Towards retrieving aerosol chemical composition from temporal variations of total PM mass concentrations: Theoretical approach, insights, and the promise of machine learning techniques
Journal of Research in Atmospheric Science (JRAS) · 2023
DOI: 10.29228/resatmsci.71191 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Research in Atmospheric Science (JRAS), 2023. Verfasst von Danish Ansari und 2 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref).
Abstract (Originalsprache)
Fine and ultrafine ambient particulate matter (PM) has major health and climate impacts. Chemical composition of PM is requiredfor better estimation of these impacts but is considerably expensive to measure as compared to the measurement of only the totalPM mass concentrations. We discuss the theoretical possibility of indirect estimation of PM chemical composition by analysingthe temporal variation of, relatively inexpensively measured, total PM mass concentrations. We highlight the peculiarities of thetemporal characteristics of primary versus secondary aerosols which can become the basis for a machine learning-assistedestimation of chemical fractions at a given time if PM mass concentration time-series of preceding few hours is supplied as input.We also analyse a publicly available chemical composition dataset to show the inter-relationships between different chemicalcomponents which can further assist machine learning algorithms to optimise the chemical fraction estimates.
Zitieren
APA
Ansari, D., Verma, P., & Ansari, T. (2023). Towards retrieving aerosol chemical composition from temporal variations of total PM mass concentrations: Theoretical approach, insights, and the promise of machine learning techniques. Journal of Research in Atmospheric Science (JRAS). https://doi.org/10.29228/resatmsci.71191
Vancouver
Ansari D, Verma P, Ansari T. Towards retrieving aerosol chemical composition from temporal variations of total PM mass concentrations: Theoretical approach, insights, and the promise of machine learning techniques. Journal of Research in Atmospheric Science (JRAS). 2023. doi:10.29228/resatmsci.71191
BibTeX
@article{Ansari2023,
author = {Ansari, Danish and Verma, Prateek and Ansari, Tabish},
title = {Towards retrieving aerosol chemical composition from temporal variations of total PM mass concentrations: Theoretical approach, insights, and the promise of machine learning techniques},
journal = {Journal of Research in Atmospheric Science (JRAS)},
year = {2023},
doi = {10.29228/resatmsci.71191}
}
EUVIMED