Method for classifying precipitation types by using K-nearest neighbor algorithm

A type and type of precipitation technology, applied in calculation, computer components, instruments, etc., can solve the problem of high sensitivity, achieve fast and accurate division, and improve the effect of precipitation estimation

Inactive Publication Date: 2019-07-26
LANZHOU UNIVERSITY
View PDF14 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Recent studies have shown that the sensitivity of the convective rainfall fraction to the choice of Z-I relationship can be considerable

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
  • Method for classifying precipitation types by using K-nearest neighbor algorithm
  • Method for classifying precipitation types by using K-nearest neighbor algorithm
  • Method for classifying precipitation types by using K-nearest neighbor algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] A kind of method of using K proximity algorithm to carry out precipitation type classification of the present invention, specifically comprises the following steps:

[0026] A) select training data set, described training data set is made up of a plurality of training samples, and determines the classification type of each training sample; The selected training sample is to select satellite cloud type data to scan range on space and ground-based radar data space The upper scanning range is the same, the scanning time is the same and there are obvious weather phenomena, such as wind, cloud, fog, rain, snow, frost, thunder, hail, etc., as training samples;

[0027] b) Select a verification sample, the classification type of the verification sample is known;

[0028] c) Calculate the distance between the verification sample and each training sample in the training data set; the distance between the verification sample and each training sample in the training data set and t...

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 field of weather and hydrology and classification of precipitation types, in particular to a method for classifying precipitation types by using a K-nearest neighbor algorithm, which comprises the following steps: 1) selecting a training data set, 2) selecting a verification sample, and 3) calculating the distance between the verification sample and each training sample in the training data set; 4) selecting K values, classification types of K samples closest to the verification samples in the training data set, and the classification types as the classification types of the verification samples; 5) selecting different K values to calculate and compare, and determining a post-optimal K value, and 6) selecting a real-time sample, calculating and comparing by using the determined optimal K value, and determining the classification type of the real-time sample. The precipitation types are classified by using the ground-based radar data and the tropical precipitation measurement satellite TRMM satellite rainfall type product data on the basis of the K-nearest neighbor algorithm, the precipitation types are quickly and accurately divided on an existing service platform, and the estimation of the precipitation amount is improved.

Description

technical field [0001] The invention relates to the field of meteorology and hydrology, and the classification of precipitation types, in particular to a method for classifying precipitation types by using a K-proximity algorithm. Background technique [0002] Precipitation can be divided into stratiform precipitation and convective precipitation. The convective precipitation system generally has the characteristics of strong rising speed, small area and high precipitation intensity, while the stratiform precipitation system has weak rising speed and large precipitation range. and the characteristics of weak precipitation intensity. [0003] Convective precipitation and stratiform precipitation have different precipitation growth mechanisms, and the physical principles of the two are also different. Discussion and research on convective precipitation and stratiform precipitation can better explore the physical mechanism. [0004] The cumulus cloud system also has a very im...

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): G06K9/62
CPCG06F18/214G06F18/24
Inventor 杨毅杨志达
Owner LANZHOU UNIVERSITY
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