Lavender hydrosol analysis using UV spectroscopy data and partial least squares regression

Abstract

The aim of our work was to estimate the composition of hydrosol produced as a byproduct of lavender steam distillation using UV–Vis spectrophotometry in the 200–600 nm wavelength range through a machine learning algorithm. The dissolved components of lavender essential oil (EO) from lavender hydrosol samples were extracted via liquid-liquid extraction, using three different solvents (pentane, heptane and diethyl ether). The UV–Vis absorbance spectra of the extracts were recorded and the composition analyzed using GC–MS. The composition data obtained allowed for the calculation of changes within the quantities of different EO components in the samples.

The partial least squares regression technique (PLS) was utilized to establish a connection between changes in the composition of the hydrosol and the changes in the UV–Vis spectra. After optimization the established PLS model showed an $R^2$ score above 0.95 for the prediction of hydrosol composition changes during cross-validation. The model can thus be utilized as a soft sensor to infer extracted mass of EO components and characterize the composition of hydrosol during the process directly from UV–Vis spectra.

• •
  Investigation of lavender water and extract using UV–Vis spectrophotometry
• •
  GC–MS analysis of extracts
• •
  PLS model development for composition estimation based on spectra