| 利用神经网络从118.75 GHz附近通道亮温反演大气温度 |
| |
| 引用本文： | 姚志刚,陈洪滨.利用神经网络从118.75 GHz附近通道亮温反演大气温度[J].气象科学,2006,26(3):252-259. |
| |
| 作者姓名： | 姚志刚 陈洪滨 |
| |
| 作者单位： | 1. 解放军理工大学气象学院,南京,211101
2. 中科院大气物理所中层大气与遥感部/LAGEO,北京,100029 |
| |
| 基金项目： | 国家重点基础研究发展规划项目(编号:2001CB309402)资助 |
| |
| 摘 要： | 为了准确快速地从118.75 GHz附近六通道亮温计算大气温度,作者开展了利用人工神经网络技术反演大气温度的数值模拟研究。与线性统计反演算法比较,海面上大气温度反演的总体均方根误差减小17%,陆面上大气温度反演的总体均方根误差减小15%。两种下垫面条件下的温度反演结果表明,近陆面的温度反演结果优于近海面的温度反演结果。另外,对温度廓线垂直结构反演性能的分析结果表明,对于具有较厚逆温层结构的温度廓线,神经网络反演对廓线的复现能力优于线性统计反演。
|
| 关 键 词： | 神经网络 118.75GHz 微波 温度廓线 反演 |
| 收稿时间： | 2/5/2005 12:00:00 AM |
| 修稿时间： | 2005年2月5日 |
RETRIEVAL OF ATMOSPHERIC TEMPERATURE PROFILES WITH NEURAL NETWORK INVERSION OF MICROWAVE RADIOMETER DATA IN 6 CHANNELS NEAR 118.75 GHz |
| |
| Yao Zhigang and Chen Hongbin.RETRIEVAL OF ATMOSPHERIC TEMPERATURE PROFILES WITH NEURAL NETWORK INVERSION OF MICROWAVE RADIOMETER DATA IN 6 CHANNELS NEAR 118.75 GHz[J].Scientia Meteorologica Sinica,2006,26(3):252-259. |
| |
| Authors: | Yao Zhigang and Chen Hongbin |
| |
| Institution: | Institute of Meteorology,PLA University of Science and Technology,Nanjing 211101;LAGEO,Institute of Atmospheric Physics,CAS,Beijing 100029 |
| |
| Abstract: | In order to retrieve atmospheric temperature profiles accurately and rapidly from 6 channels near 118.75 GHz,a numerical simulation study has been conducted using artificial neural networks.Comparison with a statistical retrieval method shows that more accurate results over ocean and over land can be obtained at all levels.The overall root mean square errors in retrieved profiles of a testing dataset are 17% over ocean and 15% over land less than that by using the statistical retrieval.In the cases of thick temperature inversion,the neural networks provide much better reproductions of the profiles than the statistical inversion. |
| |
| Keywords: | Neural network 118 75 GHz Microwave Temperature profile Retrieval |
| 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 |
