Multiblock PLS as an approach to compare and combine NIR and MIR spectra in calibrations of soybean flour

Abstract

The present work is aimed at investigating the potential benefits of simultaneously combining near-infrared (NIR) and mid-infrared (MIR) spectral regions for use in calibration development of soybean flour quality properties (crude protein and moisture). NIR and MIR spectra were analysed separately using single partial least squares (PLS), and then both spectral data sets were utilized together in the modelling by applying two multiblock methodologies based on PLS regression: Multiblock PLS (MB-PLS) and Serial PLS (S-PLS). Utilizing the concept of net analyte signal (NAS), models constructed from NIR or MIR data were compared in terms of analytical figures of merit (sensitivity (SEN), selectivity (SEL) and limit of detection (LOD)). When utilized alone, the MIR spectra gave models with considerably inferior prediction power and analytical figures of merit than NIR-based models. The multiblock methodology revealed to be very useful, since it helped to determine if there was distinctive information in each spectral data set and evaluate the relative importance of each data set. The results pointed out the existence of additional information in the MIR spectra not present in the NIR spectra. Although several works have already been reported comparing NIR and MIR spectroscopic techniques using different multivariate regression techniques, at the best of our knowledge none of them applied the approach of multiblock PLS. Therefore, the present work intends to explore this direction, using the NIR and MIR spectra as predictor blocks to model flour's properties in a parallel mode (MB-PLS) or in a serial mode (S-PLS).