首页 | 本学科首页   官方微博 | 高级检索  
     

中长期水文预报方法应用研究
引用本文:王增学,周志华,邹晓天,杨笑冰.中长期水文预报方法应用研究[J].东北水利水电,2012,30(4):43-44,52,72.
作者姓名:王增学  周志华  邹晓天  杨笑冰
作者单位:1. 吉林省水文水资源局吉林分局,吉林吉林,132013
2. 吉林省蛟河市水资源管理办公室,吉林蛟河,132500
摘    要:文章采用传统预报方法——多元线性回归和新方法——BP网络和投影寻踪技术,分别建立预报模型.利用长江宜昌站8-12月径流资料来研究预报模型的可行性和实用性.研究表明,3个预报模型的精度均在20%以内,尤其是BP模型预报精度均在10%以内,效果较好,具有一定的实用价值.

关 键 词:径流预报  多元线性回归  BP网络  投影寻踪

Application study on mid long term hydrological forecasting method
WANG Zeng-xue,ZHOU Zhi-hua,ZOU Xiao-tian,YANG Xiao-bing.Application study on mid long term hydrological forecasting method[J].Water Resources & Hydropower of Northeast China,2012,30(4):43-44,52,72.
Authors:WANG Zeng-xue  ZHOU Zhi-hua  ZOU Xiao-tian  YANG Xiao-bing
Affiliation:WANG Zeng-xue,ZHOU Zhi-hua,ZOU Xiao-tian,YANG Xiao-bing
Abstract:The forecasting models are established respectively by adopt the traditional forecasting method,the multiple linear regressions,and the new methods,BP neural network and projection pursuit.The feasibility and practicality of forecasting models are studied by using the runoff data from August to December of Yichang station in Yangtze River.The study results show that the accuracy of the three forecasting models is within 20%,especially within 10% for the accuracy of the BP model,which has the better effect and certain practical value.
Keywords:runoff forecasting  multiple linear regressions  BP network  projection pursuit
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号