Plant Taxonomy Research Articles

A Machine Learning Perspective on Daisy and Dandelion Classification: Gaussian Naive Bayes with Sobel

This study explores the classification of Daisy and Dandelion flowers using a Gaussian Naive Bayes classifier, enhanced by Sobel segmentation and Hu moment feature extraction. The research adopted a quantitative approach, utilizing a balanced dataset of Daisy and Dandelion images. The Sobel operator was employed for image segmentation, accentuating the floral features crucial for classification. Hu moments, known for their invariance to image transformations, were extracted as features. The Gaussian Naive Bayes algorithm was then applied, with its performance evaluated through a 5-fold cross-validation process. The results exhibited moderate accuracy, with the highest recorded at 60%, and precision peaking at 62.60%. These findings indicate a reasonable level of effectiveness in distinguishing between the two species, though variations in performance metrics suggested room for improvement. The study contributes to the field of botanical image classification by demonstrating the potential of integrating image processing techniques with machine learning for flower classification. However, it also highlights the limitations of the Gaussian Naive Bayes approach in handling complex image data. Future research directions include exploring more advanced machine learning algorithms and expanding the feature set to enhance classification accuracy. The practical implications of this research extend to ecological monitoring and agricultural studies, where efficient and accurate plant classification is vital

MOLECULAR GENETIC CHARACTERIZATION OF UKRAINIAN REPRESENTATIVES OF THE COMPLEX SPECIES ACONITUM ANTHORA BASED ON THE ITS1-5.8S- ITS2 REGION OF THE NUCLEAR GENOME

Problem. The question of determining the boundaries of a species, in addition to the fundamental aspects, is of practical importance for nature conservation activities. One of the taxonomically problematic groups is the complex species A. anthora s. l. In the flora of Ukraine, four taxa with controversial status are distinguished within its borders, A. anthora L., A. eulophum Rchb., A. jacquinii Rchb. and A. pseudanthora Błocki ex Pacz. The last two species are included in the Red Book of Ukraine and the IUCN list. Determining the taxonomic position of these closely related forms requires the use of molecular genetic approaches. The ITS1-5.8S-ITS2 region of 35S rDNA is considered the most popular and informative marker for plant taxonomy and barcoding. Aim. To clarify the taxonomic status and phylogenetic relationships of representatives of A. anthora s. l. using the molecular marker ITS1-5.8S-ITS2 of 35S rDNA. Methods. Herbarium specimens of four representatives of the group A. anthora s. l. were collected on the territory of Western Ukraine. DNA was isolated by a modified CTAB method and then used for PCR amplification of the ITS1-5.8S-ITS2 region. PCR products were purified and Sanger sequenced. The sequences obtained were aligned with the sequences deposited in the GenBank database for representatives of two subgenera of the genus Aconitum, i.e. the nominative subgenus and the subgenus Lycoctonum. The resulting matrix was used for principal component analysis (PCA) and phylogenetic analysis using the Maximum Likelihood method. Main results. The sequences of ITS1-5.8S-ITS2 that we obtained for A. anthora, A. eulophum, A. jacquinii, and A. pseudanthora samples were found to be almost identical. They differed from each other in only five of the 641 alignment positions. Among them, four out of five positions appeared to be polymorphic even within individual genomes. According to the results of PCA analysis, all four samples of A. anthora s. l. formed a dense cluster separated by significant distances from the clusters formed by representatives of the subgenera Aconitum and Lycoctonum. In the generated phylogenetic tree, three main monophyletic clades are present, which correspond to the subgenera Aconitum and Lycoctonum and the A. anthora s. l. group. The Lycoctonum clade was sister to other members of the genus, and the Aconitum and A. anthora s. l. clades were sister to each other. Conclusions. The use of the ITS1-5.8S-ITS2 region of 35S rDNA for phylogenetic analysis confirms the need to grant the A. anthora s. l. group the status of a separate subgenus within the genus Aconitum. The high genetic affinity between samples of A. anthora s. l. from the territory of Ukraine indicates that the species names A. eulophum, A. jacquinii, and A. pseudanthora should be considered synonyms of A. anthora.

Taxa proposed by Pourret based on the specimens conserved in Salvador herbarium (eighteenth century)

The Salvador herbarium (seventeenth to eighteenth century) is one of the oldest pre-Linnaean herbaria in Spain. Currently preserved in the Botanical Institute of Barcelona, it was reviewed by Pourret during the eighteenth century, who added the Linnaean name of the species to the labels and proposed many new names. Our study has allowed us to enlist all taxa proposed by Pourret (a total of 335); however, only 12 were validly published (some by other authors), and two of them are lectotypified here. We have also classified the rest of names into three categories: 35 that were included in publications by other authors but are not validly published names; 160 that were published by other authors; and 128 that we have not been able to find in any publication, and they should be considered as merely Pourret’s proposals without any validity. These results reflect the situation of plant taxonomy in the late eighteenth century; in Pourret’s time the number of published taxa was very low while taxonomical studies done by other contemporary authors were rarely available. Thus, Pourret was not able to assign already published taxa to all specimens and, therefore, he was forced to do new proposals that were mostly incorrectly published.

Divergence of Seed Mass in Riparian Plant Communities Dominated by Filtering and Random Processes

Restoration of degraded riparian zones is the primary challenge for ensuring the sustainability of watershed ecosystems. An essential aspect of this endeavor is gaining a deep understanding of how riparian plant communities are assembled. The main focus of this study was to investigate how riparian plant communities respond to varying levels of flooding stress along the Three Gorges Reservoir (TGR) in China’s Yangtze River. To accomplish this, we calculated the diversity of plant taxonomy, traits and phylogeny, and used a null model to reflect the plant community assembly rules within the riparian zones along the TGR. The riparian zones were divided into four regions based on water regime: the fluctuating backwater area, the permanent backwater area, mainstream and tributaries of the TGR, covering the reservoir area of 1084 km2 with 180 sampling sites surveyed. Our results showed that within the permanent backwater area of the tributaries, the gradient variation in taxonomic and trait diversity of the riparian community was strongly aligned with the varying levels of flooding stress, which suggests that strong environmental selection plays a significant role in this section. Furthermore, through analysis of phylogenetic and trait structures based on the null model, we found that environmental filtering and random processes were the primary mechanisms shaping plant communities in the riparian zones across the entire study area. However, by further examining single traits, we found that seed mass was the sole trait displaying noteworthy divergence in the riparian communities throughout the study area. This finding highlights that seed mass appears as a pivotal divergent trait in the herb succession stage of the riparian communities that is strongly governed by filtering and random processes. In conclusion, we recommend prioritizing seed mass differences in ecological restoration efforts for herb succession in flooding-stressed riparian communities. This approach is crucial for enhancing source utilization, facilitating community assembly, and improving overall recovery outcomes.

Application of chloroplast genome analysis in plant taxonomy

Chloroplasts are important components of plants and photosynthetic organs, which have played an important role in the long history of biological evolution. Because of this, chloroplast genome research has gradually become the focus of plant research. With the further development of biotechnology, it has been found that the information of chloroplast genome structure and sequence is of great value in revealing the origin of species, evolutionary evolution and the relationship between different species. At the same time, chloroplast transformation technology, which has obvious advantages over nuclear transformation, has shown great potential in genetic improvement and the production of biological agents. Chloroplast genome structure and sequence analysis is the foundation of chloroplast transformation. Based on these important roles of chloroplasts, the application of chloroplast genome in plant classification, variation and distribution analysis was discussed in this paper. At the same time, the current analysis and research methods were summarized and briefly introduced according to different objectives. According to this study, ISSR marker analysis, DNA barcoding technology and high-throughput sequencing technology are still the main biogenic analysis methods for chloroplast gene analysis, and chloroplast transformation is the focus of future research.

