Abstract
Soybean (Glycine max (L.) Merrill) is an important oil crop with significant economic value worldwide, the breeding of soybean varieties requires not only high oil content, but also the appropriate ratio of fatty acids. In this study, a rapid and nondestructive detection method for oil and fatty acid content of soybean was developed using hyperspectral imaging (HSI). Five wavelength selection methods, including competitive adaptive re-weighted sampling, random frogs, iteratively retaining informative variables, uninformative variable elimination, and genetic algorithm, were used to select the important variables, and partial least squares (PLS) was used to build the prediction models. Among five methods, uninformative variable elimination provided with satisfactory results for the prediction of oil content and fatty acid content of soybean. The validation results showed that oil content and linolenic acid had good performance with correlation coefficient for cross-validation (R2cv) values of 0.90 and 0.92, and correlation coefficient predictive (R2p) values of 0.93 and 0.93, respectively. The absolute errors between the predicted and actual values of oil and linolenic acid content ranged from -1.39% to 0.97% and from -0.86% to 1.07%, respectively. In addition, oleic acid had better results with R2cv, RPDcv, and R2p values of 0.84, 2.45, and 0.85, respectively. Furthermore, Compared the models developed using near infrared (NIR), the the average relative errors of the established HSI models for oil content, oleic acid, linoleic acid and linolenic acid in soybean decreased by 48.94%, 21.85%, 37.98% and 39.31%, respectively. Therefore, HSI has great potential to detect oil content and major fatty acids in soybeans.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call