Air quality prediction method in gridding monitoring

A technology of air quality and prediction method, applied in the field of deep learning, to improve the fitting effect, improve the accuracy, and solve the long-term dependence problem.

Pending Publication Date: 2022-01-28
中国科学院沈阳计算技术研究所有限公司
View PDF0 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In view of the above-mentioned technical deficiencies, by analyzing the change trend of the air pollutant concentration data of the monitoring station in the grid monitoring, it is found that the change trend of the air pollutant concentration data in the grid monitoring and each monitoring in the grid monitoring The spatial correlation of points has a certain connection, and the technical problem to be solved in the present invention is exactly to extract the spatial correlation feature between the monitoring sites in the grid monitoring, and improve the accuracy of the pollutant concentration data (air quality) in the air of the grid monitoring. Prediction accuracy

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 in gridding monitoring
  • Air quality prediction method in gridding monitoring
  • Air quality prediction method in gridding monitoring

Examples

Experimental program
Comparison scheme
Effect test

example

[0087] Enter as:

[0088] site longitude latitude Station A 123.556854 41.762261 Station B 123.525083 41.751233 Station C 123.439275 41.715011

[0089] First calculate the distance matrix between each site, and get the distance matrix as: (distance unit km)

[0090]

[0091] Then adjust the distance matrix according to the maximum influence distance k between the monitoring stations input by the user, assuming that the maximum influence distance k=9 (unit km) input by the user, then the adjusted matrix is:

[0092]

[0093] Then add a self-loop to the adjusted distance matrix to get the adjusted adjacency matrix:

[0094]

[0095] Step 4: This step is to map the time series matrix of pollutant concentration in the air obtained in step 2 to [0, 1], which is normalization.

[0096] Example:

[0097] Assuming the maximum air pollutant concentration x in the time series of transformed air pollutant concentrations in step two max ...

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 an air quality prediction method in gridding monitoring. The method comprises the following steps: firstly, performing data cleaning on position information and historical air pollutant concentration information of each monitoring station in gridding monitoring input by a user, then inputting the processed data into a GCN to extract space correlation information among the monitoring stations, and inputting the data with the space information into an LSTM to extract time features; and finally, integrating the features extracted by the GCN and the LSTM through a linear regression layer, generating a prediction result, and returning the prediction result to a user. The effectiveness of the method is verified through related experiments.

Description

technical field [0001] The invention relates to the field of deep learning, in particular to an air quality prediction method based on grid monitoring of GCN and LSTM. Background technique [0002] With the continuous development of my country's environmental monitoring technology and concepts, the grid monitoring technology of pollutant concentration in the air is more and more favored by relevant staff. This grid monitoring technology of pollutant concentration in the air can be used to a certain extent. However, the monitoring data of each monitoring station produced by grid monitoring has obvious spatial correlation information, and the existing air quality prediction algorithms seldom take monitoring into account. The spatial correlation characteristics between stations, which makes the use of conventional prediction methods in grid monitoring will cause a certain loss of prediction accuracy due to ignoring the spatial correlation characteristics in grid monitoring. Con...

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): G06Q10/04G06N3/04G06K9/62G06F30/27G06F30/18G01N33/00
CPCG06Q10/04G06F30/27G01N33/0004G06F30/18G06N3/044G06N3/045G06F18/214
Inventor 祁柏林王宁郭昆鹏杨彬杜毅明魏景峰王继娜刘闽王兴刚范秋枫孟繁星陈月
Owner 中国科学院沈阳计算技术研究所有限公司
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
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap