本文已被：浏览 939次 下载 1041次
中文摘要: 采用T213数值天气预报产品资料和北京市观象台(54511)实时地面气象观测资料，运用神经网络方法，建立了北京市观象台(东郊)未来1～3天( 0～72h)夜间、白天、全天平均气温及夜间最低、白天最高气温共5项气温的预报模式，经检验，预报的均方根误差<2℃，可满足供热调度节能工作的迫切需要。
中文关键词: 数值天气预报产品，气温预报，神经网络模型
Abstract:Based on the abundant numerical predicted production from T213 model and the real time observation from Beijing Meteorological Observatory, a neural network model is developed to forecast daytime, nighttime, daily mean, minimum and maximum temperatures for 1—3 day(0—72hours) in advance. The forecast tests indicate that the square root error is less than 2℃ that can be satisfied for economical heating in Beijing.
文章编号： 中图分类号： 文献标志码：
基金项目:
| Author Name | Affiliation |
引用文本：
胡江林,张德山,王志斌,陈正洪,2005.北京地区未来1～3天昼夜气温预报模型[J].气象,31(1):67-68.
,2005.The Daytime and Nighttime Temperature Forecast Model for 1—3d in Beijing[J].Meteor Mon,31(1):67-68.
胡江林,张德山,王志斌,陈正洪,2005.北京地区未来1～3天昼夜气温预报模型[J].气象,31(1):67-68.
,2005.The Daytime and Nighttime Temperature Forecast Model for 1—3d in Beijing[J].Meteor Mon,31(1):67-68.