Developing an annual building volume dataset at 1-km resolution from 2001 to 2019 in China

ABSTRACT

Urban vertical features are crucial for understanding urban morphology. However, long-term information on three-dimensional buildings, which are important fundamental data for studying on the historical urbanization processes, remains scarce in China. In this study, we proposed a Random Forest model to generate an annual 1-km resolution building volume dataset covering mainland China from 2001 to 2019, by integrating the nighttime light data, population demographics, electricity consumption records, carbon dioxide emissions data, and various optical and statistical datasets. This new building volume data are highly consistent with that derived from Baidu Maps on 1-km scale, with Pearson’s correlation coefficient (R) of 0.847, root mean square error (RMSE) of 9.17 × 10⁵ m³/km² and mean absolute error (MAE) of 5.86 × 10⁵ m³/km². Notably, cross-validation indicate that the blooming problem was greatly improved when compared with previous model-based building three-dimensional data. The proposed method holds significant advantages, benefiting form low-cost implementation based on free open-source data and providing extendable algorithm to estimate the 3D shape of cities in the future. The time-series historical building volume data offer comprehensive insights into the historical development of urban structures, and provide valuable fundmental data for future urban planning, urban climate models and land use projections.

KEYWORDS:

• Urbanization
• building volume
• time-series information
• China
• machine learning
• urban planning

Acknowledgements

We thank Raffaele Lafortezza for his constructive suggestions on this paper.

Disclosure statement

No potential conflict of interest was reported by the author(s).

Data availability statement

Reference building data are available at http://map.baidu.com. Nighttime light data are available at https://doi.org/10.3974/geodb.2022.06.01.V1. CO₂ emissions data are available at http://db.cger.nies.go.jp/dataset/ODIAC/. Electricity consumption data are available at https://doi.org/10.6084/m9.figshare.19517272.v1. Artificial impervious area data are available at https://doi.org/10.5281/zenodo.4417810. Population data are available at https://landscan.ornl.gov. GDP per capita and Population growth rate data are available at National Bureau of Statistics of China. Normalized Difference Vegetation Index are available at https://www.resdc.cn/data.aspx?DATAID = 257. Modified Normalized Difference Water Index and Normalized Difference Built-up Index are available at Landsat5, Landsat7, Landsat8. Albedo data are available at https://doi.org/10.5067/MODIS/MCD43A3.061. Land surface temperature data are available at https://doi.org/10.5067/MODIS/MOD11A2.006. Digital Elevation Model data are available at http://www.earthenv.org/DEM.html. Global urban boundaries data are available at http://data.ess.tsinghua.edu.cn.

Code availability

The codes that were used in this work are available upon author request.

Author contributions

Y.S. designed the study, proposed the scientific hypothesis and revised the manuscript. W.Y. collected and analyzed the data, drew the figures and wrote the manuscript. J.W. and X.C. performed the analyses and revised the manuscript. All the authors reviewed and revised the paper.

Additional information

Funding

This study was supported by the National Natural Science Foundation of China [grant numbers 31971458, 41971275], Innovation Group Project of Southern Marine Science and Engineering Guangdong Laboratory (Zhuhai) [grant number 311021009], ‘GDAS’ Project of Science and Technology Development [grant numbers 2020GDASYL-20200102002, 2022GDASZH-2022010105, 2023GDASQNRC-0217 ], Science and Technology Program of Guangzhou, China [grant number 2024A04J3347].