FY-3D infrared hyperspectral cloud detection method based on linear discriminant analysis

A linear discriminant analysis and FY-3D technology, applied in the field of machine learning and satellite remote sensing, can solve the problems of inconvenient to join the business assimilation system, large image classification network, high computing cost, etc., to achieve high practical application value, high accuracy, low cost effect

Active Publication Date: 2021-06-15
NAT UNIV OF DEFENSE TECH
View PDF11 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this method uses high-resolution cloud images as feature inputs, which also requires high computational costs
In addition, the typical image classification network is relatively large, which is not convenient to add to the business assimilation system of the numerical model.

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
  • FY-3D infrared hyperspectral cloud detection method based on linear discriminant analysis
  • FY-3D infrared hyperspectral cloud detection method based on linear discriminant analysis
  • FY-3D infrared hyperspectral cloud detection method based on linear discriminant analysis

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment

[0085]In order to better understand the technical content of the present invention, the forecast results of the No. 10 typhoon in 2020 - "Fengshen" are specially cited. The typhoon developed into a typhoon on September 3 and tended to intensify further. It developed into a strong typhoon on September 4 and quickly developed into a super typhoon.

[0086] As shown in Figure 4(a) and Figure 4(b), it is the test result of the No. 10 typhoon "Poseidon" in 2020 at 16:40 (UT) on September 3. Figure 4(a) shows the observation results of MERSI L2 level cloud detection products at 16:40, where 0 indicates definite cloud, 1 indicates possible cloud, 2 indicates possible clear sky, 3 indicates definite clear sky, and 4 indicates undetermined. Figure 4(b) shows the forecast results of the linear discriminant analysis model. The input is the full-channel radiation data of 16:40 HIRAS, and the output is the cloud label corresponding to the HIRAS pixel, where 0 indicates a certain cloud and ...

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 FY-3D infrared hyperspectral cloud detection method based on linear discriminant analysis, and relates to the technical field of satellite remote sensing. According to the method, a traditional cloud detection method based on an imager is utilized, a cloud detection section product of MERSI is matched with an HIRAS pixel, HIRAS data with a cloud tag is obtained, a training data set is formed, then the data set is trained by using a linear discriminant analysis algorithm, in the training process, a grid search method is adopted to select a proper linear discriminant analysis algorithm supernormal number, and finally, the linear discriminant analysis cloud detection model obtained through training is used for cloud detection processing of infrared hyperspectral data of YF-3D. The linear discriminant analysis cloud detection model can achieve the classification accuracy of 0.95, the prediction speed is about 58 times that of a traditional method, and good generalization performance is embodied.

Description

technical field [0001] The invention relates to the field of satellite remote sensing technology, in particular to a linear discriminant analysis algorithm in the field of machine learning, combined with a method for detecting clouds in the HIRAS field of view by using infrared hyperspectral data of the FY-3D satellite HIRAS instrument. Background technique [0002] Infrared hyperspectral data are important observational data for modern numerical weather prediction systems. The assimilation of infrared hyperspectral data is of great significance for effectively improving the level of numerical weather prediction. Water droplets and ice crystals in clouds can effectively absorb infrared radiation, making satellite infrared detectors unable to detect atmospheric and surface infrared radiation below the clouds. In addition, it is difficult for current radiative transfer observation operators to accurately simulate the radiative effect of clouds. Therefore, cloud pollution is ...

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): G06K9/62G06N20/00G01N21/3504G01W1/10
CPCG06N20/00G01N21/3504G01W1/10G06F18/22G06F18/241G06F18/214
Inventor 余意罗藤灵张卫民史华湘张琪刘运韬曹小群赵延来
Owner NAT UNIV OF DEFENSE 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
Try Eureka
PatSnap group products