Delineating Mixed Urban “Jobs-Housing” Patterns at a Fine Scale by Using High Spatial Resolution Remote-Sensing Imagery

The spatial distribution pattern of jobs and housing plays a vital role in urban planning and traffic construction. However, obtaining the jobs-housing distribution at a fine scale (e.g., the perspective of individual jobs-housing attribute) presents difficulties due to a lack of social media data a...

Full description

Saved in:
Bibliographic Details
Main Authors: Yao Yao, Chen Qian, Ye Hong, Qingfeng Guan, Jingmin Chen, Liangyang Dai, Zhangwei Jiang, Xun Liang
Format: Article
Language:English
Published: Wiley 2020-01-01
Series:Complexity
Online Access:http://dx.doi.org/10.1155/2020/8018629
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849469277516595200
author Yao Yao
Chen Qian
Ye Hong
Qingfeng Guan
Jingmin Chen
Liangyang Dai
Zhangwei Jiang
Xun Liang
author_facet Yao Yao
Chen Qian
Ye Hong
Qingfeng Guan
Jingmin Chen
Liangyang Dai
Zhangwei Jiang
Xun Liang
author_sort Yao Yao
collection DOAJ
description The spatial distribution pattern of jobs and housing plays a vital role in urban planning and traffic construction. However, obtaining the jobs-housing distribution at a fine scale (e.g., the perspective of individual jobs-housing attribute) presents difficulties due to a lack of social media data and useful models. With user data acquired from a location-based service provider in China, this study employs a deep bag-of-features network (BagNet) to classify remote-sensing (RS) images into various jobs-housing types. Considering Wuhan, one of the fastest developing cities in China, as a case study area, three jobs-housing types (i.e., only working, only living, and both working and living) at the land-parcel level are obtained. We demonstrate that the multiscale random sampling method can reduce the influence of image noise, increase the utilization of training data, and reduce network overfitting. By altering the network structure and the training strategy, BagNet achieved excellent fitting accuracy for identifying each jobs-housing type (overall accuracy > 0.84 and kappa > 0.8). For the first time, we demonstrate that urban socioeconomic characteristics can be obtained from high-resolution RS images using deep learning techniques. Additionally, we conclude that the total level of mixing within Wuhan is not high at present; however, Wuhan is continuously improving the mixture of jobs and housing. This study has reference value for extracting urban socioeconomic characteristics from RS images and could be used in urban planning as well as government management.
format Article
id doaj-art-fbf695173d00443ebcbddebdcdd1efbf
institution Kabale University
issn 1076-2787
1099-0526
language English
publishDate 2020-01-01
publisher Wiley
record_format Article
series Complexity
spelling doaj-art-fbf695173d00443ebcbddebdcdd1efbf2025-08-20T03:25:33ZengWileyComplexity1076-27871099-05262020-01-01202010.1155/2020/80186298018629Delineating Mixed Urban “Jobs-Housing” Patterns at a Fine Scale by Using High Spatial Resolution Remote-Sensing ImageryYao Yao0Chen Qian1Ye Hong2Qingfeng Guan3Jingmin Chen4Liangyang Dai5Zhangwei Jiang6Xun Liang7School of Geography and Information Engineering, China University of Geosciences, Wuhan 430078, Hubei, ChinaDepartment of Engineering Systems and Environment, University of Virginia, Charlottesville,, VA 22904, USAInstitute of Cartography and Geoinformation, ETH Zurich, Stefano-Franscini-Platz 5, CH-8093 Zürich, SwitzerlandSchool of Geography and Information Engineering, China University of Geosciences, Wuhan 430078, Hubei, ChinaDepartment of Data Technology and Products, Alibaba Group, Hangzhou 311121, Zhejiang, ChinaSchool of Geography and Information Engineering, China University of Geosciences, Wuhan 430078, Hubei, ChinaDepartment of Data Technology and Products, Alibaba Group, Hangzhou 311121, Zhejiang, ChinaSchool of Geography and Information Engineering, China University of Geosciences, Wuhan 430078, Hubei, ChinaThe spatial distribution pattern of jobs and housing plays a vital role in urban planning and traffic construction. However, obtaining the jobs-housing distribution at a fine scale (e.g., the perspective of individual jobs-housing attribute) presents difficulties due to a lack of social media data and useful models. With user data acquired from a location-based service provider in China, this study employs a deep bag-of-features network (BagNet) to classify remote-sensing (RS) images into various jobs-housing types. Considering Wuhan, one of the fastest developing cities in China, as a case study area, three jobs-housing types (i.e., only working, only living, and both working and living) at the land-parcel level are obtained. We demonstrate that the multiscale random sampling method can reduce the influence of image noise, increase the utilization of training data, and reduce network overfitting. By altering the network structure and the training strategy, BagNet achieved excellent fitting accuracy for identifying each jobs-housing type (overall accuracy > 0.84 and kappa > 0.8). For the first time, we demonstrate that urban socioeconomic characteristics can be obtained from high-resolution RS images using deep learning techniques. Additionally, we conclude that the total level of mixing within Wuhan is not high at present; however, Wuhan is continuously improving the mixture of jobs and housing. This study has reference value for extracting urban socioeconomic characteristics from RS images and could be used in urban planning as well as government management.http://dx.doi.org/10.1155/2020/8018629
spellingShingle Yao Yao
Chen Qian
Ye Hong
Qingfeng Guan
Jingmin Chen
Liangyang Dai
Zhangwei Jiang
Xun Liang
Delineating Mixed Urban “Jobs-Housing” Patterns at a Fine Scale by Using High Spatial Resolution Remote-Sensing Imagery
Complexity
title Delineating Mixed Urban “Jobs-Housing” Patterns at a Fine Scale by Using High Spatial Resolution Remote-Sensing Imagery
title_full Delineating Mixed Urban “Jobs-Housing” Patterns at a Fine Scale by Using High Spatial Resolution Remote-Sensing Imagery
title_fullStr Delineating Mixed Urban “Jobs-Housing” Patterns at a Fine Scale by Using High Spatial Resolution Remote-Sensing Imagery
title_full_unstemmed Delineating Mixed Urban “Jobs-Housing” Patterns at a Fine Scale by Using High Spatial Resolution Remote-Sensing Imagery
title_short Delineating Mixed Urban “Jobs-Housing” Patterns at a Fine Scale by Using High Spatial Resolution Remote-Sensing Imagery
title_sort delineating mixed urban jobs housing patterns at a fine scale by using high spatial resolution remote sensing imagery
url http://dx.doi.org/10.1155/2020/8018629
work_keys_str_mv AT yaoyao delineatingmixedurbanjobshousingpatternsatafinescalebyusinghighspatialresolutionremotesensingimagery
AT chenqian delineatingmixedurbanjobshousingpatternsatafinescalebyusinghighspatialresolutionremotesensingimagery
AT yehong delineatingmixedurbanjobshousingpatternsatafinescalebyusinghighspatialresolutionremotesensingimagery
AT qingfengguan delineatingmixedurbanjobshousingpatternsatafinescalebyusinghighspatialresolutionremotesensingimagery
AT jingminchen delineatingmixedurbanjobshousingpatternsatafinescalebyusinghighspatialresolutionremotesensingimagery
AT liangyangdai delineatingmixedurbanjobshousingpatternsatafinescalebyusinghighspatialresolutionremotesensingimagery
AT zhangweijiang delineatingmixedurbanjobshousingpatternsatafinescalebyusinghighspatialresolutionremotesensingimagery
AT xunliang delineatingmixedurbanjobshousingpatternsatafinescalebyusinghighspatialresolutionremotesensingimagery