Multi-spatial urban function modeling: A multi-modal deep network approach for transfer and multi-task learning
Understanding dynamics of urban land-use is crucial for comprehending urban spaces and evaluating planning strategies. A range of data-driven models based on the representation learning of multiple data sources have focused on extracting spatially explicit characteristics at the feature level for ur...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-02-01
|
| Series: | International Journal of Applied Earth Observations and Geoinformation |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1569843225000445 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832540427887050752 |
|---|---|
| author | Zhaoya Gong Chenglong Wang Bin Liu Binbo Li Wei Tu Yuting Chen Zhicheng Deng Pengjun Zhao |
| author_facet | Zhaoya Gong Chenglong Wang Bin Liu Binbo Li Wei Tu Yuting Chen Zhicheng Deng Pengjun Zhao |
| author_sort | Zhaoya Gong |
| collection | DOAJ |
| description | Understanding dynamics of urban land-use is crucial for comprehending urban spaces and evaluating planning strategies. A range of data-driven models based on the representation learning of multiple data sources have focused on extracting spatially explicit characteristics at the feature level for urban function inference. However, they commonly pay no attention to the systematic relationships between urban land-use and transportation as the core components of urban systems. Consequently, while performing relatively well in urban land-use recognition, these models cannot transfer across various urban tasks and have almost no generalizability in integrated urban modeling. Guided by the theory of integrated land-use and transport modeling, this study proposes a multi-modal deep learning model to leverage the systematic relationships between urban components. First, spaces of urban places, urban forms, urban flows, and urban locations are conceptualized from the interactions between land use and transportation systems and represented by multi-source heterogeneous spatial features. Second, to account for both direct and indirect interactions in these spaces, a Deep & Wide network is introduced to fuse different modalities of spatial features. Using Shenzhen city as a testbed, extensive experimental results show that our approach improves accuracy by 13.3% compared to state-of-the-art models. We further validate the superior generalizability of our approach across various urban tasks, such as predicting urban land-use, housing prices, and population density, over other baselines. Enabling such a doubly-informed framework of urban theory and AI, this study provides a pilot demonstration for the new scientific paradigm of AI for Urban Science and Modeling. |
| format | Article |
| id | doaj-art-e11ebc3ebe164f468cad98f93d595d87 |
| institution | Kabale University |
| issn | 1569-8432 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Elsevier |
| record_format | Article |
| series | International Journal of Applied Earth Observations and Geoinformation |
| spelling | doaj-art-e11ebc3ebe164f468cad98f93d595d872025-02-05T04:31:17ZengElsevierInternational Journal of Applied Earth Observations and Geoinformation1569-84322025-02-01136104397Multi-spatial urban function modeling: A multi-modal deep network approach for transfer and multi-task learningZhaoya Gong0Chenglong Wang1Bin Liu2Binbo Li3Wei Tu4Yuting Chen5Zhicheng Deng6Pengjun Zhao7School of Urban Planning & Design, Peking University Shenzhen Graduate School, Shenzhen, China; Key Laboratory of Earth Surface System and Human-Earth Relations of Ministry of Natural Resources of China, Peking University Shenzhen Graduate School, Shenzhen, China; Guangdong – Hong Kong – Macau Joint Laboratory for Smart Cities, Shenzhen University, Shenzhen, China; Corresponding authors at: School of Urban Planning & Design, Peking University Shenzhen Graduate School, 518061 Shenzhen, China.School of Urban Planning & Design, Peking University Shenzhen Graduate School, Shenzhen, China; Key Laboratory of Earth Surface System and Human-Earth Relations of Ministry of Natural Resources of China, Peking University Shenzhen Graduate School, Shenzhen, ChinaSchool of Urban Planning & Design, Peking University Shenzhen Graduate School, Shenzhen, China; Key Laboratory of Earth Surface System and Human-Earth Relations of Ministry of Natural Resources of China, Peking University Shenzhen Graduate School, Shenzhen, ChinaSchool of Urban Planning & Design, Peking University Shenzhen Graduate School, Shenzhen, China; Key Laboratory of Earth Surface System and Human-Earth Relations of Ministry of Natural Resources of China, Peking University Shenzhen Graduate School, Shenzhen, ChinaGuangdong – Hong Kong – Macau Joint Laboratory for Smart Cities, Shenzhen University, Shenzhen, China; Shenzhen Key Laboratory of Spatial Information Smart Sensing and Services, Shenzhen University, Shenzhen, China; Guangdong Key Laboratory for Urban Informatics, Shenzhen