FT-NIR and linear discriminant analysis to classify chickpea seeds produced with harvest aid chemicals.

Spectroscopy and machine learning (ML) algorithms have provided significant advances to the modern food industry. Instruments focusing on near-infrared spectroscopy allow obtaining information about seed and grain chemical composition, which can be related to changes caused by field pesticides. We investigated the potential of FT-NIR spectroscopy combined with Linear Discriminant Analysis (LDA) to discriminate chickpea seeds produced using different desiccant herbicides at harvest anticipation. Five herbicides applied at three moments of the plant reproductive stage were utilized. The NIR spectra obtained from individual seeds were used to build ML models based on LDA algorithm. The models developed to identify the herbicide and the plant phenological stage at which it was applied reached 94% in the independent validation set. Thus, the LDA models developed using near-infrared spectral data provided to be efficient, quick, non-destructive, and accurate to identify differences between seeds due to pre-harvest herbicides application.

Machine Learning for Seed Quality Classification: An Advanced Approach Using Merger Data from FT-NIR Spectroscopy and X-ray Imaging.

Optical sensors combined with machine learning algorithms have led to significant advances in seed science. These advances have facilitated the development of robust approaches, providing decision-making support in the seed industry related to the marketing of seed lots. In this study, a novel approach for seed quality classification is presented. We developed classifier models using Fourier transform near-infrared (FT-NIR) spectroscopy and X-ray imaging techniques to predict seed germination and vigor. A forage grass (Urochloa brizantha) was used as a model species. FT-NIR spectroscopy data and radiographic images were obtained from individual seeds, and the models were created based on the following algorithms: linear discriminant analysis (LDA), partial least squares discriminant analysis (PLS-DA), random forest (RF), naive Bayes (NB), and support vector machine with radial basis (SVM-r) kernel. In the germination prediction, the models individually reached an accuracy of 82% using FT-NIR data, and 90% using X-ray data. For seed vigor, the models achieved 61% and 68% accuracy using FT-NIR and X-ray data, respectively. Combining the FT-NIR and X-ray data, the performance of the classification model reached an accuracy of 85% to predict germination, and 62% for seed vigor. Overall, the models developed using both NIR spectra and X-ray imaging data in machine learning algorithms are efficient in quickly, non-destructively, and accurately identifying the capacity of seed to germinate. The use of X-ray data and the LDA algorithm showed great potential to be used as a viable alternative to assist in the quality classification of U. brizantha seeds.