Deviation influence factor analysis method for satellite radiation data

A technology of influencing factors and analysis methods, which is applied in the field of satellite radiation data analysis, can solve problems such as unsuitable high-dimensional data and high time complexity, and achieve the effect of improving the technical level, improving accuracy and stability, and improving speed and accuracy

Pending Publication Date: 2021-06-08
NORTH CHINA UNIVERSITY OF TECHNOLOGY
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The Wrapper method has a good classification accuracy, but the time

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
  • Deviation influence factor analysis method for satellite radiation data
  • Deviation influence factor analysis method for satellite radiation data
  • Deviation influence factor analysis method for satellite radiation data

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0031] The technical solutions of this patent will be described in further detail below in conjunction with specific embodiments.

[0032] A deviation affecting the satellite radiation data, for the problems of the traditional feature selection method, and the advantages of the xgboost method, calculate the importance of the XGBOOST algorithm and sort, and then screen the key influencing factors of satellite radiation data deviation.

[0033] First, the data set is selected

[0034] The ModeRate Resolution Imaging Spectroradiometer, MODIS is equipped in terra and Aqua satellite, is a very important sensor. Modis is currently a well-known performance stable and labeled-to-place observatory, and has a complex star calibration analysis system. With the continuous development of satellite remote sensing technology, remote sensing data has been more extensive in many fields. The application, there is a higher quality requirement for the quality of satellite data. MODIS has 36 bands, co...

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 a deviation influence factor analysis method for satellite radiation data, and belongs to the technical field of satellite radiation data analysis. The method comprises three steps of data set selection, data preprocessing and deviation influence factor analysis and calculation. When themethod faces a large amount of multi-dimensional data, the correlation between the deviation of the satellite radiation data and the input characteristics is analyzed, and influence factors of the deviation are preliminarily screened out; and then feature importance is calculated and sorted by adopting a machine learning method, and finally a key influence factor of the deviation is screened out. According to the method, the feature importance value is calculated by using a feature fusion mechanism, so that compared with similar algorithms, the method has the advantages that more time is saved, the speed and precision can be improved, and a foundation is laid for improving the technical level of in-orbit radiation calibration and inspection of the reflection band in China and further improving the in-orbit calibration precision and stability.

Description

technical field [0001] The invention belongs to the technical field of satellite radiation data analysis, in particular to a method for analyzing satellite radiation data deviation influencing factors. Background technique [0002] According to the relevant literature, there are many methods of feature selection, among which the common feature selection methods can be divided into filtering (Filter) and encapsulation (Wrapper). The Filter method has high selection efficiency, but is sensitive to noise data, and is generally used for preliminary screening of features. The Wrapper method has a good classification accuracy, but it has high time complexity and is not suitable for high-dimensional data. [0003] The screening of key influencing factors is very important for fast radiative transfer simulation, and it is also the key to the prediction effect of the model. The XGBoost algorithm is a boosting tree-based machine learning system proposed by Chen et al. based on a lar...

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): G06K9/62G06N20/20
CPCG06N20/20G06F18/214
Inventor 曹丹阳陈明珠宋歆睿马艳红
Owner NORTH CHINA UNIVERSITY OF TECHNOLOGY
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
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap