Estimation of particulate matter concentrations in Türkiye using a random forest model based on satellite AOD retrievals

• Published in: Stochastic environmental research and risk assessment Vol. 37; no. 9; pp. 3469 - 3491
• Main Authors: Tuna Tuygun, Gizem, Elbir, Tolga
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.09.2023; Springer Nature B.V
• Subjects: Aerosols; Air monitoring; Air quality; Aquatic Pollution; Bias; Chemistry and Earth Sciences; Coastal zone; Computational Intelligence; Computer Science; Correlation coefficient; Correlation coefficients; Earth and Environmental Science; Earth Sciences; Environment; Environmental monitoring; Math. Appl. in Environmental Science; Mathematical models; Meteorological data; MODIS; Optical analysis; Optical thickness; Original Paper; Parameters; Particulate emissions; Particulate matter; Physics; Probability Theory and Stochastic Processes; Root-mean-square errors; Spectroradiometers; Statistics for Engineering; Waste Water Technology; Water Management; Water Pollution Control; Turkey; estimation; Random forest; Bias analysis; PM; Türkiye; MODIS AOD
• ISSN: 1436-3240; 1436-3259
• DOI: 10.1007/s00477-023-02459-4

This study estimates intra-daily PM 10 concentrations at 213 inland and coastal monitoring sites in Türkiye from 2008 to 2019 using satellite-based aerosol optical depth (AOD) from the Moderate Resolution Imaging Spectroradiometer (MODIS). An estimation model based on the random forest (RF) approach was developed using the AOD data from the Terra satellite, the meteorological data, and aerosol diagnostics from the Modern-Era Retrospective analysis for Research and Applications, version 2 (MERRA-2), and other auxiliary variables. First, the correlation between the matched PM 10 concentrations and MODIS AOD was investigated simply with the quadrant regression (QR) approach. Next, the feature selection procedure was applied to obtain the most significant predictive variables for the estimation model. Then, the spatial and temporal performances of the developed RF model were intensely discussed. Finally, a bias analysis based on the most influential input parameters was also performed to examine the potential errors in the estimated PM 10 concentrations. As a result, the RF model showed moderately good performance, with a correlation coefficient (R) of 0.72 and low root mean square error (RMSE) over the entire country, which was better than the results of previous studies in the region. Moreover, the model better estimated PM 10 concentrations at individual monitoring sites (with R up to 0.90), particularly in coastal regions. However, overfitting occurred in areas with low populations and few monitoring stations. Additionally, the RF model’s performance varied slightly across different seasons, such as autumn (R ≅ 0.69), spring (R ≅ 0.65), winter (R ≅ 0.64), and summer (R ≅ 0.60), and it did not adequately estimate intra-daily PM 10 concentrations at the seasonal scale. Furthermore, the bias analyses indicated that higher PM 10 and dust mass concentrations, u and v wind components were significant parameters that caused bias in the estimations. Finally, this study provides valuable information for further applications in PM 10 patterns and represents the first step toward constructing a high-resolution satellite-based air quality monitoring network in Türkiye.