Unveiling the diverse medicinal properties of Murraya koenigii

Since the beginning of time, nature has provided medicines for treating fatal illnesses. Herbalists believe that certain plants have medicinal qualities. In tribal and rural communities, medicinal plants provide as an easily accessible source of treatment. The identification of various rejuvenating molecules that can halt or lessen the pathology of a variety of diseases will be regarded as a significant development of the present. There has been a scientific advancement in this area, and current studies on herbal medicines and traditional cures have attracted significant interest from all over the world. This plant, popularly known as the curry tree, is frequently used as herb and is also used to treat a variety of problems in traditional Indian medicine. About 80–85% of people worldwide rely on herbal products because they are thought to be efficient, secure, and cost-effective. Reviewing the plant taxonomy, ethnobotanical characteristics, folkloric or traditional uses, phytochemical, and pharmacological qualities of the Murraya koenigii plant was the goal of the current study. The leaves are used internally for dysentery as a carminative, tonic, stomachic, and inducer of vomiting. The usage of other parts includes treating piles, preventing helminthiasis, and reducing body heat, itchiness, and inflammation. Following several reports that this plant may treat a wide range of illnesses, scientists have worked to confirm the effectiveness of this plant by biological screening. A review of the literature suggests that Murraya koenigii has various medical benefits, including activity of antimicrobial, cardiac, anti-oxidative, anti-diabetic and cholesterol reduction, cytotoxic action, antiulcer, and anti-diarrhea.

Utilization of Plants at FMIPA UNM as a Learning Resource for Plant Taxonomy Subjects

Utilization of Plants at FMIPA UNM as a Learning Resource for Plant Taxonomy Subjects

Response of riparian plant community to landscape matrix differs by taxonomic and functional diversity: Implications for the planning of riparian landscapes regulated by dams

Local plant communities are embedded within the landscape matrix, and thus, diversity of these communities is largely determined by the spatial pattern of surrounding land-use. However, it is not yet clear how taxonomic and functional diversity within riparian plant communities respond differently to the landscape matrix at different scales, and whether and how these landscape-scale responses can be shaped by flooding conditions in the riparian landscape. This study is based upon field surveys of riparian plant communities in a total of 136 quadrats exposed to two different levels of flooding intensity along the reservoir formed by the Three Gorges Dam (TGD). We investigated the relationship between plant diversity of riparian communities and the surrounding landscape at different scales, which examined how the diversity, in terms of both plant taxonomy and functional traits, was affected by the landscape matrix at 15 different spatial scales ranging from 200 m to 3000 m in increments of 200 m around each sampling site. Furthermore, the community diversity in response to the landscape matrix under different levels of flooding intensity was also examined. Our findings suggested that trait-based functional diversity was more closely related to the landscape matrix at all 15 scales examined, compared to taxon-based diversity. The dispersal trait was found to be more susceptible to landscape connectivity across the matrix. Further, both types of diversity responded more strongly to landscape configurational metrics than compositional metrics. In addition, we observed that, in the communities exposed to high flooding intensity, the two types of diversity tended to have more consistent responses to the landscape matrix compared to those exposed to low flooding intensity. We concluded that while the landscape matrix had different effects on taxonomic and functional diversity, the high flooding intensity could lessen their differences in the riparian landscape. Our findings revealed that the robust local environmental filtering process, which affects the diversity of riparian communities, could lead to both diversity components exhibiting similar responses to the landscape matrix in riparian landscapes.

БАРНА МИКОЛА МИКОЛАЙОВИЧ – ВІДОМИЙ УКРАЇНСЬКИЙ ВЧЕНИЙ–БОТАНІК, ЦИТОЕМБРІОЛОГ, ЗАСЛУЖЕНИЙ ДІЯЧ НАУКИ І ТЕХНІКИ УКРАЇНИ, ПЕДАГОГ