University, Shenzhen, China; Key Laboratory for Geo-Environmental Monitoring of Great Bay Area, MNR, Shenzhen University, Shenzhen, ChinaPetrochina Shenzhen New Energy Research Institute Co., Ltd, Shenzhen, ChinaSchool of Urban Planning & Design, Peking University Shenzhen Graduate School, Shenzhen, China; Key Laboratory of Earth Surface System and Human-Earth Relations of Ministry of Natural Resources of China, Peking University Shenzhen Graduate School, Shenzhen, ChinaSchool of Urban Planning & Design, Peking University Shenzhen Graduate School, Shenzhen, China; Key Laboratory of Earth Surface System and Human-Earth Relations of Ministry of Natural Resources of China, Peking University Shenzhen Graduate School, Shenzhen, China; Corresponding authors at: School of Urban Planning & Design, Peking University Shenzhen Graduate School, 518061 Shenzhen, China.Understanding dynamics of urban land-use is crucial for comprehending urban spaces and evaluating planning strategies. A range of data-driven models based on the representation learning of multiple data sources have focused on extracting spatially explicit characteristics at the feature level for urban function inference. However, they commonly pay no attention to the systematic relationships between urban land-use and transportation as the core components of urban systems. Consequently, while performing relatively well in urban land-use recognition, these models cannot transfer across various urban tasks and have almost no generalizability in integrated urban modeling. Guided by the theory of integrated land-use and transport modeling, this study proposes a multi-modal deep learning model to leverage the systematic relationships between urban components. First, spaces of urban places, urban forms, urban flows, and urban locations are conceptualized from the interactions between land use and transportation systems and represented by multi-source heterogeneous spatial features. Second, to account for both direct and indirect interactions in these spaces, a Deep & Wide network is introduced to fuse different modalities of spatial features. Using Shenzhen city as a testbed, extensive experimental results show that our approach improves accuracy by 13.3% compared to state-of-the-art models. We further validate the superior generalizability of our approach across various urban tasks, such as predicting urban land-use, housing prices, and population density, over other baselines. Enabling such a doubly-informed framework of urban theory and AI, this study provides a pilot demonstration for the new scientific paradigm of AI for Urban Science and Modeling.http://www.sciencedirect.com/science/article/pii/S1569843225000445Urban functionsLand useMulti-modal deep learningTransfer learningMulti-task learning |
| spellingShingle | Zhaoya Gong Chenglong Wang Bin Liu Binbo Li Wei Tu Yuting Chen Zhicheng Deng Pengjun Zhao Multi-spatial urban function modeling: A multi-modal deep network approach for transfer and multi-task learning International Journal of Applied Earth Observations and Geoinformation Urban functions Land use Multi-modal deep learning Transfer learning Multi-task learning |
| title | Multi-spatial urban function modeling: A multi-modal deep network approach for transfer and multi-task learning |
| title_full | Multi-spatial urban function modeling: A multi-modal deep network approach for transfer and multi-task learning |
| title_fullStr | Multi-spatial urban function modeling: A multi-modal deep network approach for transfer and multi-task learning |
| title_full_unstemmed | Multi-spatial urban function modeling: A multi-modal deep network approach for transfer and multi-task learning |
| title_short | Multi-spatial urban function modeling: A multi-modal deep network approach for transfer and multi-task learning |
| title_sort | multi spatial urban function modeling a multi modal deep network approach for transfer and multi task learning |
| topic | Urban functions Land use Multi-modal deep learning Transfer learning Multi-task learning |
| url | http://www.sciencedirect.com/science/article/pii/S1569843225000445 |
| work_keys_str_mv | AT zhaoyagong multispatialurbanfunctionmodelingamultimodaldeepnetworkapproachfortransferandmultitasklearning AT chenglongwang multispatialurbanfunctionmodelingamultimodaldeepnetworkapproachfortransferandmultitasklearning AT binliu multispatialurbanfunctionmodelingamultimodaldeepnetworkapproachfortransferandmultitasklearning AT binboli multispatialurbanfunctionmodelingamultimodaldeepnetworkapproachfortransferandmultitasklearning AT weitu multispatialurbanfunctionmodelingamultimodaldeepnetworkapproachfortransferandmultitasklearning AT yutingchen multispatialurbanfunctionmodelingamultimodaldeepnetworkapproachfortransferandmultitasklearning AT zhichengdeng multispatialurbanfunctionmodelingamultimodaldeepnetworkapproachfortransferandmultitasklearning AT pengjunzhao multispatialurbanfunctionmodelingamultimodaldeepnetworkapproachfortransferandmultitasklearning |