Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Aerosol extinction coefficient inversion method based on deep belief network

A technology of deep belief network and extinction coefficient, applied in neural learning methods, biological neural network models, reradiation of electromagnetic waves, etc., can solve problems such as large inversion errors

Active Publication Date: 2019-08-09
NANJING UNIV OF INFORMATION SCI & TECH
View PDF7 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The traditional meter-scattering lidar retrieval methods, such as the Fernald method and the Klett method, need to set the boundary value of the aerosol extinction coefficient or the lidar ratio. large inversion error

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Aerosol extinction coefficient inversion method based on deep belief network
  • Aerosol extinction coefficient inversion method based on deep belief network
  • Aerosol extinction coefficient inversion method based on deep belief network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0061] The technical solutions of the present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0062] An aerosol extinction coefficient inversion method based on a deep belief network according to the present invention, combined with the measurement results of the meter scattering lidar and the inversion results of the Raman scattering lidar, proposes an aerosol extinction method based on the deep belief network Coefficient inversion method. The structure principle of the inversion method is as follows: figure 1 shown.

[0063] An aerosol extinction coefficient inversion method based on a deep belief network according to the present invention comprises the following steps:

[0064] Step 1: Obtain the echo power signal of the meter scattering lidar and the aerosol extinction coefficient obtained by the inversion of the Raman lidar to form a data sample set; divide the data sample set into a training sample set and a te...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses an aerosol extinction coefficient inversion method based on a deep belief network. The method comprises the following steps: S1, echo power signals of a Mie scattering lidar and an aerosol extinction coefficient obtained by inversion of a Raman lidar are obtained, and training and test sample sets are formed; S2, a normalized training sample set is obtained; S3, a deep belief network is built according to the normalized training sample set, network parameters are adjusted, and the network is trained; S4, the echo power signals of the test sample set are inputted to an optimized network to obtain network output, a network output result is compared with the aerosol extinction coefficient of the test sample set to judge whether to meet an expected condition; and S5, ifthe comparison result meets the expected condition, network optimization is ended, and if not, the third step is returned to continue to train the deep belief network until the comparison result meets the expected condition. The Mie scattering lidar detection precision is improved, and quick and accurate inversion of the aerosol extinction coefficient is realized.

Description

technical field [0001] The invention belongs to the technical field of aerosol measurement, in particular to an aerosol extinction coefficient inversion method based on a deep belief network. Background technique [0002] Atmospheric aerosols only occupy a small proportion of atmospheric composition, but they have an important impact on climate change, such as through the scattering and absorption of solar radiation and long-wave radiation, affecting atmospheric radiation, atmospheric chemistry and precipitation processes. Compared with satellite and other detection methods, lidar has been widely used as an active remote sensing detection tool for aerosol measurement due to its advantages of high temporal and spatial resolution and high measurement accuracy. The Mi-scattering LiDAR came out as early as 1961. On this basis, multi-wavelength multi-channel LiDAR and high-spectral resolution LiDAR have been developed successively. However, the meter-scattering lidar has a simpl...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G01N21/49G01N21/65G01S17/88G06N3/04G06N3/08
CPCG01N21/49G01N21/65G01S17/88G06N3/084G06N3/045
Inventor 常建华李红旭张露瑶毛仁祥张树益豆晓雷
Owner NANJING UNIV OF INFORMATION SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com