Unlock instant, AI-driven research and patent intelligence for your innovation.

PM2.5 concentration prediction method and system

A concentration prediction and concentration technology, applied in prediction, biological neural network model, data processing application, etc., can solve problems such as low accuracy and difficulty in PM2.5 concentration prediction

Pending Publication Date: 2021-02-26
CHANGCHUN UNIV OF SCI & TECH
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Mineral dust, aerosols and trace metals in pollution emission sources can also catalyze the formation of PM2.5. All these factors make the prediction of PM2.5 concentration more difficult. Currently, regression models and backpropagation neural networks are used. The network predicts the concentration of PM2.5, but the accuracy is not high

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
  • PM2.5 concentration prediction method and system
  • PM2.5 concentration prediction method and system
  • PM2.5 concentration prediction method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach

[0105] As an optional implementation, the concentration prediction module includes:

[0106] The second data acquisition unit is configured to acquire the historical feature data to be trained.

[0107] A division unit, configured to divide the historical feature data to be trained according to a set time interval to obtain multiple sets of historical feature data sets.

[0108] The correlation calculation unit is used to calculate the correlation between the PM2.5 concentration in the historical feature data to be trained and each remaining feature using the Spearman formula; the remaining feature is the historical feature data to be trained Characteristic data except PM2.5 concentration in .

[0109] The grouping unit is used to group all correlations to obtain positive correlation sequences and negative correlation sequences.

[0110] The training unit is used to combine the feature data set corresponding to the positive correlation sequence in the i-th group of historica...

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 a PM2.5 concentration prediction method and system. The method comprises the following steps of acquiring historical feature data to be predicted; and inputting the historicalfeature data to be predicted into a PM2.5 concentration prediction model to obtain the predicted concentration of PM2.5, wherein the PM2.5 concentration prediction model is obtained by training a long-term and short-term memory network model comprising a plurality of input gates by taking the historical feature data to be trained as input. The method is advantaged in that by using the multi-inputlong-short-term memory model, the optimization from the multi-dimensional single-input sequence model structure to the three-dimensional multi-input sequence model structure is realized, so PM2.5 concentration prediction efficiency is higher, and the result is more accurate.

Description

technical field [0001] The invention relates to the technical field of air quality prediction, in particular to a PM2.5 concentration prediction method and system. Background technique [0002] Air pollution is considered to be a serious environmental problem because of its adverse effects on human health. Air pollution is considered to be the leading cause of death related to environmental conditions. Typical sources of air pollution include traffic and industrial emissions. The main pollutants are particulate matter 2.5 (PM2.5), particulate matter 10 (PM10), NO 2 , SO 2 , O 3 Among them, PM2.5 is the most harmful to human beings. [0003] PM2.5 refers to fine particles or particles less than 2.5 microns in diameter, usually composed of solid or liquid particles. PM2.5 seriously endangers the health of sensitive groups such as children and the elderly. The prediction of PM2.5 concentration is helpful for people's travel decision-making and environment-related policies,...

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): G06Q10/04G06N3/04
CPCG06Q10/04G06N3/044G06N3/045
Inventor 张昕周超然张莹赖斯莹刘婧娴何金龙王超伟何敏杨宏伟
Owner CHANGCHUN UNIV OF SCI & TECH