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

Method for predicting 24-hour PM2.5 concentration based on deep neural network

A deep neural network, 24-hour technology, applied in neural learning methods, biological neural network models, neural architectures, etc., can solve problems such as large long-term concentration prediction errors, overcome modal aliasing, suppress noise interference, and improve models. performance effect

Pending Publication Date: 2022-04-12
WUHAN UNIV
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] For the current PM 2.5 For the problem of large long-term concentration prediction errors, the present invention combines the CEEMD decomposition method with the AE-BILSTM stacked deep neural network model to construct a hybrid prediction model to achieve PM 2.5 Accurate short-term prediction of concentrations and simulation of long-term concentration trends

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
  • Method for predicting 24-hour PM2.5 concentration based on deep neural network
  • Method for predicting 24-hour PM2.5 concentration based on deep neural network
  • Method for predicting 24-hour PM2.5 concentration based on deep neural network

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment

[0047] 1. Implementation goals

[0048] In order to realize the ground detection station PM 2.5 Take the short-term and long-term concentration prediction of concentration as an example. At present, many methods are difficult to achieve short-term accurate prediction and long-term accurate simulation. Therefore, the present invention proposes a mixed prediction model for PM 2.5 For better prediction of future concentrations, PM at ground monitoring stations in Beijing 2.5 concentration data as an example.

[0049] 2. Data selection

[0050] Pollutant ground monitoring stations provide hourly concentrations of six air pollutants, and NOAA weather stations can provide hourly hourly measurements of four meteorological parameters on the ground. Pollutant data includes 6 main pollutants, namely PM 10 , PM 2.5 , SO 2 , NO 2 , CO, O 3 , meteorological parameters include four kinds of PM 2.5 The species that have a greater impact on concentration are temperature T, dew point ...

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 a method for predicting 24-hour PM2.5 concentration based on a deep neural network. In order to solve the problem of large PM2.5 long-term concentration prediction error at present, a CEEMD decomposition method and an AE-BILSTM stacked deep neural network model are combined to construct a novel hybrid prediction model to realize short-term accurate prediction of PM2.5 concentration and simulation of long-term concentration trend. At present, a deep neural network model is widely applied and shows good performance; the advantage of extracting time series data change features based on the empirical mode decomposition method is gradually highlighted, and the combination of the two can bring a better prediction result.

Description

technical field [0001] The invention relates to the technical field of air pollutant prediction, in particular to PM 2.5 Trend prediction of future concentration. Background technique [0002] In recent years, with the rapid development of the economy and the intensification of urbanization, the number of car ownership has continued to increase, PM 2.5 The concentration also increased accordingly. PM 2.5 It will cause great harm to the human respiratory system and cardiovascular system, especially when its concentration exceeds 115μg / m 3 Case. In addition, the ecological environment will also be affected by high concentrations of PM 2.5 of damage, therefore, establishing an effective predictor of PM 2.5 Systems and methods for future trends in concentration methods are critical. [0003] Currently, available for PM 2.5 The technology and method of concentration prediction can be roughly classified into two categories: deterministic technology and statistical model. ...

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): G06F30/27G06N3/04G06N3/08
Inventor 李四维滕梦凡杨洁宋戈
Owner WUHAN 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