Explore the vast range of titles available.

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.

Amaranth and buckwheat are two pseudo-cereals preferred for their high nutritional value, are gluten free and carry religious importance as fasting food. Germplasm resources are the reservoir of diversity for different traits, including nutritional characteristics. These resources must be evaluated to utilize their potential in crop improvement programs. However, conventional methods are labor-, cost- and time-intensive and prone to handling errors when applied to large samples. NIRS-based machine learning to predict different nutritional traits is applied in different food crops for multiple traits. NIRS prediction models are developed in this study using the mPLS regression technique for oil, protein, fatty acids and essential amino acid estimation in amaranth and buckwheat. Good RSQ external (power of determination) values were obtained for the above traits ranging from 0.72 to 0.929. Ratio performance deviation (RPD) value for most of the traits ranged between 2 and 3, except for valine (1.88) and methionine (3.55), indicating good prediction capabilities in the developed model. These prediction models were utilized in screening the germplasm of amaranth and buckwheat; the results obtained were in good agreement and confirmed the applicability of developed models. It will enable the identification of a trait-specific germplasm as a potential gene source and aid in crop improvement programs.