Urban fabric decoded: High-precision building material identification via deep learning and remote sensing
Precise identification and categorization of building materials are essential for informing strategies related to embodied carbon reduction, building retrofitting, and circularity in urban environments. However, existing building material databases are typically limited to individual projects or spe...
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-03-01
|
| Series: | Environmental Science and Ecotechnology |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S266649842500016X |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850045636967137280 |
|---|---|
| author | Kun Sun Qiaoxuan Li Qiance Liu Jinchao Song Menglin Dai Xingjian Qian Srinivasa Raghavendra Bhuvan Gummidi Bailang Yu Felix Creutzig Gang Liu |
| author_facet | Kun Sun Qiaoxuan Li Qiance Liu Jinchao Song Menglin Dai Xingjian Qian Srinivasa Raghavendra Bhuvan Gummidi Bailang Yu Felix Creutzig Gang Liu |
| author_sort | Kun Sun |
| collection | DOAJ |
| description | Precise identification and categorization of building materials are essential for informing strategies related to embodied carbon reduction, building retrofitting, and circularity in urban environments. However, existing building material databases are typically limited to individual projects or specific geographic areas, offering only approximate assessments. Acquiring large-scale and precise material data is hindered by inadequate records and financial constraints. Here, we introduce a novel automated framework that harnesses recent advances in sensing technology and deep learning to identify roof and facade materials using remote sensing data and Google Street View imagery. The model was initially trained and validated on Odense's comprehensive dataset and then extended to characterize building materials across Danish urban landscapes, including Copenhagen, Aarhus, and Aalborg. Our approach demonstrates the model's scalability and adaptability to different geographic contexts and architectural styles, providing high-resolution insights into material distribution across diverse building types and cities. These findings are pivotal for informing sustainable urban planning, revising building codes to lower carbon emissions, and optimizing retrofitting efforts to meet contemporary standards for energy efficiency and emission reductions. |
| format | Article |
| id | doaj-art-deafbce7291c4e45af10510d96b745dc |
| institution | DOAJ |
| issn | 2666-4984 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Environmental Science and Ecotechnology |
| spelling | doaj-art-deafbce7291c4e45af10510d96b745dc2025-08-20T02:54:39ZengElsevierEnvironmental Science and Ecotechnology2666-49842025-03-012410053810.1016/j.ese.2025.100538Urban fabric decoded: High-precision building material identification via deep learning and remote sensingKun Sun0Qiaoxuan Li1Qiance Liu2Jinchao Song3Menglin Dai4Xingjian Qian5Srinivasa Raghavendra Bhuvan Gummidi6Bailang Yu7Felix Creutzig8Gang Liu9SDU Life Cycle Engineering, Department of Green Technology, University of Southern Denmark, Odense, 5230, DenmarkSchool of Resources and Environmental Science, Quanzhou Normal University, Quanzhou, 362000, ChinaSDU Life Cycle Engineering, Department of Green Technology, University of Southern Denmark, Odense, 5230, Denmark; College of Urban and Environmental Sciences, Peking University, Beijing, 100871, ChinaSDU Life Cycle Engineering, Department of Green Technology, University of Southern Denmark, Odense, 5230, DenmarkCollege of Urban and Environmental Sciences, Peking University, Beijing, 100871, ChinaKey Laboratory of Geographic Information Science, Ministry of Education, East China Normal University, Shanghai, 200241, China; School of Geographic Sciences, East China Normal University, Shanghai, 200241, ChinaSDU Life Cycle Engineering, Department of Green Technology, University of Southern Denmark, Odense, 5230, DenmarkKey Laboratory of Geographic Information Science, Ministry of Education, East China Normal University, Shanghai, 200241, China; School of Geographic Sciences, East China Normal University, Shanghai, 200241, ChinaMercator Research Institute on Global Commons and Climate Change, EUREF 19, Berlin, 10829, Germany; Bennett Institute for Innovation and Policy Acceleration, University