Estimating PM2.5 Concentrations in Contiguous Eastern Coastal Zone of China Using MODIS AOD and a Two-Stage Random Forest Model

Abstract

The coarse moderate-resolution imaging spectroradiometer (MODIS) aerosol optical depth (AOD) product (spatial resolution: 3 km) retrieved by dark-target algorithm always generates the missing values when being adopted to estimate the ground-level PM2.5 concentrations. In this study, we developed a two-stage random forest using MODIS 3 km AOD to obtain the PM2.5 concentrations with full-coverage in a contiguous coastal developed region, i.e., Yangtze River Delta-Fujian-Pearl River Delta region of China (YRD-FJ-PRD). A first-stage random forest integrated six meteorological fields was employed to predict the missing values of AOD product, and the combined AOD (i.e., random forest derived AOD and MODIS 3 km AOD) incorporated with other ancillary variables were developed for predicting PM2.5 concentrations within a second-stage random forest model. The results showed that the first-stage random forest could explain 94% of the AOD variability over YRD-FJ-PRD region, and we achieved a site-based cross validation (CV) R2 of 0.87 and a time-based CV R2 of 0.85, respectively. The full-coverage PM2.5 concentrations illustrated a spatial pattern with annual-mean PM2.5 of 46, 40 and 35 μg/m3 in YRD, PRD and FJ, respectively, sharing the same trend with previous studies. Our results indicated that the proposed two-stage random forest model could be effectively used for PM2.5 estimation in different areas.

Systematic Evaluation of Four Satellite AOD Datasets for Estimating PM2.5 Using a Random Forest Approach

“…These are AOD, BLH, surface pressure, DoY, dewpoint and wind. This is in line with the findings of many other studies such as Wei et al, Chen et [35][36][37][38]73]. Most of these studies also identified RH and temperature as important variables, which we cannot confirm with our results.…”

“…The limited sample size of AOD data can significantly affect the accuracy of PM 2.5 prediction models, and in general, all satellite AOD products suffer from a missing data problem. To address this issue, some studies introduced gap-filling approaches by imputing missing values using external data sources such as simulations from chemical transport models [41,44,45], multi-stage prediction models [37] or by AOD data fusion methods [25,47,75]. However, AOD imputations may introduce systematic and static errors, which will be propagated to PM 2.5 predictions, increasing their uncertainty [76].…”

“…Several studies using RF for AOD-based PM 2.5 estimations were performed for Asia, including different parts of China [28,[35][36][37][38], Thailand [34,39] and Iran [40]; fewer focused on the United States [41][42][43] and Europe, including Italy [44] and Great Britain [45].…”

A random forest algorithm for the prediction of cloud liquid water content from combined CloudSat/CALIPSO observations

“…Simple ML methods, such as linear regression, have been used in satellite retrievals for decades (e.g., Adler and Negri, 1988). More recently, more sophisticated methods which are better able to handle nonlinear relationships between variables have become more common (Hilburn et al, 2020;Hu et al, 2021;Yang et al, 2021;Zhang et al, 2021;Lee et al, 2022;Pfreundschuh et al, 2022;Goldenstern and Kummerow, 2023).…”

“…When making a prediction, the random forest averages the results of all the decision trees in the ensemble. Recently, random forests have been used in atmospheric science to forecast severe weather (Hill et al, 2020), improve radar-based precipitation nowcasts (Mao and Sorteberg, 2020), estimate particulate matter concentrations from satellite observations (Yang et al, 2021), and detect clouds (Haynes et al, 2022), among many other applications.…”