A Meta-Analysis and Systematic Review of Integrating Satellite-Derived Aerosol Optical Depth Data with Machine Learning for Estimating Fine Particulate Matter (PM2.5) Concentrations

Document Type : Review Article

Authors

• Rasool Taherian Esfahani ¹
• Mehdi Ghanbarzadeh Lak ²

¹ Civil Engineering Department, Faculty of ​Engineering, Urmia University, Urmia, Iran

² School of Engineering, Civil Engineering Department; Urmia University

10.22067/geoeh.2024.88696.1497

Abstract

Exposure to fine particulate matter (PM2.5) significantly impacts public health, particularly in regions where annual average levels of PM2.5 exceed the World Health Organization (WHO) guidelines. According to literature, in Iran, elevated fine particulate matter levels contribute substantially to mortality among adults. The spatial coverage limitations and intermittent data gaps of ground fine particulate matter monitoring stations pose challenges for effective air quality management. The products of remote sensing technologies, such as Aerosol Optical Depth (AOD) from moderate resolution imaging spectroradiometer (MODIS) sensors, offer a promising alternative for fine particulate matter estimation. This study reviews previous research on using machine learning algorithms to predict fine particulate matter ground concentrations based on aerosol optical depth data. A structured analysis of 127 selected studies reveals varying correlations between aerosol optical depth and fine particulate matter (i.e., the resultant coefficient of determination, R2, between ground fine particulate matter concentrations and aerosol optical depth data ranging from 48 to 99 percent), influenced by auxiliary variables like meteorological conditions and environmental factors. Integrating these variables enhances prediction accuracy, though increasing complexity and potential errors in machine learning models. The hybrid machine learning models demonstrate superior performance compared to the individual algorithms, leveraging their adaptability, parallel processing capabilities, and handling of missing data. Despite advancements, challenges persist due to data uncertainty and meteorological dynamics. In conclusion, while machine learning offers robust tools for fine particulate matter forecasting using aerosol optical depth data, ongoing research is essential to address existing limitations and optimize model performance amidst environmental variability.

Keywords

• Ambient Air Pollution
• PM2.5
• AOD
• Machine Learning Algorithm
• PRISMA

Main Subjects

• Micro pollen

---