Sorghum Grains Grading for Food, Feed, and Fuel Using NIR Spectroscopy

Spectraformer: deep learning model for grain spectral qualitative analysis based on transformer structure

This study delves into the use of compact near-infrared spectroscopy instruments for distinguishing between different varieties of barley, chickpeas, and sorghum, addressing a vital need in agriculture for precise crop variety identification. This identification is crucial for optimizing crop performance in diverse environmental conditions and enhancing food security and agricultural productivity. We also explore the potential application of transformer models in near-infrared spectroscopy and conduct an in-depth evaluation of the impact of data preprocessing and machine learning algorithms on variety classification. In our proposed spectraformer multi-classification model, we successfully differentiated 24 barley varieties, 19 chickpea varieties, and ten sorghum varieties, with the highest accuracy rates reaching 85%, 95%, and 86%, respectively. These results demonstrate that small near-infrared spectroscopy instruments are cost-effective and efficient tools with the potential to advance research in various identification methods, but also underscore the value of transformer models in near-infrared spectroscopy classification. Furthermore, we delve into the discussion of the influence of data preprocessing on the performance of deep learning models compared to traditional machine learning models, providing valuable insights for future research in this field.

Genetic variability among lowland sorghum accessions collected from southern Ethiopia for grain quality traits

The study was carried out to assess the nature and magnitude of genetic variability for grain quality traits in lowland sorghum accessions. Understanding genetic diversity and trait association is crucial to designing an effective breeding plan to develop nutrient-rich varieties. Two hundred twenty-five accessions were evaluated using a simple lattice design with two replications at Weioto. Prepared samples per replication were scanned by mixing the grains and repacking the sample cup after each scan. Analysis of grain quality traits revealed significant (P ≥ 0.01) differences among the genotypes indicating a good chance for genetic improvement. Genotypic means of nutritional content showed that amylose (Am) content ranged from 19.11 to 20.80%, ash value ranged from 0.37 to 3.14%, starch content ranged from 42.29 to 72.77%, and protein (pr) in dry basis ranged from 2.62 to 10.45%. Similarly, iron (Fe) ranged from 1.38 to 73.21 ppm, zinc (Zn) ranged from 16.8 to 66.02 ppm, and tannin content ranged between -0.08 and 9105.21%. Broad-sense heritability (h2b) of all grain quality attributes such as amylose; ash; starch; moisture; iron; zinc; protein, and tannin was in the range of 13-92%. Principal component analysis showed the first three principal components with an eigenvalue equal to or greater than unity adequately explain the variation in the data. Significant positive genetic correlations (P < 0.001) with amylase, starch, iron, and zinc, while tannin had a weak association with grain yield. This result declares/signifies/a good prospect of southern Ethiopia lowland sorghum accessions for genetic improvement in grain yield and quality traits.

High-throughput phenotyping of nutritional quality components in sweet potato roots by near-infrared spectroscopy and chemometrics methods

The lack of an efficient approach for quality evaluation of sweet potatoes significantly hinders progress in quality breeding. Therefore, this study aimed to establish a near-infrared spectroscopy (NIRS) assay for high-throughput analysis of sweet potato root quality, including total starch, amylose, amylopectin, the ratio of amylopectin to amylose, soluble sugar, crude protein, total flavonoid content, and total phenolic content. A total of 125 representative samples were utilized and a dual-optimized strategy (optimization of sample subset partitioning and variable selection) was applied to NIRS modeling. Eight optimal equations were developed with an excellent coefficient of determination for the calibration (R2C) at 0.95-0.99, cross-validation (R2CV) at 0.93-0.98, external validation (R2V) at 0.89-0.96, and the ratio of prediction to deviation (RPD) at 6.33-11.35. Overall, these NIRS models provide a feasible approach for high-throughput analysis of root quality and permit large-scale screening of elite germplasm in future sweet potato breeding.

Detection of amylase activity and moisture content in rice by reflectance spectroscopy combined with spectral data transformation

In this study, reflectance spectroscopy was used to achieve rapid and non-destructive detection of amylase activity and moisture content in rice. Since rice husk can interfere with spectral measurements, spectral data transformation was used to remove the husk interference. Reflectance spectra of rice were transformed by direct standardization, convolutional autoencoder network, and kernel regression (KR). Then, random frog and elliptical envelope were adopted to select effective wavelengths, and partial least squares regression (PLSR) and support vector regression were used to establish analysis models. The optimal transformation was from KR, and PLSR and effective wavelengths of the transformed spectra obtained excellent performance with coefficient of determination of test of 0.6987 and 0.8317 and root-mean-square error of test of 0.3359 and 2.2239, respectively. The result was better than that of the rice spectra and was close to that of the husked rice spectra. When the moisture content was integrated into the regression model of amylase activity, a better result was obtained. Thus, the proposed method can detect amylase activity and moisture content in rice accurately.

Crop Seed Phenomics: Focus on Non-Destructive Functional Trait Phenotyping Methods and Applications

Seeds play a critical role in ensuring food security for the earth's 8 billion people. There is great biodiversity in plant seed content traits worldwide. Consequently, the development of robust, rapid, and high-throughput methods is required for seed quality evaluation and acceleration of crop improvement. There has been considerable progress in the past 20 years in various non-destructive methods to uncover and understand plant seed phenomics. This review highlights recent advances in non-destructive seed phenomics techniques, including Fourier Transform near infrared (FT-NIR), Dispersive-Diode Array (DA-NIR), Single-Kernel (SKNIR), Micro-Electromechanical Systems (MEMS-NIR) spectroscopy, Hyperspectral Imaging (HSI), and Micro-Computed Tomography Imaging (micro-CT). The potential applications of NIR spectroscopy are expected to continue to rise as more seed researchers, breeders, and growers successfully adopt it as a powerful non-destructive method for seed quality phenomics. It will also discuss the advantages and limitations that need to be solved for each technique and how each method could help breeders and industry with trait identification, measurement, classification, and screening or sorting of seed nutritive traits. Finally, this review will focus on the future outlook for promoting and accelerating crop improvement and sustainability.

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

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.