An Exploratory Approach Using Regression and Machine Learning in the Analysis of Mass Absorption Cross Section of Black Carbon Aerosols: Model Development and Evaluation

• Main Authors: Hanyang Li, Andrew A. May
• Format: Article
• Language: English
• Published: MDPI AG 2020-11-01
• Series: Atmosphere
• Subjects: black carbon; mass absorption cross section (MAC); aerosol light absorption; machine learning; deep learning
• Online Access: https://www.mdpi.com/2073-4433/11/11/1185

Mass absorption cross-section of black carbon (MAC_BC) describes the absorptive cross-section per unit mass of black carbon, and is, thus, an essential parameter to estimate the radiative forcing of black carbon. Many studies have sought to estimate MAC_BC from a theoretical perspective, but these studies require the knowledge of a set of aerosol properties, which are difficult and/or labor-intensive to measure. We therefore investigate the ability of seven data analytical approaches (including different multivariate regressions, support vector machine, and neural networks) in predicting MAC_BC for both ambient and biomass burning measurements. Our model utilizes multi-wavelength light absorption and scattering as well as the aerosol size distributions as input variables to predict MAC_BC across different wavelengths. We assessed the applicability of the proposed approaches in estimating MAC_BC using different statistical metrics (such as coefficient of determination (R²), mean square error (MSE), fractional error, and fractional bias). Overall, the approaches used in this study can estimate MAC_BC appropriately, but the prediction performance varies across approaches and atmospheric environments. Based on an uncertainty evaluation of our models and the empirical and theoretical approaches to predict MAC_BC, we preliminarily put forth support vector machine (SVM) as a recommended data analytical technique for use. We provide an operational tool built with the approaches presented in this paper to facilitate this procedure for future users.