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

Multi-mode rainfall estimation method integrated with machine learning

A machine learning and multi-mode technology, applied in neural learning methods, character and pattern recognition, prediction, etc., can solve problems such as weak predictions

Pending Publication Date: 2021-09-07
NANJING UNIV OF INFORMATION SCI & TECH
View PDF2 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the prediction of extreme climate events in China under the background of global warming combined with global large-scale models and machine learning technology is relatively weak

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
  • Multi-mode rainfall estimation method integrated with machine learning
  • Multi-mode rainfall estimation method integrated with machine learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0020] The specific embodiment of the present invention is further described below in conjunction with accompanying drawing:

[0021] A multi-mode precipitation prediction method of integrated machine learning is characterized in that: it is characterized in that it comprises the following steps:

[0022] Step 1: Data preprocessing: Calculate observations and 22 CMIP6 model history and different paths (ssp245, ssp585) in the future period of heavy precipitation, continuous dry days, average total precipitation, and continuous maximum 5-day precipitation climate index, using double lines Interpolate the CMIP6 results to the grid points consistent with the observation data, and use the data slices of the time axis to obtain the extreme precipitation indices in the period of 1.5, 2, and 3 degrees of warming in the future in China;

[0023] Step 2: Dataset construction: Divide the CMIP6 model data into training data, evaluation verification data, and future climate prediction data...

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 multi-mode rainfall estimation method integrated with machine learning, which is characterized by comprising the following steps: calculating and generating extreme climate indexes of four types of rainfall in a Chinese region by adopting newest CMIP6 climate mode simulation data and grid point data observed by a station of the China Meteorological Administration; training a plurality of machine learning models by utilizing observation and mode data in historical periods, evaluating the performance of different machine models, giving different weights based on the model performance, and forming average and extreme rainfall probability estimation results of different temperature increasing scenes and temperature increasing amplitudes in the future integrally. According to the invention, the multi-mode and multi-machine algorithm integration technology is adopted, the uncertainty introduced by different modes and different algorithms in future estimation is reduced, and the estimation result is more reliable.

Description

technical field [0001] The invention belongs to the technical field of precipitation and climate forecasting, and in particular relates to a multi-mode precipitation forecasting method integrated with machine learning. Background technique [0002] The world has shown a significant warming trend in the past century. According to the IPCC report, warming may pose a great threat to the future climate system, such as the frequent occurrence of extreme events in recent years. Preliminary research so far suggests that the risk of extreme events increases significantly for warming above 2°C. The ensemble prediction based on multi-climate models is an effective means to improve the reliability of regional climate prediction. However, in the past, equal-weight ensemble and weighted ensemble were mostly used. Uncertainty is also very sensitive to evaluation variables and methods, and how to reduce the uncertainty of multi-model ensemble estimation poses a great challenge. [0003] ...

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): G06Q10/04G06K9/62G06N3/04G06N3/08G06Q50/26
CPCG06Q10/04G06Q50/26G06N3/08G06N3/045G06F18/23213Y02A90/10
Inventor 赵立龙江志红李童朱欢欢
Owner NANJING UNIV OF INFORMATION SCI & TECH
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