Research on the morphological properties of plant seeds is important because it advances the taxonomy of the genus, contributing to a better understanding of diversity and its evolutionary relationships. Silene L. is a genus of plants belonging to the family Caryophyllaceae Juss. Some Silene L. species have been considered an interesting source of nutraceutical compounds due to their medicinal properties, including anticancer, antioxidant, antibacterial, and anti-inflammatory effects. Recognising taxonomic groups based on seed morphology contributes to a better understanding of the diversity and identification of these species. Silene L. seeds from 95 populations belonging to 52 species reported in the literature were analyzed using machine learning algorithms such as random forest (RF), support vector machine (SVM), and artificial neural network (ANN) to evaluate their effectiveness in species identification and classification. The results obtained in this research study proved that the machine learning models were effective in identifying the taxonomy of these species. Therefore, the selected machine learning models developed in this study can be a useful tool to classify the taxonomy of these plants through seeds. Nevertheless, there is a considerable gap in the literature on this topic, so further research is necessary to develop new methods for enhancing the accuracy and efficiency of these classification systems.