Computer Engineering and Applications ›› 2010, Vol. 46 ›› Issue (6): 231-234.DOI: 10.3778/j.issn.1002-8331.2010.06.067

• 工程与应用 • Previous Articles     Next Articles

Application of dynamic Bayesian networks in hydrologic forecast

LI Wei-qian1,2,XIE Jian-cang1,ZHANG Yong-jin3,XUE Bao-ju1,ZHANG Li4   

  1. 1.Institute of Water Resource and Hydro-electric Engineering,Xi’an University of Technology,Xi’an 710048,China
    2.Institute of Mathematics and Information,Gansu Lianhe University,Lanzhou 730000,China
    3.Institute of Business Administration,Xi’an University of Technology,Xi’an 710048,China
    4.Xi’an University of Finance and Economics,Xi’an 710061,China

  • Received:2008-08-29 Revised:2008-11-13 Online:2010-02-21 Published:2010-02-21
  • Contact: LI Wei-qian

动态贝叶斯网络在水文预报中的应用

李维乾1,2,解建仓1,张永进3,薛保菊1,张 丽4   

  1. 1.西安理工大学 水利水电学院,西安 710048
    2.甘肃联合大学 数学与信息学院,兰州 730000
    3.西安理工大学 工商管理学院,西安 710048
    4.西安财经学院,西安710061
  • 通讯作者: 李维乾

Abstract: Bayesian network is one of the most efficient models in the uncertain knowledge and reasoning field.A rainfall-runoff prediction model based on dynamic Bayesian network is put forward in this paper.The network model is based on knowledge of the field experts and the causes of rainfall-runoff,they can produce the probability of the flow rate by calculating the conditional probability among variables on the basis of historical rainfall and runoff data.Finally through the simulation of historical data about Wei He river basin from Xianyang gauge station to Lintong gauge station,the model and the results are analyzed.

Key words: Bayesian network, dynamic Bayesian network, hydrologic forecast, data mining, higher-order Markov

摘要: 贝叶斯网络是目前人工智能中不确定知识与推理中最有效的理论模型之一。提出一种基于动态贝叶斯网络模型理论的水文预报方法。在综合考虑降雨径流成因的基础上,利用领域专家知识构建网络模型,在已有降雨、流量数据的基础上通过计算变量间的条件概率来计算流量发生的可能性。最后,通过渭河流域咸阳至临潼段历时数据进行仿真实验,对仿真结果和该模型进行了分析。

关键词: 贝叶斯网络, 动态贝叶斯网络, 水文预报, 数据挖掘, 高阶马尔科夫链

CLC Number: