Estimation of pmx concentrations from landsat 8 oli images based on a multilayer perceptron neural network

The estimation of PM_x (incl. PM₁₀ and PM_2.5 ) concentrations using satellite observations is of great significance for detecting environmental issues in many urban areas of north China. Recently, aerosol optical depth (AOD) data have been being used to estimate the PM_x concentrations by implementing linear and/or nonlinear regression analysis methods. However, a lot of relevant research based on AOD published so far have demonstrated some limitations in estimating the spatial distribution of PM_x concentrations with respect to estimation accuracy and spatial resolution. In this research, the Google Earth Engine (GEE) platform is employed to obtain the band reflectance (BR) data of a large number of Landsat 8 Operational Land Imager (OLI) remote sensing images. Combined with the meteorological, time parameter and the latitude and longitude zone (LLZ) method proposed in this article, a new BR (band reflectance)-PM_x (incl. PM₁₀ and PM_2.5 ) model based on a multilayer perceptron neural network is constructed for the estimation of PM_x concentrations directly from Landsat 8 OLI remote sensing images. This research used Beijing, China as the test area and the conducted experiments demonstrated that the BR-PM_x model achieved satisfactory performances for the PM_x-concentration estimations. The coefficient of determination (R² ) of the BR-PM_2.5 and BR-PM₁₀ models reached 0.795 and 0.773, respectively, and the root mean square error (RMSE) reached 20.09 µg/m³ and 31.27 µg/m³ . Meanwhile, the estimation results have been compared with the results calculated by Kriging interpolation at the same time point, and the spatial distribution is consistent. Therefore, it can be concluded that the proposed BR-PM_x model provides a new promising method for acquiring accurate PM_x concentrations for various cities of China.