Mykola Mykolaiovych Barna, who celebrated his 85th birthday on February 8, 2023, is a renowned Ukrainian scientist in the fields of botany, morphology, dendrology, and plant cytoembryology. He holds the titles of Academician of the Academy of Sciences of Higher Education of Ukraine, Merited Science and Technology Functionary of Ukraine, Education Excellence of Ukraine, Nature Conservation Excellence of Ukraine, and is an Honorary Member of the Ukrainian Botanical Society. He is also a scholarship holder of the Cabinet of Ministers of Ukraine, a Doctor of Biological Sciences, and a Professor at the Department of Botany and Zoology at Ternopil Volodymyr Hnatiuk National Pedagogical University.
 This article highlights Professor’s impressive 62-year career in production, research, education, pedagogy, and public service. He began as a lecturer and senior lecturer at the Department of Botany in 1971, became an associate professor in 1975, and a professor in 1996. He served as the head of the Department of Botany from 2002 to 2012 and as the head of the Department of Botany and Zoology from 2012 to 2014. Additionally, he held positions such as Deputy Dean of the Faculty of Natural Sciences from 1977 to 1985 and Dean of the Faculty of Chemistry and Biology from 1990 to June 2006.
 Professor M. M. Barna’s extensive scholarly output includes over 450 published works, including monographs, bibliographies, dictionaries, scientific publications, educational materials for high and secondary education institutions, and methodological recommendations. He has supervised the defence of seven PhD theses and served as an official opponent at academic councils for the defence of doctoral and PhD theses. He was a member of specialised academic councils at the M. G. Kholodny Institute of Botany of the National Academy of Sciences of Ukraine and the National Forestry University of Ukraine. For over two decades, he chaired the editorial board of the specialised scientific publication “Scientific notes of Ternopil Volodymyr Hnatiuk National Pedagogical University. Series: Biology.”
 Professor Barna's contributions also extend to initiatives such as the establishment of the Arboretum of Ternopil State Pedagogical Institute, the creation of the herbarium of the Department of Botany (now the “Herbarium-laboratory of plant morphology and taxonomy”), and the establishment of the laboratory of biology and ecology known as the “Holytskyi biostation of the university.” He played a crucial role in the realisation of the Biblical Botanical Garden on TNPU’s premises, turning this idea into a reality. Professor Mykola Mykolaiovych Barna's lifelong dedication to science and education has left an indelible mark on his field and the academic community.

Origin of Angiosperms: Problems, Challenges, and Solutions.

Angiosperms are frequently assumed to constitute a monophyletic group. Therefore, the origin of angiosperms is a key question in systematic botany since the answer to this question is hinged with many questions concerned with angiosperm evolution. Previously, the lack of fossil evidence undermines the robustness of related hypotheses, and explains the instability of the systematics of angiosperms in the past century. With increasing evidence of early angiosperms, the origin and early evolution of angiosperms become approachable targets. However, reaching a strict consensus is still a mission impossible now: there are too many issues open to debate. A good sign in research is that palaeobotanists started addressing the issue of criterion identifying angiosperms, this would bring order in studies of early angiosperms. Several flaws in fundamental concepts inflicting botany require efforts to elucidate and remedy. The author here opens a discussion on these problems, hoping that more botanists will join to discuss and clarify previously blurry concepts and place a solid foundation for future development in botany.

Zasługi Karola Linneusza dla postępu nauk farmaceutycznych w XVIII w.

The importance of Linnaeus’ taxonomy for the progress of pharmaceutical science in the 18th century Fundamentals of Linnaean taxonomy were established from the late 1730s and had a gradual ordering impact on all plant knowledge of the time. Pharmaceutical botany was enlivened by the following assertions, ideas or publications issued by Linnaeus: 1) the sexual system as a tool for practical identifi cation of genera; 2) the genera were newly defi ned or corrected to build a clear system; 3) botanists were encouraged to construct and study a natural system of genera which was expected to reveal similarities in pharmacological actions (as analogous to morphological similarities of allied species); 4) a critical and minimalist review of medicinal species and their therapeutical uses was published; 5) the synonymy of species was rectifi ed by selecting only good and suffi ciently descriptive polynomials; and fi nally 6) it became the new scientifi c standard to typify the name and description of a species on a proof sample, the role of which began to be played by a herbarium specimen of a plant, called a type. The practice of assigning binominal names to known or newly described species enabled botanists to place them immediately in the sexual system (by assigning a generic name, the genus was ranked in terms of fl ower structure). The increase in the number of medicinal plant species at the end of the 18th century was the result of a desire to make the knowledge complete and modern, and to add new facts about related species in a wellorganized form. Canons for the experimental and clinical study of effects of known and new medicinal plants on healthy and sick patients were being developed. The introduction of many new species into practical therapy took pharmacy by surprise, as the pharmacist had to learn to recognise medicinal plants previously unknown to pharmacy, which was not without its mistakes. Misrecognised plants that became drug ingredients could exert unintended effects in therapy, undermining the authority of physicians, hindering the evaluation of drugs and threatening to fl ood scientifi c pharmacy with a stream of erroneous knowledge. Continued practical self-education of pharmacists in the fi eld of plant taxonomy was therefore claimed.

Do Abiotic Stresses Affect the Aroma of Damask Roses?

Roses are popular ornamental plants all over the world. Rosa damascena Mill., also known as the damask rose, is a well-known scented rose species cultivated to produce essential oil. The essential oils obtained are high in volatile organic compounds (VOCs), which are in demand across the pharmaceutical, food, perfume, and cosmetic industries. Citronellol, nonadecane, heneicosane, caryophyllene, geraniol, nerol, linalool, and phenyl ethyl acetate are the most important components of the rose essential oil. Abiotic factors, including as environmental stress and stress generated by agricultural practises, frequently exert a selective impact on particular floral characteristics, hence influencing the overall quality and quantity of rose products. Additionally, it has been observed that the existence of stress exerts a notable impact on the chemical composition and abundance of aromatic compounds present in roses. Therefore, understanding the factors that affect the biosynthesis of VOCs, especially those representing the aroma and scent of rose, as a response to abiotic stress is important. This review provides comprehensive information on plant taxonomy, an overview of the volatolomics involving aromatic profiles, and describes the influence of abiotic stresses on the biosynthesis of the VOCs in damask rose.

Statistics and Analysis of Digital Information on Vascular Plant Specimens and the History of Plant Collecting in Guangzhou, China.

This paper presents a comprehensive analysis of digitized specimen data and relevant literature to investigate the vascular plant diversity in Guangzhou City, China. Specimen data were collected from various sources, including the China Digital Herbarium (CVH), the National Specimen Resource Sharing Platform (NSII), Global Plants on JSTOR, and the Global Biodiversity Information Facility (GBIF). Following data standardization, the study identified 41,890 vascular plant specimens, encompassing 248 families, 1563 genera, and 4536 species, including subspecies and cultivated plants. Among them, the native plants of Guangzhou city accounted for 60.6% of the species. The temporal analysis identified three distinct peaks in specimen collection: 1916-1920, 1928-1936, and 1950-1964. Collection activities were primarily concentrated between the months of April and November. The distribution of collected specimens exhibited significant variation among different species, with families such as Fabaceae, Poaceae, and Myrtaceae having the highest number of specimens. Similarly, genera such as Eucalyptus, Ficus, and Citrus were well-represented. The most frequently collected species included Litchi chinensis, Eucalyptus robusta, and Cycas taiwaniana. Remarkably, 21 species had specimen counts exceeding 100. Unfortunately, approximately three-quarters of the species had fewer than 10 recorded specimens. Alarmingly, 1220 species were represented by only one specimen. Geographically, the majority of specimens originated from the former suburbs of Guangzhou, Conghua Delta Mountain, and Liuxi River areas, while other regions had limited representation. In terms of specimen collections, the Herbarium of South China Botanical Garden of the Chinese Academy of Sciences (IBSC) recorded the highest number of specimens (13,828 specimens), followed by the Tree Herbarium of South China Agricultural University (CANT; 3869 specimens) and the Herbarium of Sun Yat-sen University (SYS; 3654 specimens). The collection history in Guangzhou spans nearly 300 years and can be broadly divided into two distinct periods. The first period extends from the late 13th century to 1949, primarily encompassing the collection efforts of foreign visitors in Guangzhou, and represents the pioneering phase of plant taxonomy research in China. The second period, from 1949 to the present, is characterized by extensive investigations and collection activities conducted by local scholars, with a specific emphasis on native plant resources. By meticulously organizing and verifying information derived from historical documents and specimens, the paper effectively summarizes the plant collection and research history of Guangzhou, providing detailed profiles of the key collectors. These findings furnish reliable historical reference materials for the study of plant taxonomy and diversity in Guangzhou.

Tobamoviruses show broad host ranges and little genetic diversity among four habitat types of a heterogeneous ecosystem.

