Effects of resolution on quantification in open-path Fourier transform infrared spectrometry under conditions of low detector noise. 2. Partial leastsquares regression
Bk. Hart et al., Effects of resolution on quantification in open-path Fourier transform infrared spectrometry under conditions of low detector noise. 2. Partial leastsquares regression, ENV SCI TEC, 34(7), 2000, pp. 1346-1351
Citations number
5
Categorie Soggetti
Environment/Ecology,"Environmental Engineering & Energy
The effects of resolution, spectral window, and background type on the pred
ictive capability of partial least squares regression (PLS) on spectra meas
ured by an open-path Fourier transform (OP/FT-IR) spectrometer were tested
with spectra of mixtures of alkanes and chlorinated hydrocarbons. The resul
ts were compared with the results obtained with the identical data sets usi
ng classical least squares regression (CLS). It is shown that the most accu
rate predictions are obtained using the same conditions that were optimal f
or CLS, namely spectra measured at low resolution and ratioed to background
spectra over the same path length, with the calculations made over limited
spectral windows. However, good predictions could be achieved with backgro
und spectra measured over a very short: path. Even in the worst cases, the
relative error of predictions made by PLS was usually less than 5%. On aver
age, the predicted concentrations of the components of mixtures containing
up to five chemically similar analytes made using the PLS algorithm are 120
times more accurate than the predicted concentrations of the components of
the identical data sets made using CLS.