Hierarchical partition of urban land-use units by unsupervised graph learning from high-resolution satellite images

Urban land use information can be effectively extracted from high-resolution satellite images for many urban applications. A significant challenge remains the accurate partition of fine-grained land-use units from these images. This paper presents a novel method for deriving these units based on uns...

Full description

Saved in:
Bibliographic Details
Main Authors: Mengmeng Li, Xinyi Gai, Kangkai Lou, Alfred Stein
Format: Article
Language:English
Published: Taylor & Francis Group 2024-12-01
Series:International Journal of Digital Earth
Subjects:
Online Access:https://www.tandfonline.com/doi/10.1080/17538947.2024.2432546
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850219387771944960
author Mengmeng Li
Xinyi Gai
Kangkai Lou
Alfred Stein
author_facet Mengmeng Li
Xinyi Gai
Kangkai Lou
Alfred Stein
author_sort Mengmeng Li
collection DOAJ
description Urban land use information can be effectively extracted from high-resolution satellite images for many urban applications. A significant challenge remains the accurate partition of fine-grained land-use units from these images. This paper presents a novel method for deriving these units based on unsupervised graph learning techniques using high-resolution satellite images and open street boundaries. Our method constructs a graph to represent spatial relations between land cover objects as graph nodes within a street block. These nodes are characterized by spatial composition and structure features of their surrounding neighborhood. We then apply unsupervised graph learning to partition the graph into subgraphs, which represent communities spatially bounded by street boundaries and correspond to land use units. Next, a graph neural network is used to extract deep structural features for land use classification. Experiments were conducted using high-resolution satellite images from the cities of Fuzhou and Quanzhou, China. Results showed that our method surpassed traditional grid and street block techniques, improving land use classification accuracy by 24% and 9%, respectively. Furthermore, it achieved classification results comparable to those using reference land use units, with an overall accuracy of 0.87 versus 0.89.
format Article
id doaj-art-3b9e5df7a447446e90f7c23b0ce726b8
institution OA Journals
issn 1753-8947
1753-8955
language English
publishDate 2024-12-01
publisher Taylor & Francis Group
record_format Article
series International Journal of Digital Earth
spelling doaj-art-3b9e5df7a447446e90f7c23b0ce726b82025-08-20T02:07:23ZengTaylor & Francis GroupInternational Journal of Digital Earth1753-89471753-89552024-12-0117110.1080/17538947.2024.2432546Hierarchical partition of urban land-use units by unsupervised graph learning from high-resolution satellite imagesMengmeng Li0Xinyi Gai1Kangkai Lou2Alfred Stein3Key Laboratory of Spatial Data Mining & Information Sharing of Ministry of Education, Academy of Digital China (Fujian), Fuzhou University, Fuzhou, People's Republic of ChinaKey Laboratory of Spatial Data Mining & Information Sharing of Ministry of Education, Academy of Digital China (Fujian), Fuzhou University, Fuzhou, People's Republic of ChinaKey Laboratory of Spatial Data Mining & Information Sharing of Ministry of Education, Academy of Digital China (Fujian), Fuzhou University, Fuzhou, People's Republic of ChinaFaculty of Geo-Information Science and Earth Observation (ITC), University of Twente, Enschede, The NetherlandsUrban land use information can be effectively extracted from high-resolution satellite images for many urban applications. A significant challenge remains the accurate partition of fine-grained land-use units from these images. This paper presents a novel method for deriving these units based on unsupervised graph learning techniques using high-resolution satellite images and open street boundaries. Our method constructs a graph to represent spatial relations between land cover objects as graph nodes within a street block. These nodes are characterized by spatial composition and structure features of their surrounding neighborhood. We then apply unsupervised graph learning to partition the graph into subgraphs, which represent communities spatially bounded by street boundaries and correspond to land use units. Next, a graph neural network is used to extract deep structural features for land use classification. Experiments were conducted using high-resolution satellite images from the cities of Fuzhou and Quanzhou, China. Results showed that our method surpassed traditional grid and street block techniques, improving land use classification accuracy by 24% and 9%, respectively. Furthermore, it achieved classification results comparable to those using reference land use units, with an overall accuracy of 0.87 versus 0.89.https://www.tandfonline.com/doi/10.1080/17538947.2024.2432546Land-use unit partitionurban land use classificationgraph neural networksObject-Community-Block (OCB)high-resolution satellite images
spellingShingle Mengmeng Li
Xinyi Gai
Kangkai Lou
Alfred Stein
Hierarchical partition of urban land-use units by unsupervised graph learning from high-resolution satellite images
International Journal of Digital Earth
Land-use unit partition
urban land use classification
graph neural networks
Object-Community-Block (OCB)
high-resolution satellite images
title Hierarchical partition of urban land-use units by unsupervised graph learning from high-resolution satellite images
title_full Hierarchical partition of urban land-use units by unsupervised graph learning from high-resolution satellite images
title_fullStr Hierarchical partition of urban land-use units by unsupervised graph learning from high-resolution satellite images
title_full_unstemmed Hierarchical partition of urban land-use units by unsupervised graph learning from high-resolution satellite images
title_short Hierarchical partition of urban land-use units by unsupervised graph learning from high-resolution satellite images
title_sort hierarchical partition of urban land use units by unsupervised graph learning from high resolution satellite images
topic Land-use unit partition
urban land use classification
graph neural networks
Object-Community-Block (OCB)
high-resolution satellite images
url https://www.tandfonline.com/doi/10.1080/17538947.2024.2432546
work_keys_str_mv AT mengmengli hierarchicalpartitionofurbanlanduseunitsbyunsupervisedgraphlearningfromhighresolutionsatelliteimages
AT xinyigai hierarchicalpartitionofurbanlanduseunitsbyunsupervisedgraphlearningfromhighresolutionsatelliteimages
AT kangkailou hierarchicalpartitionofurbanlanduseunitsbyunsupervisedgraphlearningfromhighresolutionsatelliteimages
AT alfredstein hierarchicalpartitionofurbanlanduseunitsbyunsupervisedgraphlearningfromhighresolutionsatelliteimages