首页> 外国专利> METHOD AND APPARATUS FOR PREDICTING FINE PARTICULATE MATTER POLLUTION LEVEL, AND COMPUTER DEVICE

METHOD AND APPARATUS FOR PREDICTING FINE PARTICULATE MATTER POLLUTION LEVEL, AND COMPUTER DEVICE

机译:用于预测细颗粒物质污染水平和计算机设备的方法和装置

摘要

Disclosed are a method and apparatus for predicting a fine particulate matter pollution level, and a computer device, relating to the field of atmospheric monitoring. A targeted test can be performed on a fine particulate matter pollution level on the basis of real-time environmental data, and the problem of a fine particulate matter analysis result not being accurate enough can be solved. The method comprises: screening out target analysis data, wherein a correlation between same and fine particulate matter complies with a preset criterion (101); creating a fine particulate matter spatial distribution map according to a concentration value of the fine particulate matter within a preset historical time period (102); training a convolutional neural network model on the basis of the target analysis data and the fine particulate matter spatial distribution map (103); and using the trained convolutional neural network model to determine the pollution level of the fine particulate matter within a future preset time period (104). The method is applicable to the prediction of a fine particulate matter pollution level.
机译:公开了一种用于预测细颗粒物质污染水平的方法和装置,以及与大气监测领域有关的计算机设备。在实时环境数据的基础上,可以在细颗粒物质污染水平上进行靶向试验,并且可以解决不准确的细颗粒物分析结果的问题。该方法包括:筛选目标分析数据,其中相同和细颗粒物之间的相关性符合预设标准(101);根据预设历史时段(102)内的细颗粒物质的浓度值,产生细颗粒物质空间分布图;基于目标分析数据和细颗粒物质空间分布图(103)训练卷积神经网络模型;并使用训练型卷积神经网络模型来确定未来预设时间段内细颗粒物质的污染水平(104)。该方法适用于预测细颗粒物质污染水平。

著录项

相似文献

  • 专利
  • 外文文献
  • 中文文献
获取专利

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