Object-oriented artificial intelligence test method for rainfall forecast

A technology of artificial intelligence and inspection methods, which is applied in meteorology, weather condition forecasting, instruments, etc., and can solve problems such as regional sensitivity

Pending Publication Date: 2021-10-19
江苏铨铨信息科技有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

MODE can only give the matching relationship between different observed precipitation areas and different forecast precipitation areas, while CRA and SAL need to subjectively select precipitation areas, and the test results are very sensitive to the range of the area

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
  • Object-oriented artificial intelligence test method for rainfall forecast
  • Object-oriented artificial intelligence test method for rainfall forecast
  • Object-oriented artificial intelligence test method for rainfall forecast

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment

[0105] Inspect the ERA5 ensemble average 24h precipitation forecast product at 00:00 UTC on July 27, 2021 (inspection area: 25°~45°N, 110°~150°E);

[0106] The first step is to read the precipitation observation field and precipitation forecast field ( Figure 3a is the situation of the original precipitation observation field in the embodiment, in mm; Figure 3b is the original precipitation forecast field situation of the embodiment, unit mm);

[0107] In the second step, a nine-point Gaussian filter smoothing process is performed on the precipitation observation field and the precipitation forecast field respectively ( Figure 4a is the situation after the smoothing of the precipitation observation field in the embodiment, the unit is mm; Figure 4b is the situation after smoothing the precipitation forecast field in the embodiment, unit mm);

[0108] In the third step, given the precipitation threshold (2mm), only keep the precipitation greater than or equal to the thre...

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 an object-oriented artificial intelligence test method for rainfall forecast. The method comprises the following specific steps: 1, reading data of a rainfall observation field (Robs) and a rainfall forecast field (Rfcst); 2, performing nine-point Gaussian filtering smoothing processing on the Robs and the Rfcst respectively; 3, giving a rainfall threshold R0, and reserving Robs and Rfcst which are larger than or equal to R0, wherein all rainfall smaller than R0 is taken as zero; 4, identifying all continuous precipitation areas in the Robs and the Rfcst respectively; 5, matching the precipitation areas based on the gravity center distance of the precipitation area in Robs and the precipitation area in Rfcst; and 6, performing error decomposition on each precipitation area matching pair. Different inspection areas are divided by using an objective method, and then precipitation error decomposition is performed in each area, so that the inspection accuracy can be improved.

Description

technical field [0001] The invention relates to the field of inspection of precipitation forecast products, in particular to an object-oriented artificial intelligence inspection method for precipitation forecast. Background technique [0002] Precipitation is an important physical quantity in meteorology and hydrology, and precipitation forecasting has always been a key and difficult issue in scientific research and business fields. At present, the commonly used precipitation forecast inspection indicators for forecasters mainly include TS (Threat Score) score, root mean square error, etc. These indicators strictly follow the principle of point-to-point testing. Although the mathematical understanding is easier and the business connection is closer, they can only provide an overall evaluation of the forecast performance, and often miss other valuable spatial characteristics of precipitation information, such as the falling area of ​​​​rainbands. , shape, etc. In order to ...

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): G06F30/20G01W1/10G06F113/08
CPCG06F30/20G01W1/10G06F2113/08Y02A90/10
Inventor 郭洪涛宋金杰
Owner 江苏铨铨信息科技有限公司
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