欢迎访问中国科学院大学学报,今天是

中国科学院大学学报 ›› 2003, Vol. 20 ›› Issue (3): 328-333.DOI: 10.7523/j.issn.2095-6134.2003.3.011

• 论文 • 上一篇    下一篇

基于气象数据与AVHRR热红外数据的人工神经网络分类方法

哈斯巴干1, 马建文1, 周自江2, 李启青1   

  1. 1. 中国科学院遥感应用研究所, 北京 100101
    2. 中国国家气象中心气象资料中心, 北京 100081
  • 收稿日期:2002-09-06 发布日期:2003-05-10
  • 基金资助:

    国家科学院数学地球基础理论研究项目(KZCSX2312);中国科学院亚洲沙尘暴- ADEC项目(KZCX20305)资助

Artificial Neural Network Method Used for Weather and AVHRR Thermal Data Classification

HASI BaGan1, MA JianWen1, ZHOU ZiJiang2, LI QiQing1   

  • Received:2002-09-06 Published:2003-05-10

摘要:

利用 52个气象站观测的温度数据与同位置的AVHRR 1b CH3、CH4、CH5三个通道的热红外遥感数据进行网络训练,再用训练出来的规则,指导整个研究区范围内图像数据进行分类,取得了较好的效果。

null

关键词: 人工神经网络, 气象数据, AVHRR卫星热红外数据

Abstract:

weather temperature data were used from 52 observation stations where they were also the same positionsfor collecting AVHRR 1b data CH3 、CH4、CH5 thermal data.Both groups of data were applied as fundamentalimport data in for artificial neural network calculation.Finally resultant rule was applied for classifying pixels in the whole area.The result was more reliable than that of split window not only because uncertainty caused by variations of topography but also it was very difficult to validate in field.

Key words: artificial neural network, weather observation data , AVHRR 1b data

中图分类号: