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

Near-surface nitrogen dioxide concentration estimation method based on Stacking integrated model

An integrated model and near-ground technology, applied in genetic models, calculation models, calculations, etc., to achieve the effect of improving overall performance and optimizing input

Pending Publication Date: 2021-06-01
HENAN UNIVERSITY
View PDF6 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, there is no report on the application of the ensemble learning model optimized by the genetic algorithm to gas concentration estimation

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
  • Near-surface nitrogen dioxide concentration estimation method based on Stacking integrated model
  • Near-surface nitrogen dioxide concentration estimation method based on Stacking integrated model
  • Near-surface nitrogen dioxide concentration estimation method based on Stacking integrated model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0031] S1, get the actual NO of the monitoring site 2 Concentration data, meteorological monitoring data, geographic data and population data.

[0032] The actual NO of the monitoring station of the present invention 2 The concentration data comes from the National Environmental Monitoring Center, using the NO of 107 stations in Henan Province in 2019 from the National Environmental Monitoring Center. 2 Mass concentration data, station distribution as figure 1 shown. NO measured at environmental monitoring points 2 Mass concentration in μg / m 3 Indicates that the monitoring period is 1 hour. The transit time of the satellite is about 13:00 local time, and the average value of the observation data of the ground station at the environmental monitoring point from 13:00 to 14:00 is selected as the daily average value.

[0033]The meteorological detection data of the present invention come from the fifth generation reanalysis data (ECMWF Reanalysis v5, ERA5) of the European Ce...

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 belongs to the technical field of remote sensing data application technology, and relates to a near-surface nitrogen dioxide concentration estimation method based on a Stacking integrated model, which comprises the following steps: acquiring actual NO2 concentration data, meteorological monitoring data, geographic data and population data of a monitoring station; acquiring satellite remote sensing data of NO2 troposphere column concentration and verifying the satellite remote sensing data; performing data cleaning, averaging actual NO2 concentration data of a monitoring station and NO2 troposphere column concentration satellite remote sensing data in a gridding mode and matched with meteorological monitoring data, and constructing an NO2 data set; performing modeling based on the NO2 data set, three models of GA-RF, GA-GBRT and GA-XGBoost are adopted as base learners, ridge regression is adopted as a meta learner for fusion, and obtaining a Stacking integrated model; and carrying out simulation estimation on the near-surface NO2 concentration by utilizing the Stacking integrated model to obtain the near-surface NO2 concentration. Through the combination of various machine learning algorithms, the defects of a single model are overcome, the input of linear regression is optimized, and the overall performance of the model is improved.

Description

technical field [0001] The invention belongs to the technical field of remote sensing data application technology, and relates to a method for estimating the concentration of nitrogen dioxide near the ground based on a Stacking integrated model. Background technique [0002] NO 2 It is an important pollutant in the atmosphere, related to photochemical smog, acid deposition and changes in atmospheric ozone, causing damage to water bodies, soil and the atmosphere. NO 2 not only O 3 , PAN and other important precursors of photochemical pollutants, and can also generate NO through photochemical reactions 3 , forming acid deposition, seriously endangering the atmosphere and ecological environment. NO 2 The natural sources of emissions mainly include natural processes such as lightning, soil emissions, and natural combustion of biomass; fossil fuel combustion and vehicle exhaust emissions are NO 2 The main source of emissions is man-made sources, which account for 2 / 3 of emi...

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): G06K9/62G06N3/12G06N20/00G01N33/00
CPCG06N20/00G06N3/126G01N33/0037G06F18/214
Inventor 蔡坤李莘莘刘扬夏禹张旭升
Owner HENAN UNIVERSITY
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