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

Air quality prediction method based on deep transition network

An air quality and network technology, applied in the field of data processing, can solve problems such as insufficient ability to extract potential features, no way to completely model coverage, etc., to avoid mutual interference.

Pending Publication Date: 2021-12-07
JILIN UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Second, there will be complex changes between pollutants, pollutants and meteorological information, and there is no way to fully model and cover all the changes
But the ability of these methods to extract latent features given auxiliary information is not enough

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
  • Air quality prediction method based on deep transition network
  • Air quality prediction method based on deep transition network
  • Air quality prediction method based on deep transition network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0058] The present invention will be further described below in conjunction with the accompanying drawings. It should be noted that this embodiment is based on the technical solution, and provides detailed implementation and specific operation process, but the protection scope of the present invention is not limited to the present invention. Example.

[0059] This embodiment provides an air quality prediction method based on a deep transition network, as shown in Figure 1, the specific process is:

[0060] S1. Obtain air quality time series data and perform preprocessing. The preprocessing process is:

[0061] S1.1. Missing value processing:

[0062] There are a lot of incomplete, inconsistent, abnormal, and deviant data in the original air quality time series data, which will affect the accuracy of air quality prediction. Therefore, data preprocessing is essential, and the common work is the missing value processing of the data set.

[0063] Data missing value processing c...

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 an air quality prediction method based on a deep transition network, and provides an air quality prediction model (AI-DTN) based on auxiliary information and the deep transition network in order to extract deep spatial features and time features of air quality data, and the AI-DTN comprises two transition networks in positive and negative different directions. And feature information is extracted from the positive and negative time sequence directions so as to enhance the feature extraction degree. Each transition network in the AI-DTN is composed of a gating circulation unit AI-GRU for extracting space features and fusing auxiliary information and an existing transition gating circulation unit T-GRU for extracting time features. In two kinds of gating of the AI-GRU, one is used for controlling the degree of the auxiliary information flowing into the gating circulation unit, the other one is used for controlling the fusion degree of the PM2.5 and the auxiliary information, and the gating mechanism can avoid mutual interference in the information fusion process.

Description

technical field [0001] The invention relates to the technical field of data processing, in particular to an air quality prediction method based on a deep transition network. Background technique [0002] There are many factors that affect air quality, such as pollutants such as NO and CO, vehicle exhaust, industrial emissions, and meteorological information such as wind speed, wind direction, and rainfall. These information are collectively referred to as auxiliary information. However, there are certain difficulties in using these auxiliary information to predict air quality. First, it is difficult to obtain all of this information accurately. For pollution information, it is also difficult to obtain all real-time vehicle exhaust emissions and industrial emission information. For weather information, because there is a certain deviation in the forecast information, it cannot be used. Forecast information, which will cause error accumulation. Therefore, current air quality...

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): G06K9/62G06N3/04G06N3/08G06Q10/04
CPCG06N3/084G06Q10/04G06N3/044G06F18/214
Inventor 欧阳继红杨智尧王艺蒙曲延非李嘉寅毕夏旭王兵
Owner JILIN 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

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