NIR Instruments and Prediction Methods for Rapid Access to Grain Protein Content in Multiple Cereals

Abstract

Achieving global goals for sustainable nutrition, health, and wellbeing will depend on delivering enhanced diets to humankind. This will require instantaneous access to information on food-source quality at key points of agri-food systems. Although laboratory analysis and benchtop NIR spectrometers are regularly used to quantify grain quality, these do not suit all end users, for example, stakeholders in decentralized agri-food chains that are typical in emerging economies. Therefore, we explored benchtop and portable NIR instruments, and the methods that might aid these particular end uses. For this purpose, we generated NIR spectra for 328 grain samples from multiple cereals (finger millet, foxtail millet, maize, pearl millet, and sorghum) with a standard benchtop NIR spectrometer (DS2500, FOSS) and a novel portable NIR-based instrument (HL-EVT5, Hone). We explored classical deterministic methods (via winISI, FOSS), novel machine learning (ML)-driven methods (via Hone Create, Hone), and a convolutional neural network (CNN)-based method for building the calibrations to predict grain protein out of the NIR spectra. All of the tested methods enabled us to build relevant calibrations out of both types of spectra (i.e., R2 ≥ 0.90, RMSE ≤ 0.91, RPD ≥ 3.08). Generally, the calibration methods integrating the ML techniques tended to enhance the prediction capacity of the model. We also documented that the prediction of grain protein content based on the NIR spectra generated using the novel portable instrument (HL-EVT5, Hone) was highly relevant for quantitative protein predictions (R2 = 0.91, RMSE = 0.97, RPD = 3.48). Thus, the presented findings lay the foundations for the expanded use of NIR spectroscopy in agricultural research, development, and trade.

Germplasm variability-assisted near infrared reflectance spectroscopy chemometrics to develop multi-trait robust prediction models in rice

“…Apart from high RSQ values, RPD value also governs the prediction accuracy of the models. RPD is defined as the ratio of prediction to standard deviation of reference values, where RPD < 1.0 indicates very poor model/predictions with no recommended use; RPD between 1.0 and 1.4 indicates poor predictions where only high and low values are distinguishable; RPD between 1.4 and 1.8 indicates fair predictions which may be used for assessment and correlation; RPD values between 1.8 and 2.0 indicates good predictions where quantitative predictions are possible; RPD between 2.0 and 2.5 indicates very good, quantitative predictions, and RPD > 2.5 indicates excellent predictions ( 36 ). Our results exhibited RPD value > 2 for each trait as for starch (2.12), amylose (2.36), and oil (2.39) indicating their usability in screening large collections and quantitative predictions.…”

Prediction of functional characteristics of gari (cassava flakes) using near-infrared reflectance spectrometry

“…Smaller RMSEs indicate better model fitting. RPD values between 1.8 and 2.0 is good for quantitative predictions; whereas RPD between 2.0 and 2.5 implies very good and, RPD >2.5 indicates an excellent prediction ( Chadalavada et al, 2022 ).…”

Research Advances in Plant Protein-Based Products: Protein Sources, Processing Technology, and Food Applications

“…Cereals, widely cultivated in numerous countries, form a staple part of the daily diet, providing various essential nutrients . The protein content in cereals predominantly resides in the endosperm, typically ranging from 6% to 20% . There are obvious differences in content and composition of proteins among different types of cereal proteins, resulting in diverse nutritional and processing properties of cereal proteins.…”