点击次数：

论文类型：期刊论文

发表时间：2004-10-01

发表刊物：WATER RESOURCES MANAGEMENT

收录刊物：Scopus、SCIE、EI

卷号：18

期号：5

页面范围：483-495

ISSN号：0920-4741

关键字：attribute significance; forecast model; hydrology; medium and long-term forecast; rough set; single element; support strength

摘要：On the basis of rough set theory, this paper presents the single element medium- and long-term classification forecast model that uses historical data of a hydrologic series as forecast factors. The minimal rule set, i.e., forecast pattern set, is achieved according to the principle of maximal attribute significance and rules frequency. Maximal support strength is put forward and applied to predict by using the model. The model is applied to forecast annual runoff of Dahuofang reservoir. The result indicates that the forecast model based on rough set can describe the relationship between forecast factors and forecast object efficiently and accurately. This model, which is composed of simple solution rules, can be easily understood and applied.