Quantitative analysis of bisphenol analogue mixtures by terahertz spectroscopy using machine learning method

Quantitative analysis of complex mixtures is a great challenge for spectral analysis. Bisphenol A (BpA) is a chemical predominantly used in manufacturing and is being replaced by other analogs due to its potential toxicity. Reliability methods is hence crucial for identification and quantification of bisphenol mixtures. In this study we present an attractive strategy for composition determination of BpA incorporated in its analogue mixtures. Terahertz spectra of four bisphenol components are analyzed using machine learning method (SVR) to learn the underlying model of the frequency against the target concentration of BpA in mixtures. The learned mode predicts the concentrations of the unknown samples with decision coefficient R2 = 0.98. Absorption spectra for bisphenols mixtures were successfully reconstructed by a hold-out validation scheme. The results indicate the terahertz spectroscopy in combination with SVR is robust and accurate in mixture quantitative analysis and should play a significant role for industrial applications in the future.

Automated summary

This study presents an attractive strategy for determining the composition of BpA in its analog mixtures using machine learning method (SVR) to analyze terahertz spectra. The learned model accurately predicts the concentrations of unknown samples with a decision coefficient R2 of 0.98. The combination of terahertz spectroscopy and SVR is shown to be robust and accurate for quantitative analysis of mixtures, indicating its potential for significant industrial applications in the future.