Urban street network morphology classification through street-block based graph neural networks and multi-model fusion

Precise categorization of urban street network patterns is essential for urban planning and morphology analysis. Current classification methods typically rely on a single model type, which causes them to struggle in considering topological, geometric, visual, and global features simultaneously, lead...

Full description

Saved in:
Bibliographic Details
Main Authors: Yang Liu, Qingsheng Guo, Chuanbang Zheng
Format: Article
Language:English
Published: Taylor & Francis Group 2025-08-01
Series:International Journal of Digital Earth
Subjects:
Online Access:https://www.tandfonline.com/doi/10.1080/17538947.2025.2497490
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849224286665965568
author Yang Liu
Qingsheng Guo
Chuanbang Zheng
author_facet Yang Liu
Qingsheng Guo
Chuanbang Zheng
author_sort Yang Liu
collection DOAJ
description Precise categorization of urban street network patterns is essential for urban planning and morphology analysis. Current classification methods typically rely on a single model type, which causes them to struggle in considering topological, geometric, visual, and global features simultaneously, leading to suboptimal results. To address this, we propose a novel fusion model that integrates three submodels: our proposed street-block graph neural network (SBGNet), a convolutional neural network (CNN) using ResNet-34, and a multi-layer perceptron (MLP). SBGNet represents urban street networks as graphs, with nodes as street blocks and geometric features as node attributes, while spatial arrangements serve as edge features. Topological and geometric features are extracted from this street-block representation. The CNN extracts visual features from monochrome images of the street network, and the MLP computes global descriptors using OSMnx and NetworkX to extract global features. Features from SBGNet, CNN, and MLP are concatenated and processed through a downstream MLP for classification. Experiments on a dataset of 6,700 samples from 12 major U.S. cities demonstrate that our fusion model significantly outperforms traditional methods, achieving a PR AUC of 0.88 ± 0.01, with improvements of 5% to 33% over baseline models, validating its effectiveness in classifying complex urban street networks.
format Article
id doaj-art-4e4fd027316841bba21cbb3cdb7f4cf7
institution Kabale University
issn 1753-8947
1753-8955
language English
publishDate 2025-08-01
publisher Taylor & Francis Group
record_format Article
series International Journal of Digital Earth
spelling doaj-art-4e4fd027316841bba21cbb3cdb7f4cf72025-08-25T11:28:39ZengTaylor & Francis GroupInternational Journal of Digital Earth1753-89471753-89552025-08-0118110.1080/17538947.2025.2497490Urban street network morphology classification through street-block based graph neural networks and multi-model fusionYang Liu0Qingsheng Guo1Chuanbang Zheng2School of Resource and Environmental Sciences, Wuhan University, Wuhan, People’s Republic of ChinaSchool of Resource and Environmental Sciences, Wuhan University, Wuhan, People’s Republic of ChinaSchool of Resource and Environmental Sciences, Wuhan University, Wuhan, People’s Republic of ChinaPrecise categorization of urban street network patterns is essential for urban planning and morphology analysis. Current classification methods typically rely on a single model type, which causes them to struggle in considering topological, geometric, visual, and global features simultaneously, leading to suboptimal results. To address this, we propose a novel fusion model that integrates three submodels: our proposed street-block graph neural network (SBGNet), a convolutional neural network (CNN) using ResNet-34, and a multi-layer perceptron (MLP). SBGNet represents urban street networks as graphs, with nodes as street blocks and geometric features as node attributes, while spatial arrangements serve as edge features. Topological and geometric features are extracted from this street-block representation. The CNN extracts visual features from monochrome images of the street network, and the MLP computes global descriptors using OSMnx and NetworkX to extract global features. Features from SBGNet, CNN, and MLP are concatenated and processed through a downstream MLP for classification. Experiments on a dataset of 6,700 samples from 12 major U.S. cities demonstrate that our fusion model significantly outperforms traditional methods, achieving a PR AUC of 0.88 ± 0.01, with improvements of 5% to 33% over baseline models, validating its effectiveness in classifying complex urban street networks.https://www.tandfonline.com/doi/10.1080/17538947.2025.2497490Urban morphologygraph neural networks (GNN)street-block graph representationmulti-model fusionurban street network classification
spellingShingle Yang Liu
Qingsheng Guo
Chuanbang Zheng
Urban street network morphology classification through street-block based graph neural networks and multi-model fusion
International Journal of Digital Earth
Urban morphology
graph neural networks (GNN)
street-block graph representation
multi-model fusion
urban street network classification
title Urban street network morphology classification through street-block based graph neural networks and multi-model fusion
title_full Urban street network morphology classification through street-block based graph neural networks and multi-model fusion
title_fullStr Urban street network morphology classification through street-block based graph neural networks and multi-model fusion
title_full_unstemmed Urban street network morphology classification through street-block based graph neural networks and multi-model fusion
title_short Urban street network morphology classification through street-block based graph neural networks and multi-model fusion
title_sort urban street network morphology classification through street block based graph neural networks and multi model fusion
topic Urban morphology
graph neural networks (GNN)
street-block graph representation
multi-model fusion
urban street network classification
url https://www.tandfonline.com/doi/10.1080/17538947.2025.2497490
work_keys_str_mv AT yangliu urbanstreetnetworkmorphologyclassificationthroughstreetblockbasedgraphneuralnetworksandmultimodelfusion
AT qingshengguo urbanstreetnetworkmorphologyclassificationthroughstreetblockbasedgraphneuralnetworksandmultimodelfusion
AT chuanbangzheng urbanstreetnetworkmorphologyclassificationthroughstreetblockbasedgraphneuralnetworksandmultimodelfusion