Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Atmospheric aerosol data prediction method

An atmospheric aerosol and data prediction technology, applied in the field of remote sensing, can solve problems such as the inability to achieve high accuracy and high coverage, temporal and spatial resolution and method errors, solve the problem of temporal and spatial non-stationarity, improve accuracy, and improve reliability. dimensional effect

Pending Publication Date: 2020-08-07
CHINA UNIV OF MINING & TECH (BEIJING)
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The disadvantage of this method lies in the problem of temporal and spatial resolution and method error, so that the result of aerosol data fusion cannot achieve high accuracy and high coverage

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
  • Atmospheric aerosol data prediction method
  • Atmospheric aerosol data prediction method
  • Atmospheric aerosol data prediction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0051] The purpose of the present invention is achieved through the following technical solutions: a method of predicting atmospheric aerosol data based on nonlinear principal component analysis and time-space geographical weighted regression research method, comprising the following steps:

[0052] 1. Preprocess the atmospheric aerosol image data, and obtain the aerosol data values ​​of the image data in batches;

[0053] Obtain atmospheric aerosol image data and name, analyze the image data file name and return date, obtain the data value of an image, locate and divide the grid of 3km*3km, extract the coordinates of the grid center point and aerosol data value, and atmospheric aerosol data Write into the database, calculate the average value of the aerosol data of the same coordinates of the Terra and Aqua satellites, and randomly select 1594 uniformly distributed aerosol data points.

[0054] 2. Preprocess a total of 15 indicators of air quality data, meteorological data an...

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 atmospheric aerosol data prediction method. The method is based on nonlinear principal component analysis and space-time geographically weighted regression, and comprises the following steps: for a target area, employing m principal components obtained by nonlinear principal component analysis as explanatory variables of space-time geographically weighted regression, andoperating a space-time geographically weighted regression model to obtain a predicted value of aerosol data. According to the method, the principal components are expressed as nonlinear combinationsof original data, nonlinear characteristics of the data can be well reserved, the dimension reduction effect is improved, more original index information is reflected with fewer principal components,multiple collinearity is effectively eliminated, and information loss of the original data is reduced; the space-time geographically weighted regression considers the space-time characteristics of thedata into the regression model, so the problem of space-time non-stationarity of the regression model is effectively solved, and the accuracy of estimating the AOD concentration by the model is improved.

Description

technical field [0001] The invention relates to the technical field of remote sensing, in particular to an atmospheric aerosol data prediction method based on nonlinear principal component analysis and time-space geographical weighted regression. Background technique [0002] A number of remote sensing satellites have been launched around the world to monitor changes in the distribution of atmospheric aerosols, and a large number of satellite image data of atmospheric aerosols around the world have been obtained so far. Its image data is mainly used in scientific fields such as climate change, air quality, environmental pollution, and human health, and provides technical support for the country to solve some major decision-making issues. However, satellite observations of atmospheric aerosols show blank values ​​in most areas due to the interference of clouds and other influencing factors. This not only reduces the quality of image data, but also hinders the development of ...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06Q10/04G06F16/29
CPCG06Q10/04G06F16/29
Inventor 陈伟李广超
Owner CHINA UNIV OF MINING & TECH (BEIJING)
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap 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