Zhang et al. (2026) Mapping three decades of urban growth in China: a 30 m annual building height dataset (1990–2019)

Identification

• Journal: Earth system science data
• Year: 2026
• Date: 2026-07-24
• Authors: Yizhi Zhang, Yue-Han Wang, Quanhua Dong, Xiaojian Chen, Fan Zhang, Xuecao Li, Yu Liu
• DOI: 10.5194/essd-18-5329-2026

Research Groups

• Institute of Remote Sensing and Geographic Information System, School of Earth and Space Sciences, Peking University
• Key Laboratory of Radiometric Calibration and Validation for Environmental Satellites, National Satellite Meteorological Center (National Center for Space Weather), China Meteorological Administration
• Innovation Center for FengYun Meteorological Satellite
• Guangdong Key Laboratory for Urbanization and Geo-simulation, School of Geography and Planning, Sun Yat-Sen University

Short Summary

This study generates a framework to map annual building height datasets in China from 1990 to 2019 at 30m spatial resolution. The framework integrates multi-source remote sensing data through the eXtreme Gradient Boosting (XGBoost) model.

Objective

• Develop a long-term building height dataset for China from 1990 to 2019 with high accuracy and fine spatial resolution.
• Integrate multiple sources of remote sensing data, including optical, SAR, and terrain information, to improve estimation accuracy.
• Account for urban renewal processes by using the Continuous Change Detection and Classification (CCDC) algorithm.

Study Configuration

• Spatial Scale: 30m annual building height maps for China from 1990 to 2019.
• Temporal Scale: Annual data from 1990 to 2019, with a focus on long-term trends and changes in building heights.

Methodology and Data

• Models used:
  • eXtreme Gradient Boosting (XGBoost) model for height regression.
  • Random Forest regression framework for reconstructing VV backscatter data.
• Data sources:
  • Landsat surface reflectance time series data from 1990 to 2019.
  • Sentinel-1 and Sentinel-2 SAR data for building height mapping (2015-2019).
  • Terrain data, including ALOS World 3D-30m DSM and SRTM DEM.

Main Results

• The study generates annual building height maps for China from 1990 to 2019 at 30m spatial resolution.
• The framework achieves high accuracy, with nationwide RMSE values ranging between 3.20 and 4.27m.
• The results show pronounced horizontal and vertical expansion of Chinese cities between 1990 and 2019.

Contributions

• This study provides a long-term building height dataset for China from 1990 to 2019, which is essential for understanding urban growth patterns and guiding sustainable urban planning.
• The framework integrates multiple sources of remote sensing data, improving estimation accuracy and accounting for urban renewal processes.

Funding

• National Natural Science Foundation of China (Grant No. 41531180)
• National Key Research and Development Program of China (Grant No. 2017YFA0603600)

Citation

@article{Zhang2026Mapping,
  author = {Zhang, Yizhi and Wang, Yue-Han and Dong, Quanhua and Chen, Xiaojian and Zhang, Fan and Li, Xuecao and Liu, Yu},
  title = {Mapping three decades of urban growth in China: a 30 m annual building height dataset (1990–2019)},
  journal = {Earth system science data},
  year = {2026},
  doi = {10.5194/essd-18-5329-2026},
  url = {https://doi.org/10.5194/essd-18-5329-2026}
}