Plant taxonomy is the scientific study of the classification and naming of various plant species. It is a branch of biology that aims to categorize and organize the diverse variety of plant life on earth. Traditionally, plant taxonomy has been performed using morphological and anatomical characteristics, such as leaf shape, flower structure, and seed and fruit characters. Artificial intelligence (AI), machine learning, and especially deep learning can also play an instrumental role in plant taxonomy by automating the process of categorizing plant species based on the available features. This study investigated transfer learning techniques to analyze images of plants and extract features that can be used to cluster the species hierarchically using the k-means clustering algorithm. Several pretrained deep learning models were employed and evaluated. In this regard, two separate datasets were used in the study comprising of seed images of wild plants collected from Egypt. Extensive experiments using the transfer learning method (DenseNet201) demonstrated that the proposed methods achieved superior accuracy compared to traditional methods with the highest accuracy of 93% and F1-score and area under the curve (AUC) of 95%, respectively. That is considerable in contrast to the state-of-the-art approaches in the literature.

In this study the morphological and anatomical variation in stem and leaf tissues of three genera of Zygophyllaceae: Fagonia (4 taxa), Tetraena (4 taxa), and Tribulus (4 taxa) were investigated. The twelve examined taxa included nine species that grow in the eastern region of Saudi Arabia. Additional features for taxon identification and characterization can be developed because of our findings. The anatomical features investigated included, stem diagram, epidermal cell shape, structure of cortex and pith, the number of vascular bundles, petiole and blade outline in cross section, mesophyll type, and distribution of secretory tissues and crystals. The conclusions of this study show that anatomical features, particularly the petiole and blade outlines and the type of vasculature of the stem and petiole, are significant tools in identifying and distinguishing between the species examined and can provide a key for identification of the investigated taxa. Distinction of the investigated Zygophyllaceae species, based on the characters assessed in this study, agreed with previous classifications of these species.

Aromatic plants are considered as one of the most important species, known for their significant contributions towards the human life since from ancient times to the present day. Their key importance lies in their production of odorous aromatic chemical compounds known as essential oils. These essential oils find extensive use in the food, cosmetic, and pharmaceutical industries. Saudi Arabia is majorly rich towards the diversity of plants which includes aromatic species. The flora of Saudi Arabia consists of a total of 68 species of aromatic plants belonging to five different families, with Lamiaceae family being the most dominant; which comprises 42 species. This study aims to provide an overview of 15 endemic medicinal and aromatic plants native to Saudi Arabia, all of which belongs to Lamiaceae family. The focus is mainly on their morphology, distribution, phytochemical properties, and the significance of the essential oils extracted from these plants. However, further research and examination are required to fully comprehend the medicinal properties and chemical content of aromatic plants, such as Ballota undulata, Otostegia fruticosa, Satureja nabateorum, and Thymus decussatus.