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

Surface PM2.5 concentration estimation method based on gradient boosting decision-making tree

A decision tree and gradient technology, applied in the direction of measurement devices, suspension and porous material analysis, special data processing applications, etc., can solve problems such as non-stationarity and limitations

Active Publication Date: 2020-12-11
HENAN UNIVERSITY
View PDF3 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to solve the problem of space and time non-stationarity and limitation of sample size when estimating or predicting PM2.5 concentration by using chemical, physical and statistical models, and provides a method based on gradient lifting decision tree surface PM2. 5 Methods for 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
  • Surface PM2.5 concentration estimation method based on gradient boosting decision-making tree
  • Surface PM2.5 concentration estimation method based on gradient boosting decision-making tree
  • Surface PM2.5 concentration estimation method based on gradient boosting decision-making tree

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0068] Specific implementation mode one: the method for estimating the surface PM2.5 concentration based on the gradient lifting decision tree in this implementation mode is carried out according to the following steps:

[0069] 1. Preprocess the PM2.5 concentration data observed on the ground, and obtain the daily, monthly and annual average PM2.5 observed concentration data of each station in the study area;

[0070] 2. Process the remote sensing AOD product data, obtain AOD data with better quality control and expand the spatial coverage of AOD data, and then extract the remote sensing AOD data of corresponding points according to the result data obtained in step 1;

[0071] According to the result data obtained in step 1, the process of extracting the remote sensing AOD data of the corresponding point is as follows:

[0072] a. Utilize the control quality file data of remote sensing AOD product data, select the data that has passed the quality inspection (that is, the data...

specific Embodiment approach 2

[0098] Embodiment 2: This embodiment differs from Embodiment 1 in that the meteorological data in Step 3 is temperature, precipitation or evapotranspiration. Others are the same as the first embodiment.

specific Embodiment approach 3

[0099] Embodiment 3: This embodiment differs from Embodiment 1 or Embodiment 2 in that the auxiliary data described in Step 3 is DEM, NDVI or LUCC. Others are the same as those in Embodiment 1 or 2.

[0100] Adopt following experiment verification effect of the present invention:

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 estimation method, in particular to the surface PM2.5 concentration estimation method based on a gradient boosting decision-making tree. The invention aims at solving the problems that the estimation is limited by space and time non-stationarity, and the sample size when PM2.5 concentration is estimated or predicted through chemical, physical and statistical models. The method comprises the following steps: 1, preprocessing PM2.5 concentration data observed on the ground to obtain average PM2.5 observation concentration data of each station; and 2, processing the remote sensing AOD product data to obtain AOD data with better control quality and expand the space coverage rate of the AOD data. And 3, preprocessing and unifying the meteorologicaldata and the auxiliary data. And 4, integrating the data to ensure that all the data are consistent in space and time. And 5, performing exploratory analysis on the data, so that the problem of colinearity among multiple variables can be eliminated. And 6, constructing a PM2.5 concentration estimation model by using a gradient boosting decision tree method. The invention is suitable for estimating large-range surface PM2.5 concentration spatial distribution from remote sensing AOD data.

Description

technical field [0001] The invention relates to a method for estimating the concentration of PM2.5. Background technique [0002] Fine particulate matter PM2.5 is the main component of air pollutants and has a high degree of concern. Studies have shown that PM2.5 will directly enter the bronchi after being inhaled into the human body, causing diseases including asthma, bronchitis and cardiovascular disease, and affecting human health. In view of the current PM2.5 pollution problem, China needs fine and high-resolution PM2.5 data covering the whole country. [0003] Accurate PM2.5 concentration data is mainly obtained by ground monitoring. However, due to the sparseness of ground monitoring sites, limited monitoring data, and uneven distribution of sites, it is impossible to simulate the temporal and spatial changes of PM2.5 concentration in a large geographical range. Big limitations. Satellite remote sensing images can provide data with a large spatial range, so fitting ...

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): G06F30/20G01N15/06
CPCG06F30/20G01N15/06Y02A90/10
Inventor 郑辉张鹏岩张文李颜颜杨丹何炜欢
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