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

Deep learning-based northern hemisphere high latitude region ROTI prediction method

A deep learning, high-latitude technology, applied in the direction of neural learning methods, neural architecture, biological neural network models, etc., can solve the problems of Doppler frequency shift, reduce the accuracy of satellite navigation, increase the bit error rate, etc., and achieve generalization ability Improve the effect of real-time and effective forecasting

Inactive Publication Date: 2020-12-11
AEROSPACE INFORMATION RES INST CAS
View PDF2 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

When the fading amplitude exceeds the redundancy and dynamic range of the receiving system, it will cause satellite communication obstacles and increase the bit error rate; phase scintillation will cause Doppler frequency shift
Due to the influence of the irregular structure of the ionosphere, the refraction index of radio waves also fluctuates randomly, which changes the signal path, causes multipath effects and reduces the accuracy of satellite navigation.

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 northern hemisphere high latitude region ROTI prediction method
  • Deep learning-based northern hemisphere high latitude region ROTI prediction method
  • Deep learning-based northern hemisphere high latitude region ROTI prediction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] The present invention will be described in detail below with reference to the accompanying drawings and examples.

[0030] The present invention provides a method for predicting ROTI in high latitude regions of the northern hemisphere based on deep learning. The purpose is to use a recursive neural network to predict ROTI in the future to provide ionospheric scintillation warning services.

[0031] Among them, ROTI is the time series of TEC (total ionospheric electron content) rate of change index. Compared with traditional artificial neural network (ANN), recurrent neural network (RNN) can better capture the information of time series data: RNN and ANN The error backpropagation algorithm is also used, but the training parameters of ANN are only transmitted between neurons in different layers, while the training parameters of RNN are not only output to the next layer of neurons, but also passed to the next layer of neurons in this layer. time. Therefore, RNN (SimpleRNN...

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 deep learning-based northern hemisphere high latitude region ROTI prediction method, which can achieve real-time prediction of ionospheric scintillation by predicting the value of ROTI several minutes later by using an artificial intelligence method. The method comprises the following steps: collecting and obtaining related parameter data influencing ionospheric scintillation in a high-latitude area, wherein the related parameter data comprise ROTI indexes; dividing all data into a training set, a verification set and a test set; preprocessing the data in the trainingset, the verification set and the test set to obtain normalized data; and aiming at the combination of the normalized data of the current moment t and the previous set quantity moment, setting the set label as the ROTI index of the future moment, and obtaining the mapping relationship; and constructing a recurrent neural network model, performing training by using the training set, and performingverification by using the verification set; returning the loss functions of the training set and the verification set in each iteration, and ending the training when the loss function of the verification set reaches the minimum, so as to obtain a trained recurrent neural network model, i.e., the ROTI prediction model.

Description

technical field [0001] The present invention relates to the field of space ionosphere technology, in particular to a method for predicting ROTI in high latitude regions of the northern hemisphere based on deep learning. Background technique [0002] The existence of the ionosphere and its electron density inhomogeneity makes the amplitude, phase, angle of arrival and polarization state of the radio waves passing through it fluctuate rapidly, which is ionosphere scintillation. Ionospheric scintillation often causes deep fading and distortion of radio signals received by ground receivers. For example, amplitude flicker will cause signal fading, which can reach more than 20dB at most. When the fading amplitude exceeds the redundancy and dynamic range of the receiving system, it will cause satellite communication obstacles and increase the bit error rate; phase scintillation will cause Doppler frequency shift. Due to the influence of the irregular structure of the ionosphere, ...

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): G06N3/04G06N3/08
CPCG06N3/084G06N3/049G06N3/045
Inventor 李子申徐福隆张克非王宁波王晓明
Owner AEROSPACE INFORMATION RES INST CAS
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