Nitrogen dioxide concentration prediction method and system

A nitrogen dioxide and concentration prediction technology, applied in prediction, design optimization/simulation, instruments, etc., can solve the problems of not considering the influence of space factors, poor portability, and few prediction methods, etc., to achieve wide coverage and ensure transplantation The effect of reducing the prediction residual error

Active Publication Date: 2022-04-01
SHANDONG UNIV
View PDF12 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although there are many methods and applications of machine learning algorithms for air quality prediction, there are few methods for predicting atmospheric nitrogen dioxide concentrations in large-scale regions
The machine learning prediction method based on a small-scale, single data source (pollution data and meteorological data) does not consider the influence of spatial factors in different regions, has poor portability, and is only suitable for air quality prediction in the current region

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
  • Nitrogen dioxide concentration prediction method and system
  • Nitrogen dioxide concentration prediction method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0035] The present embodiment 1 provides a nitrogen dioxide concentration prediction system, which includes:

[0036] The acquisition module is used to acquire monitoring data; the monitoring data includes air pollution monitoring data, meteorological data, remote sensing reanalysis meteorological field data and geographic covariate data;

[0037] The prediction module is used to process the monitoring data respectively by using a pre-trained random forest model, an extreme gradient boosting tree model and a gated recurrent unit neural network model combined with residual connections to obtain three predicted values ​​of nitrogen dioxide concentration ;

[0038] The calculation module is used to calculate and obtain the final nitrogen dioxide concentration value based on the three predicted nitrogen dioxide concentration values ​​and in combination with a weighted average algorithm.

[0039] In this embodiment 1, the above-mentioned nitrogen dioxide concentration prediction s...

Embodiment 2

[0057] In this embodiment 2, a method based on machine learning to predict the short-term NO of an air quality monitoring station in a certain area is provided. 2 Concentration method to achieve large-scale, multi-sequence NO 2 Rapid and accurate concentration prediction solves the problem that the current machine learning prediction method has low portability and cannot be applied to new monitoring stations with little historical data.

[0058] In Example 2, the short-term NO of the air quality monitoring station is predicted based on machine learning 2 Concentration method, the implementation process specifically includes the following steps: Step 1, obtain air pollution monitoring data and auxiliary feature data sets covering a certain area, and obtain multi-source data sets; Step 2, perform long-term multi-source data sets Preprocessing, time and space fusion, using resampling technology to generate data sets with different time resolutions; step 3, based on the fused mul...

Embodiment 3

[0077] In this embodiment 3, a machine learning-based prediction of short-term NO in air quality monitoring stations is provided. 2 Concentration method, the implementation method specifically includes the following steps: Step 1, obtain air pollution monitoring data and auxiliary feature data sets covering the target area; Step 2, perform preprocessing, time and space fusion on long-term multi-source data sets, Use resampling technology to generate data sets with different time resolutions. Step 3, based on the fused multi-source data sets, use feature engineering to extract spatio-temporal information and add them to the data sets and divide training sets and test sets; Step 4, train multi-source data sets based on machine learning Timing NO 2 The model of the relationship with the feature vector, and finally realize the NO of multi-time series in the target area 2 Concentration Prediction.

[0078] The specific calculation is to use z-score standardization to map the orig...

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 provides a nitrogen dioxide concentration prediction method and system, and belongs to the technical field of air quality monitoring, and the method comprises the steps: obtaining monitoring data such as atmospheric pollution monitoring data, meteorological monitoring data, remote sensing reanalysis meteorological field data and geographic covariable data; a pre-trained random forest model, an extreme gradient boosting tree model and a residual connection-combined gated circulation unit neural network model are used for processing monitoring data respectively to obtain three nitrogen dioxide concentration predicted values, and a weighted average algorithm is combined to calculate a final nitrogen dioxide concentration value. According to the method, multi-source spatio-temporal data are fused, and time and space change modes of nitrogen dioxide are learned; the advantages of different algorithms are combined through integrated learning, so that the stability of the prediction result is improved, the prediction residual error is reduced, and the nitrogen dioxide concentration prediction with wide coverage range, high prediction precision and multiple time sequences is realized; the portability of the machine learning prediction method is ensured, and the method can be directly applied to a new monitoring station with less historical data.

Description

technical field [0001] The invention relates to the technical field of air quality monitoring, in particular to a method and system for predicting nitrogen dioxide concentration based on a machine learning algorithm. Background technique [0002] Excessive use of fossil fuels such as coal, oil, and natural gas has made the problem of air pollution more and more serious, causing a series of impacts on people's lives and health. Long-term exposure to air pollution can cause diseases such as respiratory system, cardiovascular disease, and even death. . Therefore, we should attach great importance to the prevention and control of air pollution, and continue to promote refined and scientific prevention and control of the atmospheric environment. Timely prediction and early warning of the concentration of air pollutants can remind people to do preventive work in advance, and help decision makers propose solutions to problems in a timely manner to avoid , Curb the impact of air po...

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): G06F30/27G06N20/20G06Q10/04G06Q50/26
CPCY02A90/10
Inventor 张庆竹汪先锋陶辰亮王桥王文兴
Owner SHANDONG UNIV
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