Host ranges of plant viruses are poorly known, as studies have focused on pathogenic viruses in crops and adjacent wild plants. High throughput sequencing (HTS) avoids the bias towards plant-virus interactions that result in disease. Here we study the host ranges of tobamoviruses, important pathogens of crops, by HTS analyses of an extensive sample of plant communities in four habitats of a heterogeneous ecosystem. Sequences of 17 virus operational taxonomic units (OTUs) matched references in the Tobamovirus genus, eight had narrow, and five had wide host ranges. Regardless of host range, each OTU host belonged to taxonomically distant families, suggesting no phylogenetic constraints in host use associated with virus adaptation, and that tobamoviruses may be host generalists. The OTUs identified as TMGMV, TMV, PMMoV and YoMV, had the largest realized host ranges that occurred across habitats, and exhibited host use unrelated to the degree of human intervention. This result is at odds with assumptions that contact transmitted viruses would be more abundant in crops than in wild plant communities, and could be explained by effective seed, contact, or pollinator-mediated transmission, or by survival in the soil. TMGMV and TMV had low genetic diversity that was not structured according to habitat or host plant taxonomy, which indicated that phenotypic plasticity allows virus genotypes to infect new hosts with no need for adaptive evolution. Our results underscore the relevance of ecological factors in host range evolution, in addition to the more often studied genetic factors.

SENSORY, GC-MS AND FTIR ANALYSIS OF AQUEOUS EXTRACT OF HIBISCUS SABDARRIFFA AND VERNONIA AMYGDALINA HERBAL TEA WITH BLENDS OF GINGER AND LEMON ZEST

The use of herbal remedies, especially in the form of teas for management of various diseases is gaining increasing popularity, making them the main stay of health care system, especially among the rural populace in the developing countries. Therefore, it is imperative to carryout proper analysis and screening of these plants, such as Hibiscus Sabdarriffa and Vernonia Amygdalina, to investigate their informed use. This research aimed at producing herbal teas from leaves of Hibiscus Sabdarriffa and Vernonia Amygdalina with additives of ginger and lemon zest with acceptable sensory attributes and also to investigate the phytocomponents of these herbal teas produced using GC-MS spectroscopy and FTIR spectroscopy. Ginger, lemon zest and fresh leaves of Hibiscus Sabdarriffa and Vernonia Amygdalina were collected from modern market areas of makurdi Benue State, authenticated by a plant taxonomist in Department of Botany, University of Agriculture Makurdi. Aqueous extracts of the herbal teas were analyzed using GC-MS Clarus 500 Perkin Elmer system. Identification of functional groups of samples (was done using FT-IR spectroscope (Shimadzu, IR Affinity 1, Japan). Results: FT-IR analysis of the herbal tea samples revealed the presence of phytochemicals like alkanes, alkenes, Carboxylic acids, phenols, alcohols, flavonoids, aromatics and saturated aliphatic esters,. GC-MS analyses of aqueous extract of the samples provided different peaks determining the presence of twenty two compounds with highest abundance. Twelve compounds were identified for Vernonia Amygdalina herbal tea sample and ten for Hibiscus Sabdarriffa herbal tea sample. The findings from this research showed that herbal teas produced from leave of Hibiscus Sabdarriffa and Vernonia Amygdalina had acceptable sensory attributes and also contains bioactive constituents of pharmacological importance for management of diseases which were identified by GC-MS and FTIR analysis.

Revealing leaf species through specific contour and region-based features extraction

Leaf identification plays a vital role in plant classification and protection, and advancements in artificial intelligence and machine vision have revolutionized leaf identification technology. This study focuses on evaluating different feature extraction methods, specifically region-based and contour-based approaches, to identify plant leaf species through image analysis. The study initially extracts leaf characteristics from images, which are then divided into two groups based on area features or contour features. The dataset is split into 80% for training and 20% for testing, and a K-Nearest Neighbour (K-NN) classifier is employed for species identification. Three approaches are compared for leaf classification. The first approach utilizes region-based shape descriptors (RBSD) and achieves an accuracy rate of 75%. The second approach employs contour-based shape descriptors (CBSD) and achieves a higher accuracy of 76%. The third approach combines both area and contour features, resulting in an average accuracy of 75.5%. Through the comparison of all three methods, it is evident that the CBSD approach outperforms the others, making it the most effective feature extraction method for plant species identification. The developed automatic leaf species identification system was implemented using the PyCharm environment.The proposed approach and feature extraction techniques surpass previous state-of-the-art 69.61%, 72%, 74.4% results, showcasing the potential of the proposed separation of leaf characteristics. Also the advancement of automated leaf species identification and have significant implications for plant taxonomy and protection efforts.

