Paullinia stellata is found in anthropogenic places and lowland forests, yet little information about their reproductive characteristics is known. This study aimed to determine the physical properties of seeds and the characteristics of their reproductive aspects. Racemes, fruits, and seeds were measured and weighed. The physical properties of the seeds were determined using three-dimensional data. A descriptive statistic was applied for racemes and fruits, and a statistic of small samples was conducted for the physical properties. The results showed low magnitude variations for variables analyzed in both parameters. The physical properties of the seeds are relatively moderate variations from low oscillations. Fruit maturity is detected by the opening of the endocarp exposing the seed, but it presents early and late fruit with asynchronous maturation. This study was conducted only on a single plant and observed asynchronous fruits within the same raceme.

With the increasing soybean production in Brazil, and the demand for soybeans with high protein and oil content, it is essential to conduct an in-depth study of the constituents of this grain, which can vary according to genotypes and growing conditions. Therefore, the objective of this study was to classify soybean genotypes, cultivated in different environments and sowing seasons, according to their chemical composition and the spectrum generated by near-infrared spectroscopy (NIRS). For this purpose, artificial intelligence and its machine learning technique were employed. 10 soybean genotypes were used, sown in two sowing seasons and cultivated 7 cities in Rio Grande do Sul. The chemical composition of the samples was analyzed using the FOSS NIRS DS2500 equipment, selecting the band between 807 and 817 nm. The applied algorithms were J48, Random Forest, CVR, lBk, MLP, using the Resample filter. The Weka software, version 3.8.6, was employed for data mining. The IBk algorithm achieved the best performance, reaching 89% correct classification of attributes. From the Confusion Matrix, it was observed that all genotypes obtained results above 60/70 for correctly predicted values, highlighting the algorithms’ good performance. In the metrics, IBk achieved 0.89 Precision, Recall, and F-Measure, and 0.94 ROC Area. Thus, it was possible to classify the genotypes according to their chemical composition related to the data obtained in the spectral curve, sowing season, and environment, using artificial intelligence and machine learning.

The differences observed in the physical properties of the seeds may indicate types of equipment for harvesting and processing, in addition to variability between plants. It was studied the characterization of the dimensions of the seeds, linear and geometric and the viability defined in categories. The results showed that the studied seeds did not reach a spherical shape, and their mass underwent variation resulting from the sorption and desorption process. The morphological characteristics suggested slight differences in the shape of the seeds. A high coefficient of variation was observed for fresh seed mass (18.34%), volume index (18.07%), seed volume (18.07%), and seed surface area (12.47%). Seed colorations showed differences in germination. The analysis concluded that all categories of seeds are viable. These descriptive data indicate that the combination of seed characteristics and the germination process help in methodologies for planting, harvesting, processing, and storage of seeds.