Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Method and device for extracting multi-mode optimal information for rainfall set prediction, and medium

A model information and multi-model technology, applied in the field of multi-model precipitation forecasting, can solve problems such as forecast failure

Pending Publication Date: 2021-10-19
INST OF ATMOSPHERIC PHYSICS CHINESE ACADEMY SCI
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, through evaluation, it is found that even a model system with poor overall performance in precipitation prediction can have good prediction perfor

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 and device for extracting multi-mode optimal information for rainfall set prediction, and medium
  • Method and device for extracting multi-mode optimal information for rainfall set prediction, and medium
  • Method and device for extracting multi-mode optimal information for rainfall set prediction, and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0029] Multi-mode ensemble methods mostly use ensemble averages, including equal-weight arithmetic mean (formula (1)), and non-equal-weight algorithms (formula (2));

[0030]

[0031]

[0032] Among them, y 1 ,y 2 ,...,y M is the direct prediction result of M modes, y' is the prediction result; α 1 , α 2 ,...,α M are the weight coefficients of the M modes. when α 1 = α 2 =...=α M When the weight coefficient of the optimal mode with good performance is 1, and the weight coefficient of the mode with poor performance is 0, it is the optimal mode aggregation me...

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 a method and a device for extracting multi-mode optimal information for rainfall set prediction, and a medium, and the method comprises the steps of performing modal decomposition on observed rainfall to obtain spatial distribution and corresponding time coefficients, and obtaining prediction information of a j-th mode related to an i-th mode and a prediction result of the time coefficient of the i-th mode through screening; adopting a step-by-step introduction and step-by-step elimination method to eliminate a result which has a negative effect on a set average result to obtain a set sample subset, performing equal-weight arithmetic averaging to serve as a prediction time coefficient of a corresponding mode, and reconstructing observation rainfall; due to the fact that each mode has a mode with good prediction performance, in the final explanation application model, advantage information of each mode is reserved, and compared with a conventional optimal mode set method, the method fully excavates available information of modes with low prediction performance in conventional evaluation.

Description

technical field [0001] The invention belongs to the field of climate prediction, and in particular relates to a method, device and medium for multi-model ensemble prediction of precipitation. Background technique [0002] my country is a high-incidence area of ​​climate disasters, and the huge economic losses every year seriously affect the sustainable development of the country. Therefore, departments such as agriculture, water conservancy, and disaster prevention and mitigation urgently need accurate short-term climate prediction information to serve the national economic construction scientifically and reduce casualties and economic losses caused by climate disasters. Compared with short-term weather forecasting, climate forecasting is not only a matter of the initial value of the atmosphere, but also involves the changes and interactions of the various spheres of the earth system. The variation mechanism of the forecasted objects is very complicated. Therefore, climate f...

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): G06Q10/04G06F30/20G06Q50/26
CPCG06Q10/04G06Q50/26G06F30/20Y02A90/10
Inventor 马洁华孙建奇
Owner INST OF ATMOSPHERIC PHYSICS CHINESE ACADEMY SCI
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
Eureka Blog
Learn More
PatSnap group products