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

Sandstorm prediction method based on improved Naive Bayesian-CNN multi-objective classification algorithm

A technology of classification algorithm and prediction method, applied in the field of sandstorm prediction, to achieve the effect of strong scalability

Active Publication Date: 2019-05-21
INNER MONGOLIA UNIV OF TECH
View PDF5 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In order to overcome the above-mentioned shortcoming that the existing sandstorm forecasting model based on statistics only considers a single factor when sandstorms occur, the purpose of the present invention is to provide a kind of sandstorm forecasting method based on the improved Naive Bayesian-CNN multi-objective classification algorithm, aiming at the sandstorm forecasting problem, Under the condition of meeting the constraints of sandstorm prediction accuracy, the model is continuously optimized to solve the problem of sandstorm prediction from a spatial three-dimensional perspective, and achieve the goal of effectively predicting the intensity and location of sandstorm occurrence

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
  • Sandstorm prediction method based on improved Naive Bayesian-CNN multi-objective classification algorithm
  • Sandstorm prediction method based on improved Naive Bayesian-CNN multi-objective classification algorithm
  • Sandstorm prediction method based on improved Naive Bayesian-CNN multi-objective classification algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] The implementation of the present invention will be described in detail below in conjunction with the drawings and examples.

[0037] Description of the problem: Predict the occurrence intensity of sandstorms while considering surface meteorological factors and atmospheric movement factors.

[0038] Time complexity constraints: model training time max .

[0039] Space complexity constraint: storage space required for model training max .

[0040] Decision variable: the accuracy of the model's prediction of sandstorms under different levels of sandstorms.

[0041] where T max is the upper bound of the model training time, S max is the maximum storage space limit specified by the server.

[0042] refer to figure 1, the present invention first considers the impact of atmospheric movement factors on sandstorms, establishes a sandstorm prediction model based on convolutional neural network algorithms, considers the impact of ground meteorological factors on sandstorms, ...

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

A sandstorm prediction method based on an improved Naive Bayesian-CNN multi-objective classification algorithm uses the "China's strong sandstorm sequence and its supporting dataset", the "China's strong sandstorm sequence and its supporting dataset" and the "China's terrestrial regional cloud map (IR1)" as the research objects. The method comprises the following steps of firstly considering the ground factors of sandstorm occurrence, using a naive Bayesian algorithm to analyze the meteorological data collected by the meteorological station, and establishing a sandstorm prediction model; secondly, considering that the atmospheric motion also affects the occurrence of sandstorms, using a convolutional neural network algorithm to analyze the infrared satellite cloud image and establish a sandstorm prediction model; and finally using a multi-objective algorithm to normalize the output probability of the two sandstorm prediction models. A sandstorm prediction method with strong expandability based on an improved Naive Bayesian-CNN multi-objective classification algorithm is disposed. The algorithm and the sandstorm prediction method provided by the invention comprehensively consider the influence of ground and atmospheric motion on the sandstorm occurrence, and are consistent with the characteristics of sandstorm occurrence.

Description

technical field [0001] The invention belongs to the technical field of artificial intelligence and extreme weather forecasting, relates to the forecasting of sandstorms, in particular to a sandstorm forecasting method based on an improved Naive Bayesian-CNN multi-objective classification algorithm. Background technique [0002] In arid regions on the earth, especially in deserts and their adjacent regions, sandstorms often occur, and the severe ones are sandstorms. This natural phenomenon has been natural since ancient times and is due to the specific natural geographical environment and climatic conditions. Only Europe has not reported sandstorms in the whole world, and there are sandstorms in Asia, Africa, America and Australia, which are related to the long-term and relatively regular and short-term and relatively irregular changes of the climate. Natural disasters such as global large-scale drought, desertification, floods, and freezing threats to human beings have freq...

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): G01W1/10G06K9/62G06N3/04
Inventor 仁庆道尔吉李天成李娜邱莹
Owner INNER MONGOLIA UNIV OF 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