urbanflood24 Dataset

Urban Flood Spatiotemporal Simulation MIKE+ 2023 Journal of Hydrology

56 Rainfall Events

1 min Temporal Res.

1D–2D Coupled Model

500yr Max Return Period

About

The dataset is a spatial and temporal dynamic simulation of rainfall-induced urban flooding. A total of 56 rainfall events, including 20 measured rainfall events and 36 design rainfall events, are used to assess urban flooding induced by various rainfall conditions.

The measured rainfall events are the most severe events recorded in Shenzhen City, China, during 2008–2018, with a duration of 6 hours, rainfall amounts of 48–211 mm, and return periods of 0.1–20 years. To analyze potential extreme rainfall risk due to climate change, 36 design extreme rainfall events are generated based on Chicago storm profiles and Shenzhen rainfall intensity-duration-frequency (IDF) relationships, with a duration of 3 h, return periods of 100–500 years, time-peak ratios of 0.1–0.9, and a recording frequency of 1 min.

Flood spatiotemporal dynamics are generated by MIKE Plus 2023 with a 1D–2D coupled scheme at 1-minute recording frequency. Geo-information data including DSM, drainage inlet area, and imperviousness are also provided.

Training and testing sequences can be found in the GitHub repository.

News

(2026.03) We optimized the U-RNN GitHub repo for low-cost reproduction, including a one-click Google Colab demo!
(2025.04) Our paper is online! Please see Journal of Hydrology.
(2025.03) U-RNN is accepted by Journal of Hydrology! 🎊🎊🎊
(2024.12) We have released the urbanflood24 dataset!

Download

The dataset is publicly available from the following sources. All versions are identical in content.

Baidu Cloud password: urnn figshare no password

References

If you find this dataset useful, please cite:

@article{cao2025u, title   = {U-RNN high-resolution spatiotemporal nowcasting of urban flooding}, author  = {Cao, Xiaoyan and Wang, Baoying and Yao, Yao and Zhang, Lin and Xing, Yanwen and Mao, Junqi and Zhang, Runqiao and Fu, Guangtao and Borthwick, Alistair GL and Qin, Huapeng}, journal = {Journal of Hydrology}, pages   = {133117}, year    = {2025}, publisher = {Elsevier} }
@misc{cao2024supplementary, author    = {Cao, Xiaoyan and Wang, Baoying and Qin, Huapeng}, title     = {Supplementary data of U-RNN high-resolution spatiotemporal nowcasting of urban flooding}, year      = {2024}, publisher = {figshare}, note      = {Dataset} }

Contact

For questions or suggestions, contact us at caoxiaoyan@stu.pku.edu.cn.