RESUMO
We have recently developed a low-cost spark-induced breakdown spectroscopy (SIBS) instrument for in-situ analysis of toxic metal aerosol particles that we call TARTA (toxic-metal aerosol real time analyzer). In this work, we applied machine learning methods to improve the quantitative analysis of elemental mass concentrations measured by this instrument. Specifically, we applied least absolute shrinkage and selection operator (LASSO), partial least squares (PLS) regression, principal component regression (PCR), and support vector regression (SVR) to develop multivariate calibration models for 13 metals (e.g., Cr, Cu, Mn, Fe, Zn, Co, Al, K, Be, Hg, Cd, Pb, and Ni), some of which are included on the US EPA hazardous air pollutants (HAPS) list. The calibration performance, adjusted coefficient of determination (R2) and normalized root mean square error (RMSE), and limit of detection (LOD) of the proposed models were compared to those of univariate calibration models for each analyte. Our results suggest that machine learning models tend to have better prediction accuracy and lower LODs than conventional univariate calibration, of which the LASSO approach performs the best with R2 > 0.8 and LODs of 40-170 ng m-3 at a sampling time of 30 min and a flow rate of 15 l min -1. We then assessed the applicability of the LASSO model for quantifying elemental concentrations in mixtures of these metals, serving as independent validation datasets. Ultimately, the LASSO model developed in this work is a very promising machine learning approach for quantifying mass concentration of metals in aerosol particles using TARTA.
RESUMO
To meet the demand for identifying and controlling toxic air contaminants in environmental justice communities, we have recently developed a cost-effective spark-induced breakdown spectroscopy (SIBS) instrument for detecting and quantifying toxic metal air pollutants. We characterized the detection limit and linearity of this SIBS instrument by analyzing nebulized elemental standard solutions. The experimental parameters affecting SIBS performance were optimized, including the time delay to observation, the distance between electrodes, and the ablation voltage. The instrument successfully detected Cr, Cu, Mn, Fe, Zn, Co, and Ni, with limits of detection ranged from 0.05 µg m-3 to 0.81 µg m-3 at a flow rate of 15 l min-1 and a 30 min sampling duration. Similar to other investigations using ion breakdown spectroscopy, we did not observe strong emissions lines for As, Sb, Se, Hg, Pb, and Cd, which were likely due to spectral overlap, matrix effects, and the limited detection range of the optical components. Overall, SIBS is a promising technique for field measurements of toxic metals for environmental justice, industrial and urban applications.