Mapping and Understanding Patterns of Air Quality Using Satellite Data and Machine Learning

Abstract

The quantification of factors leading to harmfully high levels of particulate matter (PM) remains challenging. This study presents a novel approach using a statistical model that is trained to predict hourly concentrations of particles smaller than 10 μm (PM10) by combining satellite‐borne aerosol optical depth (AOD) with meteorological and land‐use parameters. The model is shown to accurately predict PM10 (overall R 2 = 0.77, RMSE = 7.44 μg/m 3) for measurement sites in Germany. The capability of satellite observations to map and monitor surface air pollution is assessed by investigating the relationship between AOD and PM10 in the same modeling setup. Sensitivity analyses show that important drivers of modeled PM10 include multiday mean wind flow, boundary layer height (BLH), day of year (DOY), and temperature. Different mechanisms associated with elevated PM10 concentrations are identified in winter and summer. In winter, mean predictions of PM10 concentrations >35 μg/m 3 occur when BLH is below ∼500 m. Paired with multiday easterly wind flow, mean model predictions surpass 40 μg/m 3 of PM10. In summer, PM10 concentrations seemingly are less driven by meteorology, but by emission or chemical particle formation processes, which are not included in the model. The relationship between AOD and predicted PM10 concentrations depends to a large extent on ambient meteorological conditions. Results suggest that AOD can be used to assess air quality at ground level in a machine learning approach linking it with meteorological conditions.

Exploring Environmental Health Inequalities: A Scientometric Analysis of Global Research Trends (1970–2020)

“…The convergence of the availability of these new data sources, GIS, image processing techniques, and statistical algorithms creates a fertile research environment for EHI studies. Therefore, incorporating indicators derived from new data source into addressing EHI issues could effectively supplement data on some contextual factors and behavioral information for certain environmental exposures, and, thus, allow a more objective and comprehensive understanding on environmental inequality [ 102 , 103 , 104 , 105 , 106 , 107 , 108 ].…”

Attribution of Observed Recent Decrease in Low Clouds Over the Northeastern Pacific to Cloud‐Controlling Factors

“…To compare the traditionally used ordinary least squares regression (OLS) (Cesana & Del Genio, 2021;Klein et al, 2017;McCoy et al, 2017;Myers & Norris, 2016;Myers et al, 2021;Scott et al, 2020) and machine learning techniques that have gained relevance in the field lately, artificial neural networks (ANNs; Andersen et al, 2017) and extreme gradient boosting (XGB; Chen & Guestrin, 2016) are used. XGB is a gradient tree boosting method similar to the popular gradient boosting regression trees (GBRTs) that have been used in many aerosol and cloud related studies recently (Andersen et al, 2021;Dadashazar et al, 2020Dadashazar et al, , 2021Fuchs et al, 2018;Stirnberg et al, 2020Stirnberg et al, , 2021, with the advantages of a built-in regularization techniques and much shorter run times (Chen & Guestrin, 2016).…”

A Machine Learning Methodology for the Generation of a Parameterization of the Hydroxyl Radical: a Tool to Improve Computational-Efficiency in Chemistry Climate Models

“…A variety of machine learning techniques, such as neural networks (Nicely et al, 2017;Nicely et al, 2020;Kelp et al, 2020), random forest regression (Keller and Evans, 2019), and gradient boosted regression trees (GBRTs) (Ivatt and Evans, 2020;Stirnberg et al, 2020) show promise for use in new, efficient methods to generate parameterizations of OH as these techniques have been successfully used in atmospheric chemistry applications. In particular, GBRT models (Elith et al, 2008;Chen and Guestrin, 2016) use an ensemble of decision trees to predict the value of a target based on multiple inputs.…”

“…Decision trees are created sequentially, with each new tree minimizing a cost function based on the results of the previous tree (Elith et al, 2008;Stirnberg et al, 2020). Unlike other machine learning algorithms, regression tree methods have easily interpretable metrics that help highlight the influence of the different input variables (Yan et al, 2016).…”