干旱区生态环境知识资源中心(Arid): Design flood estimation for global river networks based on machine learning models

Arid

DOI	10.5194/hess-25-5981-2021
	Design flood estimation for global river networks based on machine learning models
	Zhao, Gang; Bates, Paul; Neal, Jeffrey; Pang, Bo
通讯作者	Zhao, G (corresponding author), Univ Bristol, Sch Geog Sci, Bristol, Avon, England.
来源期刊	HYDROLOGY AND EARTH SYSTEM SCIENCES
ISSN	1027-5606
EISSN	1607-7938
出版年	2021
卷号	25 期号:11 页码:5981-5999
英文摘要	Design flood estimation is a fundamental task in hydrology. In this research, we propose a machine-learning-based approach to estimate design floods globally. This approach involves three stages: (i) estimating at-site flood frequency curves for global gauging stations using the Anderson-Darling test and a Bayesian Markov chain Monte Carlo (MCMC) method; (ii) clustering these stations into subgroups using a K-means model based on 12 globally available catchment descriptors; and (iii) developing a regression model in each subgroup for regional design flood estimation using the same descriptors. A total of 11 793 stations globally were selected for model development, and three widely used regression models were compared for design flood estimation. The results showed that (1) the proposed approach achieved the highest accuracy for design flood estimation when using all 12 descriptors for clustering; and the performance of the regression was improved by considering more descriptors during training and validation; (2) a support vector machine regression provided the highest prediction performance amongst all regression models tested, with a root mean square normalised error of 0.708 for 100-year return period flood estimation; (3) 100-year design floods in tropical, arid, temperate, cold and polar climate zones could be reliably estimated (i.e. <+/- 25 % error), with relative mean bias (RBIAS) values of -0.199, -0.233, -0.169, 0.179 and -0.091 respectively; (4) the machine-learning-based approach developed in this paper showed considerable improvement over the index-flood-based method introduced by Smith et al. (2015, https://doi.org/10.1002/2014WR015814) for design flood estimation at global scales; and (5) the average RBIAS in estimation is less than 18 % for 10-, 20-, 50- and 100-year design floods. We conclude that the proposed approach is a valid method to estimate design floods anywhere on the global river network, improving our prediction of the flood hazard, especially in ungauged areas.
类型	Article
语种	英语
开放获取类型	Green Submitted, gold
收录类别	SCI-E
WOS记录号	WOS:000721621900001
WOS关键词	SUPPORT VECTOR REGRESSION ; FREQUENCY-ANALYSIS ; UNCERTAINTY ; WATER ; DEPENDENCE ; IMPACTS ; REGIONS ; FUTURE
WOS类目	Geosciences, Multidisciplinary ; Water Resources
WOS研究方向	Geology ; Water Resources
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/373875
作者单位	[Zhao, Gang; Bates, Paul; Neal, Jeffrey] Univ Bristol, Sch Geog Sci, Bristol, Avon, England; [Bates, Paul; Neal, Jeffrey] Fathom, Engine Shed, Stn Approach, Bristol, Avon, England; [Pang, Bo] Beijing Normal Univ, Coll Water Sci, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Zhao, Gang,Bates, Paul,Neal, Jeffrey,et al. Design flood estimation for global river networks based on machine learning models[J],2021,25(11):5981-5999.
APA	Zhao, Gang,Bates, Paul,Neal, Jeffrey,&Pang, Bo.(2021).Design flood estimation for global river networks based on machine learning models.HYDROLOGY AND EARTH SYSTEM SCIENCES,25(11),5981-5999.
MLA	Zhao, Gang,et al."Design flood estimation for global river networks based on machine learning models".HYDROLOGY AND EARTH SYSTEM SCIENCES 25.11(2021):5981-5999.