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

Hail recognition method under multi-dimensional radar data based on semi-supervised learning

A semi-supervised learning and radar data technology, which is applied in the interdisciplinary field of computer artificial intelligence and meteorology, can solve the problems that the recognition effect needs to be improved, and achieve the effect of automatically optimizing the training model, improving the accuracy rate, and reducing the false alarm rate

Active Publication Date: 2021-07-09
CHENGDU UNIV OF INFORMATION TECH
View PDF8 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] This method ignores the difference between the n-dimensional features involved in the operation, and the recognition effect after classification needs to be improved

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
  • Hail recognition method under multi-dimensional radar data based on semi-supervised learning
  • Hail recognition method under multi-dimensional radar data based on semi-supervised learning
  • Hail recognition method under multi-dimensional radar data based on semi-supervised learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0040] This embodiment discloses a hail recognition method based on semi-supervised learning under multi-dimensional radar data, comprising the following steps:

[0041] S1: Obtain the labeled sample set, extract the supervised sample set from the labeled sample set by random sampling, and divide the labeled sample set into the rainstorm sample training set and the hail sample training set according to the rainstorm and hail labels, and obtain the unlabeled data set. Divided into q first samples;

[0042] In this embodiment, the labeled sample set includes radar basic reflectivity images and Doppler weather radar series data;

[0043] Specifically, read in m labeled sample sets:

[0044]

[0045] Randomly selected from the labeled sample set samples, named Used to supervise the training process. Supervised sample set :

[0046]

[0047] According to the labeled sample labels, it is divided into rainstorm sample training set training set with hail samples :

...

Embodiment 2

[0088] Based on the method in Embodiment 1, a specific implementation is proposed in this embodiment to train and test the method in Embodiment 1:

[0089] In this embodiment, 104 initial hail training data and 103 hail test data are selected, 104 are randomly selected from 207 hail live data as training data, and the other 103 are used as test data; 1098 rainstorm training data are selected simultaneously, 1098 1098 training data and another 1098 are randomly divided from 2196 rainstorm real data as test data. The unknown sample data can be: The network collects the time when the hailstorm occurred in Chongqing in 2019, and analyzes the combined reflectance file near the time point, and obtains a total of 20,850 sample data, which is used as an unlabeled data set for training the recognition model;

[0090] The 20850 unknown sample data were randomly divided into 1000 groups, and then added to the training according to the method in Example 1. The weight values ​​used in the ...

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 provides a hail recognition method under multi-dimensional radar data based on semi-supervised learning, and the method comprises the steps: S1, obtaining a labeled sample set, randomly extracting a supervised sample set, a rainstorm sample training set and a hail sample training set, obtaining an unlabeled data set, and randomly dividing the unlabeled data set into q parts of first samples; s2, calculating a clustering center of each cluster training set; s3, clustering and dividing one first sample into corresponding clusters, and updating a clustering center; s4, performing iteration to obtain the clustering center of each cluster and the confidence coefficient of the corresponding cluster at the moment; s5, repeating the steps S2-S4 on the supervision sample set to obtain supervision confidence of the supervision sample set for each clustering center, and classifying the data into corresponding clusters; s6, judging whether the first sample is updated into the cluster or not, and repeating the steps S2-S6 until the first sample is processed; and S7, inputting the optimal clustering center as a recognition model, obtaining the confidence coefficient of each sample to each cluster, and performing classification. According to the method, the hail identification accuracy is effectively improved, and the false alarm rate is reduced.

Description

technical field [0001] The invention belongs to the technical field of computer artificial intelligence and meteorology, and in particular relates to a hail recognition method under multi-dimensional radar data based on semi-supervised learning. Background technique [0002] Hail is a kind of strong local disastrous weather generated under the background of special geography, topographical environment and certain large-scale circulation; it has the characteristics of sudden occurrence, rapid movement, severe weather and strong destructive power, and it often causes damage to local areas involving agriculture, Huge losses in traffic, electricity, communications and other aspects, and even threaten the safety of people's lives. [0003] Accurate identification of hail is particularly important in hail forecasting and rescue after hail disasters. Effectively improve the accuracy of hail prediction, timely and accurately notify relevant departments to take effective preventive ...

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): G06K9/62G01S13/95
CPCG01S13/95G06F18/23G06F18/24Y02A90/10
Inventor 文立玉罗飞钟宇舒红平曹亮刘魁郭本俊
Owner CHENGDU UNIV OF INFORMATION TECH
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