• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>Tenth Joint International Symposium on Atmospheric and Ocean Optics/Atmospheric Physics Part.II Laser Sensing and Atmospheric Physics; Jun 24-28, 2003; Tomsk, Russia >APPLICATION OF NEURAL NETWORKS FOR RETRIEVING OF ATMOSPHERIC GASES CONCENTRATION PROFILE FOR LIDAR SOUNDING DATA
【24h】

APPLICATION OF NEURAL NETWORKS FOR RETRIEVING OF ATMOSPHERIC GASES CONCENTRATION PROFILE FOR LIDAR SOUNDING DATA

机译：神经网络在激光雷达测深数据中大气气浓度分布图反演中的应用

获取原文
获取原文并翻译 | 示例
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

In the report a method of ozone profile concentration retrieving from the lidar data sounding on the basis of neural networks (NN) is description. Application of neural networks in inverse tasks is connected with solving some important stages. In the first, it is necessary to carry out training of NN on the basis of the big data set (measurement - decision). In the second, basing on the results of the first stage to generate optimum NN (number of layers, transfer functions). Results of simulation inverse task of ozone profile concentration retrieving from the lidar data sounding have shown reliability of work in NN, speed of the inverse tasks solving and accuracy of retrieving ozone profile comparable to traditional methods.
机译：在该报告中，描述了一种基于神经网络（NN）从激光雷达数据探测中检索臭氧剖面浓度的方法。神经网络在逆任务中的应用与解决一些重要阶段有关。首先，有必要在大数据集（测量-决策）的基础上进行神经网络的训练。在第二步中，基于第一步的结果来生成最佳NN（层数，传递函数）。从激光雷达数据探测中反演臭氧剖面浓度的模拟反任务结果表明，与传统方法相比，神经网络的工作可靠性，反任务求解速度和反演臭氧剖面的准确性都很高。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号