of Sussex Business School, Brighton, BN1 9SL, UK; Technical University Berlin, Straßedes 17 Junis 135, Berlin, 10623, GermanyCollege of Urban and Environmental Sciences, Peking University, Beijing, 100871, China; Institute of Carbon Neutrality, Peking University, Beijing, 100871, China; Corresponding author. College of Urban and Environmental Sciences, Peking University, Beijing, 100871, China.Precise identification and categorization of building materials are essential for informing strategies related to embodied carbon reduction, building retrofitting, and circularity in urban environments. However, existing building material databases are typically limited to individual projects or specific geographic areas, offering only approximate assessments. Acquiring large-scale and precise material data is hindered by inadequate records and financial constraints. Here, we introduce a novel automated framework that harnesses recent advances in sensing technology and deep learning to identify roof and facade materials using remote sensing data and Google Street View imagery. The model was initially trained and validated on Odense's comprehensive dataset and then extended to characterize building materials across Danish urban landscapes, including Copenhagen, Aarhus, and Aalborg. Our approach demonstrates the model's scalability and adaptability to different geographic contexts and architectural styles, providing high-resolution insights into material distribution across diverse building types and cities. These findings are pivotal for informing sustainable urban planning, revising building codes to lower carbon emissions, and optimizing retrofitting efforts to meet contemporary standards for energy efficiency and emission reductions.http://www.sciencedirect.com/science/article/pii/S266649842500016XBuilding material intensityBuilt environmentStreetview imageRemote sensingDeep learning |
| spellingShingle | Kun Sun Qiaoxuan Li Qiance Liu Jinchao Song Menglin Dai Xingjian Qian Srinivasa Raghavendra Bhuvan Gummidi Bailang Yu Felix Creutzig Gang Liu Urban fabric decoded: High-precision building material identification via deep learning and remote sensing Environmental Science and Ecotechnology Building material intensity Built environment Streetview image Remote sensing Deep learning |
| title | Urban fabric decoded: High-precision building material identification via deep learning and remote sensing |
| title_full | Urban fabric decoded: High-precision building material identification via deep learning and remote sensing |
| title_fullStr | Urban fabric decoded: High-precision building material identification via deep learning and remote sensing |
| title_full_unstemmed | Urban fabric decoded: High-precision building material identification via deep learning and remote sensing |
| title_short | Urban fabric decoded: High-precision building material identification via deep learning and remote sensing |
| title_sort | urban fabric decoded high precision building material identification via deep learning and remote sensing |
| topic | Building material intensity Built environment Streetview image Remote sensing Deep learning |
| url | http://www.sciencedirect.com/science/article/pii/S266649842500016X |
| work_keys_str_mv | AT kunsun urbanfabricdecodedhighprecisionbuildingmaterialidentificationviadeeplearningandremotesensing AT qiaoxuanli urbanfabricdecodedhighprecisionbuildingmaterialidentificationviadeeplearningandremotesensing AT qianceliu urbanfabricdecodedhighprecisionbuildingmaterialidentificationviadeeplearningandremotesensing AT jinchaosong urbanfabricdecodedhighprecisionbuildingmaterialidentificationviadeeplearningandremotesensing AT menglindai urbanfabricdecodedhighprecisionbuildingmaterialidentificationviadeeplearningandremotesensing AT xingjianqian urbanfabricdecodedhighprecisionbuildingmaterialidentificationviadeeplearningandremotesensing AT srinivasaraghavendrabhuvangummidi urbanfabricdecodedhighprecisionbuildingmaterialidentificationviadeeplearningandremotesensing AT bailangyu urbanfabricdecodedhighprecisionbuildingmaterialidentificationviadeeplearningandremotesensing AT felixcreutzig urbanfabricdecodedhighprecisionbuildingmaterialidentificationviadeeplearningandremotesensing AT gangliu urbanfabricdecodedhighprecisionbuildingmaterialidentificationviadeeplearningandremotesensing |