Radar quantitative rainfall estimation method based on deep learning

A deep learning and radar technology, applied in the field of remote sensing information processing, can solve problems such as large errors, and achieve the effects of easy operation, good recognition effect, and improved convergence speed

Pending Publication Date: 2021-12-14
NANJING UNIV OF INFORMATION SCI & TECH
View PDF1 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Aiming at the problems existing in the prior art, the present invention provides a radar quantitative precipitation estimation method based on deep learning. The radar quantitative precipitation estimation method estimates the

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
  • Radar quantitative rainfall estimation method based on deep learning
  • Radar quantitative rainfall estimation method based on deep learning
  • Radar quantitative rainfall estimation method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] The technical solution of the present invention will be further described below in conjunction with the accompanying drawings.

[0029] Such as figure 1 It is a flow chart of the radar quantitative precipitation estimation method based on deep learning of the present invention, and the radar quantitative precipitation estimation method specifically includes the following steps:

[0030] (1) Obtain weather radar data and ground station precipitation data respectively according to historical precipitation data; Among the present invention, historical precipitation data is obtained from China Meteorological Data Network (http: / / data.cma.cn).

[0031] (2) According to the weather radar data obtained in step (1), the elevation angle reflectivity data of the weather radar is screened, coordinate conversion, interpolation, and the weather radar data of preprocessing is obtained; specifically, according to the weather radar obtained in step (1) Data, filter and retain the weat...

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 radar quantitative rainfall estimation method based on deep learning. The method comprises the following steps: acquiring weather radar data and ground station rainfall data; performing data screening and coordinate correction on the reflectivity data of the elevation angle of the weather radar data; performing data quality control on the rainfall data of the ground station to obtain a relatively accurate rainfall intensity label; carrying out space-time matching on the weather radar data and the ground station rainfall data after pre-data processing, cutting the weather radar data into three-dimensional radar data structures, and respectively taking the three-dimensional radar data structures as input samples and labels of a radar quantitative rainfall estimation model; and generating a complete quantitative rainfall estimation result, and superposing the result on the topographic file to generate accurate regional rainfall information. The rainfall intensity can be accurately estimated based on the radar data, and high-precision regional rainfall intensity estimation is realized.

Description

technical field [0001] The invention belongs to the technical field of remote sensing information processing, and in particular relates to a radar quantitative precipitation estimation method based on deep learning. Background technique [0002] More accurate and real-time Quantitative Precipitation Estimation (QPE) provides a reliable data source for hydrological, meteorological and disaster forecasting. However, the spatial distribution of rainfall processes is very complex, and 70–80% of the uncertainty in land hydrological processes is attributed to the temporal and spatial variability of precipitation, which poses a serious challenge to QPE. The spatial resolution of radar data is about 1 km, which is the best among all remote sensing data, and is often used in the study of QPE. The QPE methods based on radar data are mainly divided into two types: one uses the Z-R relationship, and the other is based on the combined radar-raingauge (R-G) method. The Z-R relationship ...

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): G01S13/95G01W1/14G06K9/62G06N3/04G06N3/08
CPCG01S13/95G01W1/14G06N3/08G06N3/045G06F18/253Y02A90/10
Inventor 陈诗伟张永宏王丽华
Owner NANJING UNIV OF INFORMATION SCI & TECH
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