Hits:

Indexed by:期刊论文

Date of Publication:2015-07-01

Journal:WATER SCIENCE AND TECHNOLOGY

Included Journals:SCIE、EI、PubMed、Scopus

Volume:71

Issue:10

Page Number:1507-1515

ISSN No.:0273-1223

Key Words:conceptual hydrological model; flood classification; K-means cluster; real-time flood forecasting; rough set

Abstract:This research presents a new classified real-time flood forecasting framework. In this framework, historical floods are classified by a K-means cluster according to the spatial and temporal distribution of precipitation, the time variance of precipitation intensity and other hydrological factors. Based on the classified results, a rough set is used to extract the identification rules for real-time flood forecasting. Then, the parameters of different categories within the conceptual hydrological model are calibrated using a genetic algorithm. In real-time forecasting, the corresponding category of parameters is selected for flood forecasting according to the obtained flood information. This research tests the new classified framework on Guanyinge Reservoir and compares the framework with the traditional flood forecasting method. It finds that the performance of the new classified framework is significantly better in terms of accuracy. Furthermore, the framework can be considered in a catchment with fewer historical floods.