Analyzing protein concentration from intact wheat caryopsis using hyperspectral reflectance

Abstract

Abstract Background Winter wheat grain samples from 185 sites across southern Shanxi region were processed and analyzed using a non-destructive approach. For this purpose, spectral data and protein content of grain and grain powder were obtained. After combining six types of preprocessed spectra and four types of multivariate statistical models, a relationship between hyperspectral datasets and grain protein is presented. Results It was found that the hyperspectral reflectance of winter wheat grain and powder was positively correlated with the protein contents, which provide the possibility for hyperspectral quantitative assessment. The spectral characteristic bands of protein content in winter wheat extracted based on the SPA algorithm were proved to be around 350–430 nm; 851–1154 nm; 1300–1476 nm; and 1990–2050 nm. In powder samples, SG-BPNN had the best monitoring effect, with the accuracy of R v 2 = 0.814, RMSEv = 0.024 g/g, and RPDv = 2.318. While in case of grain samples, the SG-SVM model exhibited the best monitoring effect, with the accuracy of R v 2 = 0.789, RMSEv = 0.026 g/g, and RPDv = 2.177. Conclusions Based on the experimental findings, we propose that a combination of spectral pretreatment and multivariate statistical modeling is helpful for the non-destructive and rapid estimation of protein content in winter wheat. Graphical Abstract

Keywords

• Grain protein
• Hyperspectral technology
• Multivariate models
• Spectral preprocessing
• Wheat