Multispectral Information in the Classification of Soybean Genotypes Using Algorithms Regarding Micronutrient Nutritional Contents

Identifying machine learning models that are capable of classifying soybean genotypes according to micronutrient content using only spectral data as input is relevant and useful for plant breeding programs and agricultural producers. Therefore, our objective was to classify soybean genotypes according to leaf micronutrient levels using multispectral images. In the 2019/20 crop year, a field experiment was carried out with 103 F2 soybean populations in the experimental area of the Federal University of Mato Grosso do Sul, in Chapadão do Sul, Brazil. The data were subjected to machine learning analysis using algorithms to classify genotypes according to leaf micronutrient content. The spectral data were divided into three distinct input groups to be tested in the machine learning models: spectral bands (SBs), vegetation indices (VIs), and combining VIs and SBs. The algorithms tested were: J48 Decision Tree (J48), Random Forest (RF), Support Vector Machine (SVM), Perceptron Multilayer Neural Network (ANN), Logistic Regression (LR), and REPTree (DT). All model parameters were set as the default settings in Weka 3.8.5 software. The Random Forest (RF) algorithm outperformed (>90 for CC and >0.9 for Kappa and Fscore) regardless of the input used, demonstrating that it is a robust model with good data generalization capacity. The DT and J48 algorithms performed well when using VIs or VIs+SBs inputs. The SVM algorithm performed well with VIs+SBs as input. Overall, inputs containing information about VIs provided better results for the classification of soybean genotypes. Finally, when deciding which data should serve as input in scenarios of spectral bands, vegetation indices or the combination (VIs+SBs), we suggest that the ease and speed of obtaining information are decisive, and, therefore, a better condition is achieved with band-only inputs. This allows for the identification of genetic materials that use micronutrients more efficiently and the adaptation of management practices. In addition, the decision to be made can be made quickly, without the need for chemical evaluation in the laboratory.