Effect of spectral Pre-processing mMethods on developed models for nondestructive prediction of sugar content in Sugar Beet and design of a detection system based on Vis/NIR spectroscopy

In this study, the ability of the near infrared interactance (NIR) spectrometry for nondestructive assessment and prediction of the sugar content of the roots of sugar beet were studied. Additionally, the effect of spectral pre-processing methods on the accuracy of multivariate predictor models was assessed. In this regard, the spectrometry of sugar beet samples was performed in the interactance measurement mode within the spectral range of 350-2500 nm using a contact probe. For this purpose, at first skin spectroscopy was performed in 3 desired areas and then the samples were cut vertically and finally spectroscopy was performed in these three areas. The results show that spectroscopy could be used to measure the amount of sugar in beets. Regions of the main absorbance peaks on NIR spectra of the intact and peeled sugar beets were the same. Therefore, the effect of chemical compounds of sugar beet skin can be ignored to identify internal compounds with nondestructive NIR spectroscopy. Additionally, sugar content of the product can be measured without the need to cut it. Prediction of the sugar content of intact samples with the PLS model based on SG + D2, is the the most accurate prediction method. Thus, SG+D2 preprocessing (rc =0.87, RMSEC = 0.90, rp = 0.95, RMSEP = 0.55) is suitable for predicting the amount of SC with the highes accuracy rate (SDR= 3.20). Finally, a system was designed based on the developed model with the ability to measure the grade of the product in a nondestructive way. This system can be used to process the facilities of sugar beet as well as research on breeding of sugar beet in breeding Institutes.