Single-kernel NIR spectroscopy for non-destructive rice bran color discrimination across diverse hull types and production environments

Authors: MENDOZA, PRINCESS TIFFAN - Kansas State University; ARMSTRONG, PAUL - Retired ARS Employee; MCLUNG, ANNA - Retired ARS Employee; Scully, Erin; SILIVERU, KALIRAMESH - Kansas State University

Submitted to: Smart Agricultural Technology
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 5/4/2026
Publication Date: 5/7/2026
Citation: Mendoza, P.D., Armstrong, P., Mclung, A.M., Scully, E.D., Siliveru, K. 2026. Single-kernel NIR spectroscopy for non-destructive rice bran color discrimination across diverse hull types and production environments. Smart Agricultural Technology. 26(10):2936. https://doi.org/10.3390/s26102936.
DOI: https://doi.org/10.3390/s26102936

Interpretive Summary: Although white rice is traditionally grown in the US, purple and red pigmented rice varieties with antioxidant properties in the bran layer are associated with positive human health benefits and are being increasingly grown. Uniformity of bran color in seed lots is important as the presence of any discolored or pigmented rice degrades the quality and value of the finished product. Normally, determining bran color requires the removal of the outer hull, which is destructive and time-consuming. Thus, rapid, non-destructive methods of sorting seeds by color are required. In this study, single-kernel near-infrared (SKNIR) spectroscopy was explored to discriminate rough rice based on bran color (brown, purple, or red) without removing the hull. The results revealed that brown bran is the easiest to identify among the three bran colors and that models were consistently accurate in identifying brown rice regardless of variations in hull color and growing environment. In contrast, it was most difficult to accurately identify red bran, especially when grown in different environments and when hull color was consistent; however, even under these conditions, the model correctly detected red bran 87% of the time. Adding additional variables to the model, such as seed size or gelatinization, into the model could improve prediction. These results demonstrate the potential of SKNIR for rapid and non-destructive separation of rough rice according to bran color, facilitating sorting and quality control applications for breeding and processing of pigmented rice varieties.

Technical Abstract: Uniformity of rice bran color is important in the whole grain rice market as well as in seed rice production. Normally, determining bran color requires the removal of the outer hull, which is a destructive process, time-consuming, and an obstacle to the production of nutritious pigmented bran varieties. In this study, single-kernel near-infrared (SKNIR) spectroscopy (905-1688 nm) and multivariate techniques were explored to discriminate rough rice based on bran color (brown, purple, red bran) in rice varieties with similar hull colors, different hull colors, and different growing environments in the US. Classification models were developed using partial least squares discriminant analysis (PLS-DA) and quadratic discriminant analysis (QDA) in combination with variable selection techniques. The results revealed that brown bran is the easiest to identify among the three bran colors. In rough rice varieties with similar straw hulls and different growing environments, the lowest precision was found in red bran. The models from QDA, which performed better than PLS-DA, achieved a recall (true positive rate) of 90-100% and a maximum false positive rate of 7%. These results demonstrate the potential of SKNIR for rapid and non-destructive separation of rough rice according to bran color, facilitating sorting and quality control applications for breeding and processing of pigmented rice varieties.