Maturity Classification of Rapeseed Using Hyperspectral Image Combined with Machine Learning

Oilseed rape is an important oilseed crop planted worldwide. Maturity classification plays a crucial role in enhancing yield and expediting breeding research. Conventional methods of maturity classification are laborious and destructive in nature. In this study, a nondestructive classification model was established on the basis of hyperspectral imaging combined with machine learning algorithms. Initially, hyperspectral images were captured for 3 distinct ripeness stages of rapeseed, and raw spectral data were extracted from the hyperspectral images. The raw spectral data underwent preprocessing using 5 pretreatment methods, namely, Savitzky-Golay, first derivative, second derivative (D2nd), standard normal variate, and detrend, as well as various combinations of these methods. Subsequently, the feature wavelengths were extracted from the processed spectra using competitive adaptive reweighted sampling, successive projection algorithm (SPA), iterative spatial shrinkage of interval variables (IVISSA), and their combination algorithms, respectively. The classification models were constructed using the following algorithms: extreme learning machine, k-nearest neighbor, random forest, partial least-squares discriminant analysis, and support vector machine (SVM) algorithms, applied separately to the full wavelength and the feature wavelengths. A comparative analysis was conducted to evaluate the performance of diverse preprocessing methods, feature wavelength selection algorithms, and classification models, and the results showed that the model based on preprocessing-feature wavelength selection-machine learning could effectively predict the maturity of rapeseed. The D2nd-IVISSA-SPA-SVM model exhibited the highest modeling performance, attaining an accuracy rate of 97.86%. The findings suggest that rapeseed maturity can be rapidly and nondestructively ascertained through hyperspectral imaging.