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

Interpretable short critical extreme rainfall prediction method based on attention mechanism

A technology of extreme rainfall and forecasting methods, applied in forecasting, climate sustainability, weather condition forecasting, etc., can solve problems such as low forecasting accuracy and weak generalization ability

Active Publication Date: 2020-10-23
HOHAI UNIV
View PDF2 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, it is difficult to apply the climate characteristics of this area to all regions, so the prediction accuracy of the model for short-term heavy rainfall is low, and the generalization ability 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
  • Interpretable short critical extreme rainfall prediction method based on attention mechanism
  • Interpretable short critical extreme rainfall prediction method based on attention mechanism
  • Interpretable short critical extreme rainfall prediction method based on attention mechanism

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] Below in conjunction with specific embodiment, further illustrate the present invention, should be understood that these embodiments are only used to illustrate the present invention and are not intended to limit the scope of the present invention, after having read the present invention, those skilled in the art will understand various equivalent forms of the present invention All modifications fall within the scope defined by the appended claims of the present application.

[0044] like figure 1 As shown, an interpretable short-term extreme rainfall prediction method based on the attention mechanism disclosed in the embodiment of the present invention mainly includes the following steps:

[0045] Step 1: Collect observation data from meteorological stations and filter and clean the obtained data sets;

[0046] Step 2: Use the random forest algorithm to calculate the correlation between the meteorological factors observed at the meteorological station and the rainfall...

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 interpretable short critical extreme rainfall prediction method based on an attention mechanism. The interpretable short critical extreme rainfall prediction method includesthe steps: firstly, screening use parameters through a random forest; calculating a standard precipitation index (SPI) of the to-be-measured station; forming a new matrix by the standard precipitationindexes and the selected parameters and inputting the new matrix into a long-term and short-term memory network for training; adding an attention mechanism into the neural network; visualizing weightcalculation of the attention mechanism in the training process; and finally, predicting the rainfall of the target area in the future 3, 6, 9 and 12 hours by taking 3 hours as a unit, wherein an attention mechanism is used in the prediction process to optimize the situation of short-term heavy rainfall, so that the prediction capability of the model for extreme weather is improved, and meanwhile,the interpretability of the model is also enhanced.

Description

technical field [0001] The invention relates to the field of rainfall prediction, in particular to an interpretable short-term and extreme rainfall prediction method based on an attention mechanism. Background technique [0002] Atmospheric precipitation is an important part of the global water cycle, especially in arid and semi-arid regions, where rainfall is the main source of water supply. The study of rainfall forecast is of great significance to economic development and improvement of people's quality of life. The category of rainfall forecast is generally divided into four categories according to the forecast time, short-term forecast, short-term forecast, medium-term forecast and long-term forecast. Among them, the short-term forecast can warn the occurrence of disasters such as mudslides, and at the same time guide local traffic and people's travel. In addition, the variability, diversity and complexity of meteorological conditions make it difficult to predict extre...

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): G06Q10/04G06Q10/06G06Q50/26G01W1/10G06N3/04G06N3/08
CPCG06Q10/04G06Q10/06393G06Q50/26G06N3/049G06N3/08G01W1/10G06N3/045Y02A90/10
Inventor 张鹏程曹文南
Owner HOHAI 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