Open AccessResearch and application of an intelligent networking model for flood forecasting in the arid mountainous basins
Author(s) -
Yuan Ximin,
Zhang Xingyuan,
Tian Fuchang
Publication year - 2020
Publication title -
journal of flood risk management
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.049
H-Index - 36
ISSN - 1753-318X
DOI - 10.1111/jfr3.12638
Subject(s) - flood forecasting , flood myth , surface runoff , environmental science , arid , hec hms , flow routing , drainage basin , hydrology (agriculture) , 100 year flood , routing (electronic design automation) , storm , structural basin , hydrological modelling , meteorology , computer science , climatology , geography , geology , cartography , biology , ecology , paleontology , computer network , geotechnical engineering , archaeology
Storm floods occur frequently and have complex characteristics in arid mountainous areas, which for a long time has been a weak link in flood forecasting. The application of an artificial intelligent model and physically‐based hydrological model has some limitations on flood forecasting in arid mountainous areas with scarce data. In this article, the ANN model and Muskingum‐Cunge method are combined to propose an intelligent networking model for flood forecasting (FFIN model) in arid mountainous areas with scarce data, which BR‐ANN model is used to forecast the flood in the catchment sub‐basin with runoff data, while the General Regression Neural Network model is used to carry out flood parallel forecast in the catchment sub‐basin without runoff data. The Muskingum‐Cunge method is used to connect the sub‐basins and form a confluence network, so as to simulate the flood routing process in river. The verification and comparison results in study area show that the FFIN model has a superior overall forecasting ability. For the forecasting period, the evaluation index Kling‐Gupta efficiency is 0.88, Nash efficiency coefficient is 0.982 and forecasting deviation of flood peak flow is 7.15%. The FFIN model can be effectively applied to flood forecasting in arid mountainous areas with scarce runoff data.