Convective cloud machine learning identification method based on satellite cloud picture

A technology of machine learning and identification method, applied in the field of satellite cloud image analysis, which can solve problems such as selection difficulties and restricting real-time monitoring of streaming clouds.

Inactive Publication Date: 2021-12-10
江苏铨铨信息科技有限公司
View PDF9 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the process of real-time processing of satellite cloud images, it is very difficult to selec

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
  • Convective cloud machine learning identification method based on satellite cloud picture
  • Convective cloud machine learning identification method based on satellite cloud picture
  • Convective cloud machine learning identification method based on satellite cloud picture

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] Below in conjunction with accompanying drawing and specific embodiment the present invention is described in further detail:

[0027] Work flow chart of the present invention is as figure 1 As shown, specifically:

[0028] The first step is to obtain the cloud top brightness temperature TBB historical period and current monitoring data of p channels of meteorological satellites, taking Himawari-8 satellite as an example, including infrared brightness temperature observations of 10 channels (channels 7~16); obtain the same historical period The reanalysis data of surface precipitation within the system, taking ERA5 as an example, includes total precipitation TP and convective precipitation CP;

[0029] In the second step, through bicubic spline interpolation, the historical period and current TBB data are interpolated to the grid of the surface precipitation field in the historical period, so that the horizontal grid points where TBB, TP and CP are located are consisten...

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

A convective cloud machine learning identification method based on a satellite cloud picture comprises the following steps: 1, acquiring a cloud top brightness temperature historical time period and current monitoring data, and acquiring ground rainfall in the same historical time period; 2, interpolating the historical time period and the current TBB data to the grids of the ground precipitation field in the historical time period through bicubic spline interpolation; 3, generating a historical period brightness temperature index library and a current brightness temperature index library; 4, selecting a rainfall threshold value; 5, calculating mutual information of Y and X; 6, obtaining a nonlinear relation between Y and corresponding parameters through a support vector machine technology; 7, calculating mutual information of Z and X; 8, obtaining a nonlinear relation between Z and corresponding parameters through a support vector machine technology; 9, estimating the current probability of rainfall; 10, estimating the probability of existence or absence of convective rainfall at present; and 11, determining whether convective cloud exists. According to the method, the machine learning technology is utilized, the characteristics of the convection cloud on different channel satellite cloud pictures are quantitatively recognized, and the real-time recognition technology of the convection cloud is developed.

Description

technical field [0001] The invention relates to the technical field of satellite cloud image analysis, in particular to a method for machine learning identification of convective clouds based on satellite cloud images. Background technique [0002] Severe convective cloud clusters are often accompanied by catastrophic events such as strong winds, heavy rains, and huge waves, which can not only cause significant casualties, but also bring huge economic losses. Overland convective cloud monitoring can be achieved through ground automatic weather stations, ground-based radars, satellites, etc., while in the vast ocean, satellites are the primary means of convective cloud monitoring. Early studies mainly relied on the analysis of cloud shape, cloud coverage area and other visual appearance features on satellite cloud images to identify convective clouds. With the continuous upgrading and development of meteorological satellites, later studies mainly quantified the identificatio...

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): G06N20/00G01W1/00
CPCG06N20/00G01W1/00Y02A90/10
Inventor 郭洪涛宋金杰
Owner 江苏铨铨信息科技有限公司
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