Urban open space (UOS) plays an important role, especially in areas characterized by intense social and economic activity. However, UOS mapping products for major cities around the world are lacking. To fill this gap, we used a deep learning–based method based on a tiny-manual annotation strategy to map UOS and produced a 1.19 m resolution UOS map of 2021 in urban areas of global 169 megacities with populations of over 3,000,000 people (namely the OpenspaceGlobal product). It contains five urban open space categories, namely "park and green spaces," "outdoor sports spaces," "transportation spaces," "water body spaces", and "background". The OpenspaceGlobal product can promote a better understanding of human-made space surfaces in major cities worldwide and facilitate functions such as urban livability estimation, urban planning, and sustainable development. The OpenspaceGlobal product is free to use for non-commercial forms including scientific research and science promotion under proper citation.
https://doi.org/10.57760/sciencedb.09109.
https://www.nature.com/articles/s41597-025-04924-x
If it is helpful for you, please cite the following references.
@article{fan2025first,
title={The first urban open space product of global 169 megacities using remote sensing and geospatial data},
author={Fan, Runyu and Wang, Lizhe and Xu, Zijian and Niu, Hongyang and Chen, Jiajun and Zhou, Zhaoying and Li, Wenyue and Wang, Haoyu and Sun, Yuyue and Feng, Ruyi},
journal={Scientific Data},
volume={12},
number={1},
pages={586},
year={2025},
publisher={Nature Publishing Group UK London}
}