Articles | Volume 25, issue 11
https://doi.org/10.5194/hess-25-5981-2021
https://doi.org/10.5194/hess-25-5981-2021
Research article
 | 
22 Nov 2021
Research article |  | 22 Nov 2021

Design flood estimation for global river networks based on machine learning models

Gang Zhao, Paul Bates, Jeffrey Neal, and Bo Pang

Related authors

Flood Volume Allocation Method for Flood Hazard Mapping Using River Model with Levee Scheme
Muhammad Hasnain Aslam, Yukiko Hirabayashi, Dai Yamazaki, Gang Zhao, Yuki Kita, and Do Ngoc Khanh
EGUsphere, https://doi.org/10.5194/egusphere-2025-4358,https://doi.org/10.5194/egusphere-2025-4358, 2025
This preprint is open for discussion and under review for Geoscientific Model Development (GMD).
Short summary

Cited articles

Ahmad, M. I., Sinclair, C., and Spurr, B.: Assessment of flood frequency models using empirical distribution function statistics, Water Resour. Res., 24, 1323–1328, 1988. 
Alexandersson, H.: A Homogeneity Test Applied to Precipitation Data, J Climatol., 6, 661–675, https://doi.org/10.1002/joc.3370060607, 1986. 
Bárdossy, A., Pegram, G. G., and Samaniego, L.: Modeling data relationships with a local variance reducing technique: Applications in hydrology, Water Resour. Res., 41, W08404, https://doi.org/10.1029/2004WR003851, 2005. 
Bates, P. D., Quinn, N., Sampson, C., Smith, A., Wing, O., Sosa, J., Savage, J., Olcese, G., Neal, J., and Schumann, G.: Combined modelling of US fluvial, pluvial and coastal flood hazard under current and future climates, Water Resour. Res., e2020WR028673, https://doi.org/10.1029/2020WR028673, 2020. 
Beames, P., Lehner, B., and Anand, M.: Global Reservoir and Dam Database (GRanD), available at: http://globaldamwatch.org/grand/, last access: October 2021. 
Download
Short summary
Design flood estimation is a fundamental task in hydrology. We propose a machine- learning-based approach to estimate design floods anywhere on the global river network. This approach shows considerable improvement over the index-flood-based method, and the average bias in estimation is less than 18 % for 10-, 20-, 50- and 100-year design floods. This approach is a valid method to estimate design floods globally, improving our prediction of flood hazard, especially in ungauged areas.
Share