Optimizing Near-Infrared Spectroscopy Models for Rapid and Green Detection of Crude Protein and Fat in Crop Grains Using Sample Set Division

Rapid detection of crop grain components is crucial for effective production and energy conversion. We used the sample set division method to divide multiple sample sets and optimize NIRS models for rapid prediction of protein and fat content. 1243 and 415 crop grain samples were screened and divided into 5 and 4 sets, respectively. The aim was to establish NIRS models for protein and fat content prediction. The best modeling methods for protein were N (Norris Derivative)+D (detrending)-C (CARS)-P (PLS) and N+M (MC-UVE)-C-P, while those for fat were N+M-C-P and N+S (Savitzky-Golay)-C-P. The SS (Soybean Set), KS (Sorghum Set), and FS (Full Samples Set) data sets provided accurate protein content analysis, while the FS and SS data sets were suitable for both protein content prediction and evaluation. For fat, the FS, SS, and CS (Cereal Set) models met content analysis requirements, with the FS model suitable for external validation. It compared and analyzed the fitness, robustness, and accuracy of different NIRS set models, employing various division methods in this study, which provided a new idea of green method theoretical and technical support for major component rapid detection of biomass raw materials.