首页 | 本学科首页   官方微博 | 高级检索  
     检索      

基于数值预报产品的地面气温BP-MOS预报方法
引用本文:吴君,裴洪芹,石莹,张京英,王庆华.基于数值预报产品的地面气温BP-MOS预报方法[J].气象科学,2007,27(4):430-435.
作者姓名:吴君  裴洪芹  石莹  张京英  王庆华
作者单位:山东省临沂市气象局,临沂,276004
摘    要:在山东省临沂市气象局开发的"中尺度数值预报业务系统"的基础上,利用高分辨率的数值预报产品和地面气温观测资料,建立了地面气温的BP神经网络方法预报模型。检验结果表明BP神经网络模型的气温预报准确率高于逐步回归模型和MM5模式输出的气温预报准确率,可应用于实际预报业务中来制作气温的精细化预报。

关 键 词:气温预报  数值预报产品  MM5模式  BP神经网络  逐步回归
收稿时间:2005-01-26
修稿时间:2006-01-14

THE FORECASTING OF SURFACE AIR TEMPERATURE USING BP-MOS METHOD BASED ON THE NUMERICAL FORECASTING RESULTS
Wu Jun,Pei Hongqin,Shi Ying,Zhang Jingying and Wang Qinghua.THE FORECASTING OF SURFACE AIR TEMPERATURE USING BP-MOS METHOD BASED ON THE NUMERICAL FORECASTING RESULTS[J].Scientia Meteorologica Sinica,2007,27(4):430-435.
Authors:Wu Jun  Pei Hongqin  Shi Ying  Zhang Jingying and Wang Qinghua
Institution:Linyi Meteorological Observatory, Linyi of Shandong 276004
Abstract:In this paper,based on the "Mesoscale Numerical Forecasting System" developed by the Linyi Meteorological Bureau,the BP neural network model was applied to forecast the surface air temperature using the high resolution numerical forecasting data and observation as input.The result shows that accuracy rate of the BP model is higher than the stepwise regression model and MM5 model in surface air temperature forecasting,and the BP model can be applied in realtime surface air temperature forecast
Keywords:Temperature forecast Numerical forecasting data MM5 model BP neural network Stepwise regression
本文献已被 CNKI 维普 万方数据 等数据库收录!
点击此处可从《气象科学》浏览原始摘要信息
点击此处可从《气象科学》下载免费的PDF全文
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