Spatial Estimation of Regional PM2.5 Concentrations with GWR Models Using PCA and RBF Interpolation Optimization

Abstract

In recent years, geographically weighted regression (GWR) models have been widely used to address the spatial heterogeneity and spatial autocorrelation of PM2.5, but these studies have not fully considered the effects of all potential variables on PM2.5 variation and have rarely optimized the models for residuals. Therefore, we first propose a modified GWR model based on principal component analysis (PCA-GWR), then introduce five different spatial interpolation methods of radial basis functions to correct the residuals of the PCA-GWR model, and finally construct five combinations of residual correction models to estimate regional PM2.5 concentrations. The results show that (1) the PCA-GWR model can fully consider the contributions of all potential explanatory variables to estimate PM2.5 concentrations and minimize the multicollinearity among explanatory variables, and the PM2.5 estimation accuracy and the fitting effect of the PCA-GWR model are better than the original GWR model. (2) All five residual correction combination models can better achieve the residual correction optimization of the PCA-GWR model, among which the PCA-GWR model corrected by Multiquadric Spline (MS) residual interpolation (PCA-GWRMS) has the most obvious accuracy improvement and more stable generalizability at different time scales. Therefore, the residual correction of PCA-GWR models using spatial interpolation methods is effective and feasible, and the results can provide references for regional PM2.5 spatial estimation and spatiotemporal mapping. (3) The PM2.5 concentrations in the study area are high in winter months (January, February, December) and low in summer months (June, July, August), and spatially, PM2.5 concentrations show a distribution of high north and low south.

Estimation of PM2.5 Concentration across China Based on Multi-Source Remote Sensing Data and Machine Learning Methods

“…However, the complex temporal and spatial distribution of PM 2.5 and the diversity of influencing factors limit the accuracy of simple linear regression models. Therefore, scholars have gradually added factors such as meteorological and land-related factors, leading to the development of multivariate regression models, such as the mixed-effects model [12], two-stage model [13,14], geographically weighted regression model [15,16], and geographically and temporally weighted regression model [17][18][19]. These models have further improved the accuracy of PM 2.5 concentration retrieval by incorporating multiple factors and considering their spatial and temporal variations.…”

Synergistic Evolution of PM2.5 and O3 Concentrations: Evidence from Environmental Kuznets Curve Tests in the Yellow River Basin

“…In terms of factors, the main focus is on natural factors-ranging from precipitation [35], vegetation [36], wind speed [37], and per capita GDP [30] to urbanization [38], digital economy [39,40], and other socio-economic factors-to analyze their effects on air pollutant concentrations. The specific factor research methods include GWR [41], machine learning [23,42], GeoDetector [43], and spatial metrics [44].…”

A Novel Flexible Geographically Weighted Neural Network for High-Precision PM2.5 Mapping across the Contiguous United States

“…The accuracy of these methods is constrained by the number of monitoring stations, remote sensing data resolution, and model quality [26], and a comprehensive approach incorporating multiple data sources and methods is often necessary to enhance inversion accuracy. However, the reality is that traditional spatial statistical tools tend to focus on detecting spatial relationships in sample data [27], and when the spatial density and uniformity of sampling points are insufficient, the estimation accuracy and confidence significantly decrease [28]. The air quality products derived from ground-based stations can solve these problems.…”