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

Deep learning-based stationary orbit meteorological satellite radar reflectivity factor inversion method

A radar reflection, geostationary orbit technology, applied in neural learning methods, reflection/re-radiation of radio waves, computer systems based on knowledge-based patterns, etc. and other problems, to achieve the effect of shortening the time interval, strong nonlinear reconstruction, and high inversion accuracy

Pending Publication Date: 2021-10-22
NAT SATELLITE METEOROLOGICAL CENT
View PDF0 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The existing technology uses geostationary meteorological satellite early warning products (or integrates numerical forecast model data) to detect strong convective weather, but the technology still stays at identification and segmentation, and lacks the capture of intensity information of radar echoes

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
  • Deep learning-based stationary orbit meteorological satellite radar reflectivity factor inversion method
  • Deep learning-based stationary orbit meteorological satellite radar reflectivity factor inversion method
  • Deep learning-based stationary orbit meteorological satellite radar reflectivity factor inversion method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0046] Such as figure 1 As shown, Embodiment 1 of the present invention proposes a method for inversion of geostationary satellite radar reflectivity factors based on deep learning. The invention is mainly composed of two modules, namely the preprocessing and training module on the left side of the block diagram and the verification module of the inventive technology shown on the right side of the block diagram.

[0047] 1. Data preparation

[0048] Firstly, the random forest method is used innovatively to select the channel with strong correlation with the radar reflectivity factor as the input of the model for the new generation geostationary orbit meteorological satellite imager data. On the one hand, it reduces the calculation and storage pressure, and on the other hand, it also clarifies the physical relationship between the radar reflectivity factor and the input. The radar reflectivity factor is closely related to the microphysical properties of clouds and the distrib...

Embodiment 2

[0068] Embodiment 2 of the present invention proposes a radar reflectivity factor inversion system for geostationary meteorological satellites based on deep learning. The system includes: a radar reflectivity factor inversion model, a sensitivity channel selection module, and an inversion result output module; the specific processing method is the same as in embodiment 1, wherein,

[0069] The sensitive channel selection module is used to select the sensitive channel of the geostationary meteorological satellite imager according to the random forest method; the sensitive channel is a channel with a strong correlation with the radar reflectivity factor;

[0070] The inversion result output module is used to receive the sensitive channel data transmitted by the imager of the geostationary meteorological satellite, input the pre-established and trained radar reflectivity factor inversion model, and obtain the inversion result.

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 relates to the technical field of severe convection weather early warning, in particular to a deep learning-based stationary orbit meteorological satellite radar reflectivity factor inversion method. The method comprises the following steps: selecting a sensitive channel of a geostationary orbit meteorological satellite imager according to a random forest method, wherein the sensitive channel is a channel with strong correlation with a radar reflectivity factor; and receiving sensitive channel data downloaded by the geostationary orbit meteorological satellite imager, and inputting the sensitive channel data into the pre-established and trained radar reflectivity factor inversion model to obtain an inversion result. According to the method, basic detection and diagnosis data are provided for disastrous weather in a radar uncovered area, and the beneficial effects of a severe convection system incompletely covered by radar data and typhoon cyclone strength distribution can be intuitively understood; therefore, the time interval can be shortened, and monitoring of a convection system which develops rapidly is facilitated; besides, the method has higher nonlinear reconstruction capability and higher inversion precision.

Description

technical field [0001] The invention relates to the technical field of strong convective weather early warning, in particular to a deep learning-based inversion method for geostationary meteorological satellite radar reflectivity factors. Background technique [0002] Disastrous weather often shows the natural characteristics of high intensity, strong destructiveness, wide distribution, rapid development and evolution, and great destructive power, which has attracted widespread attention. Quickly and effectively responding to disastrous weather events such as strong winds, heavy rainfall, and mountain torrents is of great significance to reducing the threat to the safety of people's lives and property. The key to forecasting these sudden disaster weather systems is timely observation, which has high spatial resolution and is the basis for situational awareness and forecasting. As we all know, Doppler weather radar with high temporal and spatial resolution has become one 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
IPC IPC(8): G01S13/95G01S13/89G01S7/41G06F30/27G06N3/04G06N3/08G06N5/00G06N20/20
CPCG01S13/955G01S13/89G01S7/411G06F30/27G06N20/20G06N3/08G06N5/01G06N3/048G06N3/045Y02A90/10
Inventor 孙逢林覃丹宇李博陆其峰
Owner NAT SATELLITE METEOROLOGICAL CENT
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