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

Hail and short-time heavy rainfall forecasting method based on GBDT+LR model

A LR model, a technology for heavy precipitation, applied in weather forecasting, measuring devices, meteorology, etc., can solve the problem of small detection space scale, achieve excellent performance and reduce impact.

Inactive Publication Date: 2020-03-17
TIANJIN UNIV
View PDF8 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Weather radar can be used to forecast hail and short-term heavy precipitation, but the information reflected by weather radar is only the real situation, and the detection space scale is small. Therefore, weather radar cannot make forecasts for a long time in advance

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 and short-time heavy rainfall forecasting method based on GBDT+LR model
  • Hail and short-time heavy rainfall forecasting method based on GBDT+LR model
  • Hail and short-time heavy rainfall forecasting method based on GBDT+LR model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0056] This embodiment takes the Tianjin area as an example. The hail and short-term heavy precipitation forecast method based on the GBDT+LR model in Tianjin includes the following steps:

[0057] Step S1, acquisition of raw data:

[0058]Collect the ground meteorological observation station data of Tianjin Meteorological Bureau from March to September every year from 2006 to 2018, hours before the occurrence of hail and short-term heavy precipitation, including: ground pressure, sea level pressure, temperature, dew point temperature, relative Humidity, vapor pressure, 2-minute average wind direction, 2-minute average wind speed, 10-minute average wind direction, and 10-minute average wind speed. In this embodiment, the data of 3 hours before the occurrence of hail and short-term heavy precipitation are collected.

[0059] see figure 1 , select the data of five sounding stations (at 8:00 am and 8:00 pm) in the upper reaches of Tianjin, Beijing air-sounding meteorological s...

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 hail and short-time heavy rainfall forecasting method. The method comprises the following steps: acquiring ground meteorological observation station data of a certain regionfrom March to September each year before hail and short-time heavy rainfall occur and data of a plurality of sounding stations at the upstream of the region; expanding the hail process data with relatively small data volume in the data through an SMOTE oversampling algorithm to obtain an oversampled data set; carrying out dimension reduction on the oversampled data set by adopting a PCA method; dividing samples in the data set after dimension reduction into a training set and a test set; constructing a GBDT + LR model, taking features extracted from leaf nodes of the GBDT model as input features of the LR model, and training and testing the GBDT + LR model through the samples of the training set and the test set; and acquiring ground meteorological observation station data three hours before a to-be-predicted time point of the region, acquiring data of a plurality of sounding stations at the upstream of the region, substituting the data into the trained GBDT + LR model and judging whether hail or short-time heavy rainfall occurs at the predicted time point.

Description

technical field [0001] The invention relates to the field of weather forecasting, in particular to a method for forecasting hail and short-term heavy precipitation. Background technique [0002] In meteorological forecasting, hail and short-term heavy precipitation have the characteristics of short generation and extinction cycles, small affected areas, and extremely severe weather changes. They will have a great impact on industry, agriculture and people's daily life. [0003] Weather radars can be used to forecast hail and short-term heavy precipitation, but the information reflected by weather radars is only the real situation, and the detection space scale is small. Therefore, weather radars cannot forecast for a long time in advance. Contents of the invention [0004] In order to overcome the deficiencies of the prior art, the present invention aims to provide a method for forecasting hail and short-term heavy precipitation based on the GBDT+LR model, using the relat...

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): G01W1/10
CPCG01W1/10
Inventor 路志英汪永清
Owner TIANJIN UNIV
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