PLANT IDENTIFICATION USING MACHINE LEARNING

The preservation of therapeutic plants is crucial as it will help a broad variety of sectors, including medicine, botanic research, and plant taxonomy studies, among others. Existing technologies cannot imitate the range of therapeutic plant species present in India. The suggested technique facilitates the classification of medicinal plants by exploiting textural aspects crucial in leaf recognition and identification. The three key phases of the proposed technique are picture enhancement, feature extraction, and classification. The photographs of the leaves are shot using cellphones and then processed using digital image processing algorithms to extract the features that may be compared between them. Finally, the CNN classifier is employed to develop an automated classifier. Key Words: Plant identification, CNN algorithm, Image processing.

Botanical characterization and authentication of lavender essential oil using its volatile organic compounds and compound-specific carbon and hydrogen isotope ratio analysis

The determination of authenticity and provenance is one of the main issues in high-value natural products such as lavender (L. angustifolia) essential oil. Due to their high value, natural products are often totally or partially substituted with cheaper alternatives. Therefore, it is necessary to accurately characterize the composition of lavender essential oil and its related species, particularly lavandin (L. intermedia) essential oil, which is frequently used as an adulterant. In this study, we analyzed the most distinctive volatile organic compounds (VOCs) and their relative compound-specific stable carbon and hydrogen (δ13C and δ2H) isotope ratios in lavender, lavandin, and commercial lavender essential oil samples using fast GC-MS/MS and GC-IRMS methods and sparse Partial Least Square Discriminant Analysis (sPLS-DA) to classify and verify their botanical origin. For the first time, concentration ranges for 79 VOCs and the δ13C and δ2H values in 32 VOCs were used to characterize lavender essential oils. sPLS-DA models with either VOCs, δ13C and δ2H, or in combination successfully classify lavender and lavandin with 100% accuracy. VOCs such as camphor, borneol, eucalyptol, α-bisabolol, and α-pinene were found to be the most important variables for differentiating lavender oil from lavandin. Similarly, δ13C in camphor, eucalyptol, trans-β-ocimene and 3-octanone, and δ2H in α-terpineol and trans-β-ocimene and 3-octanone also differentiated lavender and lavandin oil. In addition, we demonstrated that compound-specific δ13C and δ2H detected the adulteration of natural lavender or lavandin oil if more than 15% of linalool, linalyl acetate, eucalyptol, and α-terpineol were of synthetic origin. These preliminary results with sPLS-DA models suggest that VOCs and compound-specific δ13C and δ2H can be a promising tool for the botanical classification of lavender essential oil and the detection of possible adulteration with synthetic compounds.

Transfer Learning Approach to Seed Taxonomy: A Wild Plant Case Study

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.

Inventarisasi Dan Analisis Jenis Tumbuhan Famili Euphorbiaceae Dan Sebarannya Di Desa Cipeundeuy, Kecamatan Bantarujeg, Kabupaten Majalengka

Plant classification exists to simplify and clarify the level of kinship and the type of treatment in plant distribution, at the taxonomic level there are family categories, this family in plant taxonomy is a classification system that groups plants based on similarities between their morphology, characteristics, morphology. Euphorbiaceae is a family with flower characteristics hidden in cyathia structures (inflorencia), sap and various sizes. This research is located in Cipeundeuy Village, Bantarujeg District, Majalengka Regency with quantitative analysis using the exploration method in the residents' yards in Cipeundeuy Village. The results of the study found 1 individual of Ephorbia milli, 1 individual of Euphorbia hirta, 1 individual of Pedilanthus tithymaloides, 4 individuals of Acalypha siamensis and 8 individuals of Manihot esculenta from the Euphorbiacea family. This plant is used as an ornamental plant and can be used as herbal medicine because it has chemical compounds that are antiseptic, anti-inflammatory and antibacterial because it contains tannins, flavonoids and saponins which are effective for healing wounds and several other diseases. The purpose of this research is to inventory and identify plants in Cipeundeuy Village so that the systematics of plants in this area can be known.