FY-3D Infrared Hyperspectral Cloud Detection Method Based on Logistic Regression

A FY-3D, logistic regression technology, applied in the field of logistic regression algorithm, HIRAS field of view cloud detection, can solve the problems of large image classification network, high computing cost, inconvenient to join the business assimilation system, etc., to achieve high accuracy and low cost , the effect of high practical application value

Active Publication Date: 2022-05-27
NAT UNIV OF DEFENSE TECH
View PDF4 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 Logistic Regression
  • FY-3D Infrared Hyperspectral Cloud Detection Method Based on Logistic Regression
  • FY-3D Infrared Hyperspectral Cloud Detection Method Based on Logistic Regression

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment

[0104] In order to better understand the technical content of the present invention, the forecast results of the case of Typhoon No. 10 in 2020 - "Fengshen" are given. The typhoon developed into a typhoon on September 3 and had a tendency to further intensify. It developed into a strong typhoon on September 4 and quickly developed into a super typhoon.

[0105] As shown in Figure 4(a) and Figure 4(b), it is the test result of the 2020 No. 10 typhoon "Poseidon" at 04:10 (UTC) on September 3. Figure 4(a) shows the observation results of MERSI L2 cloud detection product 04:10, in which 0 means certain cloud, 1 means possible cloud, 2 means possible clear sky, 3 means clear sky, and 4 means undetermined. Figure 4(b) shows the prediction result of the logistic regression model. The input is the full-channel radiation data of 04:10 HIRAS, and the output is the cloud label corresponding to the HIRAS pixel, where 0 means a certain cloud and 1 means a certain clear sky.

[0106] As sh...

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 FY‑3D infrared hyperspectral cloud detection method based on logistic regression, and relates to the technical field of satellite remote sensing. The present invention uses the traditional imager-based cloud detection method to match the cloud detection segment products of MERSI with the HIRAS pixel to obtain HIRAS data with cloud labels to form a training data set, and then use a logistic regression algorithm to train the data set, During the training process, the grid search method is used to select the appropriate hyperconstant of the logistic regression algorithm, and the model parameters with the best generalization performance are obtained. Finally, the trained logistic regression cloud detection model is used for the cloud of YF‑3D infrared hyperspectral data. Detection processing. The logic regression cloud detection model of the present invention can achieve a classification accuracy of 0.97, and the prediction speed is about 50 times that of the traditional method, showing good generalization performance.

Description

technical field [0001] The invention relates to the technical field of satellite remote sensing, in particular to a logistic regression algorithm in the field of machine learning, and a method for detecting clouds in the field of view of HIRAS 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 forecasting systems. The assimilation of infrared hyperspectral data is of great significance for effectively improving the level of numerical weather prediction. The water droplets and ice crystals in the cloud can effectively absorb infrared radiation, which makes the satellite infrared sounder unable to detect the infrared radiation of the atmosphere and the surface below the cloud layer. In addition, it is difficult for the current radiative transfer observation operators to accurately simulate the radiative effects of clouds. Therefore, ...

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 Patents(China)
IPC IPC(8): G06T17/00G06K9/62G06V10/764G06F17/11G06F17/15
CPCG06T17/00G06F17/11G06F17/15G06F18/24
Inventor 余意史华湘张卫民罗藤灵张琪王鹏飞吴建平王舒畅
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