’s Walled City
Land
urban morphology
plot classification
graph attention network
spatial relationships
urban renewal
title Unsupervised Plot Morphology Classification via Graph Attention Networks: Evidence from Nanjing’s Walled City
title_full Unsupervised Plot Morphology Classification via Graph Attention Networks: Evidence from Nanjing’s Walled City
title_fullStr Unsupervised Plot Morphology Classification via Graph Attention Networks: Evidence from Nanjing’s Walled City
title_full_unstemmed Unsupervised Plot Morphology Classification via Graph Attention Networks: Evidence from Nanjing’s Walled City
title_short Unsupervised Plot Morphology Classification via Graph Attention Networks: Evidence from Nanjing’s Walled City
title_sort unsupervised plot morphology classification via graph attention networks evidence from nanjing s walled city
topic urban morphology
plot classification
graph attention network
spatial relationships
urban renewal
url https://www.mdpi.com/2073-445X/14/7/1469
work_keys_str_mv AT ziyuliu unsupervisedplotmorphologyclassificationviagraphattentionnetworksevidencefromnanjingswalledcity
AT yachengsong unsupervisedplotmorphologyclassificationviagraphattentionnetworksevidencefromnanjingswalledcity