PM2.5 comprehensive domain space-time calculation inference method based on multi-source city big data

Abstract

The invention relates to the field of atmospheric pollutant space-time distribution calculation, and discloses a fine particulate matter (PM2.5) comprehensive domain space-time calculation inference method based on multi-source city big data. According to the method, PM2.5 concentration data of a fixed station and a sensor, satellite remote sensing aerosol optical thickness and other environment covariants are collected, an iteration vacancy filling-machine learning model is established, and the problems of data heterogeneity, space-time insufficient matching, sampling deviation and the like existing in multi-source data fusion are effectively solved. According to the method, multi-source data of a fixed station, a sensor, satellite remote sensing and the like are flexibly and efficiently fused, high-resolution spatial-temporal distribution of PM2.5 can be more accurately reconstructed, a high-resolution spatial-temporal distribution result of PM2.5 hourly concentration of a 1km grid is formed, the method is an important technical basis for realizing fine management and control of air quality, high potential pollution sources can be explored and positioned in real time, and finally, pollution discharge can be monitored and controlled in a targeted manner.

Description

technical field [0001] The invention relates to the field of calculating the temporal and spatial distribution of atmospheric pollutants, specifically PM based on multi-source urban big data 2.5 A comprehensive domain spatiotemporal computational inference method. Background technique [0002] In recent years, the air quality in most parts of my country has been significantly improved, but the overall pollution level is still high, among which fine particulate matter (PM 2.5 ) is still the primary air pollutant in most areas, mastering PM 2.5 The high-resolution spatio-temporal distribution of atmospheric pollutant concentrations is of great value for fine-grained air quality management. While adding ground monitoring stations, based on multi-dimensional environmental data and machine learning, it is economical and efficient Accurately obtain the high-precision spatio-temporal distribution of atmospheric pollutant concentrations (such as 1km grid PM 2.5 hourly concentrati...

AI Technical Summary

Problems solved by technology

[0007] In order to achieve the purpose of effectively solving the problems of time-space under-matching and sampling deviation in the fusion of air quality multi-source information, the present invention provides a PM based on multi-source urban big data. 2.5 The comprehensive domain spatio-temporal calculation and inference method, its key iterative filling technology gives full play to the respective advantages of multi-dimensional environmental data, effectively solves the problems of training data spatio-temporal under-matching and sampling deviation, and provides algorithm support for the reconstruction of air pollutant spatio-temporal distribution, " Complementary measurement by calculation" to provide scientific support for refined air quality management

Images