CMAB: A Multi-Attribute Building Dataset of China DOI Creative Commons
Yecheng Zhang, Huimin Zhao, Ying Long

et al.

Scientific Data, Journal Year: 2025, Volume and Issue: 12(1)

Published: March 12, 2025

Rapidly acquiring three-dimensional (3D) building data, including geometric attributes like rooftop, height and orientations, as well indicative function, quality, age, is essential for accurate urban analysis, simulations, policy updates. Current datasets suffer from incomplete coverage of multi-attributes. This paper presents the first national-scale Multi-Attribute Building dataset (CMAB) with artificial intelligence, covering 3,667 spatial cities, 31 million buildings, 23.6 billion m² rooftops an F1-Score 89.93% in OCRNet-based extraction, totaling 363 m³ stock. We trained bootstrap aggregated XGBoost models city administrative classifications, incorporating morphology, location, function features. Using multi-source billions remote sensing images 60 street view (SVIs), we generated height, structure, style, quality each machine learning large multimodal models. Accuracy was validated through model benchmarks, existing similar products, manual SVI validation, mostly above 80%. Our results are crucial global SDGs planning.

Language: Английский

A deep learning-based super-resolution method for building height estimation at 2.5 m spatial resolution in the Northern Hemisphere DOI Creative Commons
Yinxia Cao, Qihao Weng

Remote Sensing of Environment, Journal Year: 2024, Volume and Issue: 310, P. 114241 - 114241

Published: June 4, 2024

Language: Английский

Citations

12
Refining urban morphology: An explainable machine learning method for estimating footprint-level building height DOI
Yang Chen, Wenjie Sun, Ling Yang

et al.

Sustainable Cities and Society, Journal Year: 2024, Volume and Issue: 112, P. 105635 - 105635

Published: July 1, 2024

Language: Английский

Citations

5
Impacts of urban block form on carbon and pollutant emissions from urban life in China from the perspective of regional differences DOI
Wang Wei, Wenshan Su

Sustainable Cities and Society, Journal Year: 2024, Volume and Issue: unknown, P. 105849 - 105849

Published: Oct. 1, 2024

Language: Английский

Citations

4
CMAB: A Multi-Attribute Building Dataset of China DOI Creative Commons
Yecheng Zhang, Huimin Zhao, Ying Long

et al.

Scientific Data, Journal Year: 2025, Volume and Issue: 12(1)

Published: March 12, 2025

Rapidly acquiring three-dimensional (3D) building data, including geometric attributes like rooftop, height and orientations, as well indicative function, quality, age, is essential for accurate urban analysis, simulations, policy updates. Current datasets suffer from incomplete coverage of multi-attributes. This paper presents the first national-scale Multi-Attribute Building dataset (CMAB) with artificial intelligence, covering 3,667 spatial cities, 31 million buildings, 23.6 billion m² rooftops an F1-Score 89.93% in OCRNet-based extraction, totaling 363 m³ stock. We trained bootstrap aggregated XGBoost models city administrative classifications, incorporating morphology, location, function features. Using multi-source billions remote sensing images 60 street view (SVIs), we generated height, structure, style, quality each machine learning large multimodal models. Accuracy was validated through model benchmarks, existing similar products, manual SVI validation, mostly above 80%. Our results are crucial global SDGs planning.

Language: Английский

Citations

0