秦淮河流域东山站洪水位预报模型研究  

Study on flood level forecasting model of Dongshan Station in Qinhuai River Basin

作　　者：杜开连 王建群[2] 葛忆 朱力 张佳丽 DU Kailian;WANG Jianqun;GE Yi;ZHU Li;ZHANG Jiali(Jurong Water Conservancy Bureau of Jiangsu Province,Jurong 212400,China;College of Hydrology and Water Resources,Hohai University,Nanjing 210098,China)

机构地区：[1]句容市水利局,江苏句容212400 [2]河海大学水文水资源学院,江苏南京210098

出　　处：《水利信息化》2020年第3期25-28,共4页Water Resources Informatization

基　　金：国家重点研发计划课题(2016YFC0400909)。

摘　　要：为了提高秦淮河流域洪水预报的水平,对东山站洪水位过程预报模型进行深入研究。采用线性动态系统模型与BP人工神经网络模型建立东山站洪水位逐时段预报模型,采用2010-2015年及2016-2017年汛期秦淮河流域实测雨量和东山站水位资料对模型进行率定和验证。结果表明:东山站洪水位逐时段预报的BP人工神经网络模型相对于线性动态系统模型具有较高的精度;相对于一维河网水动力模型,简单实用。In order to improve the ability of flood forecast in Qinhuai River Basin,the flood level forecasting models of Dongshan Station in Qinhuai River Basin are studied.Based on the linear dynamic system model and BP neural network model,the flood level time interval forecasting model of Dongshan Station is established.The models are calibrated and verified by the measured rainfall data and the measured water level data of Dongshan Station during the flood season of 2010—2015 and 2016—2017.The results show that the BP neural network model of the flood level time interval forecasting model of Dongshan Station has higher precision than linear dynamic system model,and it is simple and practical compared with one-dimensional river network hydrodynamic model.

关 键 词：洪水预报 BP人工神经网络 线性动态系统 一维水动力模型 

分 类 号：P338[天文地球—水文科学]