PM2.5 inversion method based on MODIS and machine learning model fusion

Abstract

The invention relates to the technical field of remote sensing image processing, in particular to a PM2.5 inversion method based on MODIS and machine learning model fusion. An MODIS image and PM2.5 monitoring data are acquired; the PM2.5 data are interpolated into PM2.5 interpolation image; the MODIS image is subjected to cloud detection; a training set and a test set are constructed; performanceindicators are calculated according to the training set and the test set; a histogram of the performance indicators is made; all corresponding models in a histogram interval with the highest frequencyin the histogram are selected and taken as the optimal model combination; the optimal model combination is used for the full MODIS image for inversion of model fusion. In the method, the relation between the remote sensing image and actually measured PM2.5 is directly constructed on the basis of data of the remote sensing image through a machine learning algorithm and model fusion, so that the inversion result with higher accuracy is realized. Error transferring is avoided and the inversion accuracy is high.

Description

technical field [0001] The invention relates to the technical field of remote sensing image processing, in particular to a PM2.5 inversion method based on fusion of MODIS and machine learning models. Background technique [0002] Aerosol, also known as aerosol or smog, refers to a dispersion system formed by solid or liquid particles stably suspended in a gas medium, and its general size is between 0.01-10 microns, which can be divided into two types: natural and human-generated; Aerosols can affect the climate, including absorbing radiation or scattering radiation, and aerosols can become condensation nuclei and affect the properties of clouds, etc. Clouds, fog, and dust in the sky, smoke from unburned fuel in boilers and various engines used in industry and transportation, solid dust from mining, quarry grinding, and grain processing, Man-made masking smoke and toxic smoke are specific examples of aerosols. The elimination of aerosols mainly depends on the process of atm...

AI Technical Summary

Problems solved by technology

[0004] The current monitoring methods are the establishment of ground-based observation stations, such as the Global Automatic Observation Network (AER ONET), the US Environmental Visual Monitoring Station (IMPROVE), and the US Environmental Protection Agency's nearly 4,000 air observation stations (SLAMS), which can detect aerosols. Continuous observation can directly reflect the ground concentration information of pollutants, but the sparseness and discontinuity of ground environmental observation stations make it difficult to reflect the temporal and spatial distribution, pollution sources and transmission characteristics of PM2.5 aerosol particles on a large scale. Expensive instruments restrict the effective monitoring and macro analysis of PM2.5; more advanced monitoring now uses the inversion of PM2.5 for monitoring and analysis, and the inversion of PM2.5 refers to the inversion of its mass concentration. The inversion method of PM2.5 is to invert the atmospheric aerosol optical depth AOD first, then establish the statistical relationship between the aerosol optical depth AOD and the ground measured PM2.5, and then use the statistical relationship to obtain the non-ground observation point The PM2.5 value in the area will bring errors in the process of retrieving AOD, and then use AOD to establish the process of measuring PM2.5, which will lead to the transmission of errors, thus affecting the final PM2.5 inversion accuracy

Images