Factors influencing ambient particulate matter in Delhi, India: Insights from machine learning

Abstract

Concentrations of ambient particulate matter (PM) depend on various factors including emissions of primary pollutants, meteorology and chemical transformations. New Delhi, India is the most polluted megacity in the world and routinely experiences extreme pollution episodes. As part of the Delhi Aerosol Supersite study, we measured online continuous PM₁ (particulate matter of size less than 1 μm) concentrations and composition for over five years starting January 2017, using an Aerosol Chemical Speciation Monitor (ACSM). Here, we describe the development and application of machine learning models using random forest regression to estimate the concentrations, composition, sources and dynamics of PM in Delhi. These models estimate PM₁ species concentrations based on meteorological parameters including ambient temperature, relative humidity, planetary boundary layer height, wind speed, wind direction, precipitation, agricultural burning fire counts, solar radiation and cloud cover. We used hour of day, day of week and month of year as proxies for time-dependent emissions (e.g., emissions from traffic during rush hours). We demonstrate the applicability of these models to capture temporal variability of the PM₁ species, to understand the influence of individual factors via sensitivity analyses, and to separate impacts of the COVID-19 lockdowns and associated activity restrictions from impacts of other factors. Our models provide new insights into the factors influencing ambient PM₁ in New Delhi, India, demonstrating the power of machine learning models in atmospheric science applications.

Copyright © 2023 American Association for Aerosol Research

Graphical Abstract

Editor:

• Nicole Riemer

Acknowledgements

We thank Dr. Ann Marie Carlton for fruitful discussions about MODIS cloud data and Dr. Barron Henderson for providing the scripts to extract MODIS cloud data.

Disclosure statement

No potential conflict of interest was reported by the authors.

Additional information

Funding

This manuscript is based on work supported in part by the Welch Foundation under Grants F-1925-20170325 and F-1925-20200401 and the National Science Foundation under Grant 1653625. It is also supported by the University of Austin Cockrell School of Engineering Graduate Continuing Fellowship. We thank the funding agencies for their support.