CAJ | 학술논문

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,通过渭河流域成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.
패협사망락시목전인공지능중불학정지식여추리중최유효적이론모형지일.제출일충기우동태패협사망락모형이론적수문예보방법.재종합고필강우경류성인적기출상,이용영역전가지식구건망락모형,재이유강우、류량수거적기출상통과계산변량간적조건개솔래계산류량발생적가능성.최후,통과위하류역성양지림동단력시수거진행방진실험,대방진결과화해모형진행료분석.
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.