High-Precision Phenotyping in Soybeans: Applying Multispectral Variables Acquired at Different Phenological Stages

Soybean stands out for being the most economically important oilseed in the world. Remote sensing techniques and precision agriculture are being analyzed through research in different agricultural regions as a technological system aiming at productivity and possible low-cost reduction. Machine learning (ML) methods, together with the advent of demand for remotely piloted aircraft available on the market in the recent decade, have been conducive to remote sensing data processes. The objective of this work was to evaluate the best ML and input configurations in the classification of agronomic variables in different phenological stages. The spectral variables were obtained in three phenological stages of soybean genotypes: V8 (at 45 days after emergence—DAE), R1 (60 DAE), and R5 (80 DAE). A Sensefly eBee fixed-wing RPA equipped with the Parrot Sequoia multispectral sensor coupled to the RGB sensor was used. The Sequoia multispectral sensor with an RGB sensor acquired reflectance at wavelengths of blue (450 nm), green (550 nm), red (660 nm), near-infrared (735 nm), and infrared (790 nm). The following were used to evaluate the agronomic traits: days to maturity, number of branches, productivity, plant height, height of the first pod insertion and diameter of the main stem. The random forest (RF) model showed greater accuracy with data collected in the R5 stage, whose accuracies were close to 56 for the percentage of correct classifications (CC), close to 0.2 for Kappa, and above 0.55 for the F-score. Logistic regression (RL) and support vector machine (SVM) models showed better performance in the early reproductive stage R1, with accuracies above 55 for CC, close to 0.1 for Kappa, and close to 0.4 for the F-score. J48 performed better with data from the V8 stage, with accuracies above 50 for CC and close to 0.4 for the F-score. This reinforces that the use of different specific spectra for each model can enhance accuracy, optimizing the choice of model according to the phenological stage of the plants.