Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

MWHTS channel weight function calculation method based on neural network

A technology of weight function and neural network, which is applied to the calculation field of MWHTS channel weight function, can solve the problems of large amount of calculation and low calculation efficiency, and achieve the effect of small amount of calculation, simple and easy operation, and fast calculation speed.

Pending Publication Date: 2020-10-02
LUOYANG NORMAL UNIV
View PDF3 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, for the current calculation method based on the physical mechanism of the channel weight function, when a large amount of spaceborne microwave radiation observation data is applied, the calculation amount of this method is large, and the calculation efficiency is low

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
  • MWHTS channel weight function calculation method based on neural network
  • MWHTS channel weight function calculation method based on neural network
  • MWHTS channel weight function calculation method based on neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0039] The observational altitude angle in the observation data of Fengyun-3D Microwave Humidity and Temperature Sounder (MWHTS) is matched with the atmospheric parameters in the ERA Interim data set of the European Center for Medium-Range Weather Forecasting (ECMWF). Among them, the used atmospheric parameters, geospatial The resolution, profile layering, and matching rules in time and space are as described in Step 1. The time range used is from January 2019 to June 2019, and the geographical range is (25°N—45°N, 160 °E—220°E). 583089 groups of matching data can be obtained. Input the matching data into the radiative transfer model RTTOV to calculate the atmospheric transmittance of each atmospheric layer to the satellite payload MWHTS.

[0040] According to step 2, the weight function profile of each MWHTS channel is calculated by using the atmospheric transmittance and the pressure value of each layer of the atmospheric layer, and the matching data set of atmospheric para...

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 MWHTS channel weight function calculation method based on a neural network, and the method comprises the steps: inputting an atmospheric parameter and an MWHTS observation altitude angle into a radiation transmission model RTTOV, and calculating the atmospheric transmittance from each layer in atmospheric stratification to a satellite load MWHTS; calculating an MWHTS channel weight function profile according to the atmospheric transmittance, and establishing a matching data set of the atmospheric parameters, the MWHTS observation elevation angle and the MWHTS channelweight function profile; training a BP neural network based on the matching data set, and establishing an optimal model for MWHTS channel weight function profile calculation based on the BP neural network for each channel of the MWHTS; establishing an MWHTS channel weight function maximum value sample as the output of the deep neural network; training the deep neural network by taking the atmospheric parameters and the MWHTS observation altitude angle as the input of the deep neural network, and establishing an optimal model of atmospheric stratification calculation in which the MWHTS channelweight function maximum value based on the deep neural network is located for each channel of the MWHTS. The method is high in calculation speed, small in calculation amount and simple and easy to operate.

Description

technical field [0001] The invention relates to a calculation method of a weight function of a MWHTS channel, in particular to a calculation method of a weight function of a MWHTS channel based on a neural network. Background technique [0002] Spaceborne microwave radiometers play an important role in the fields of atmospheric science such as numerical weather prediction, climate change research, and severe convective weather monitoring. The channel weight function is the theoretical basis for the channel setting of the spaceborne microwave radiometer receiver, and is an indicator of the sensitivity of each channel of the spaceborne microwave radiometer to different atmospheres. The atmospheric stratification corresponding to the maximum value of the channel weight function indicates that the channel is most sensitive to the layer of the atmosphere. In other words, the detection advantage of the channel is the atmospheric stratification where the maximum value of the channe...

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): G06F17/15G06N3/04G06N3/08
CPCG06F17/15G06N3/08G06N3/084G06N3/045G06N3/044Y02A90/10
Inventor 贺秋瑞李德光金彦龄张永新任桢琴周莉朱婷婷朱艺萍
Owner LUOYANG NORMAL UNIV
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
Eureka Blog
Learn More
PatSnap group products