Plant Identification Research Articles

Diversity, utility and communities of weed in wheat of Nowshera, Pakistan

Weeds are disregarded for their competitive nature and difficulties during harvesting and threshing. Categorizing them by economic use classes enables effective management. Weed ecological studies in wheat crop fields were conducted to evaluate the floristic diversity, ecological characteristics, community structures and economic uses of weeds in District Nowshera, Pakistan. Different wheat crop fields were surveyed for the collection and identification of plant species growing as weed. Total 50 plant species from 47 genera and 20 families were recorded in the study area. Asteraceae had the highest number of species (10), followed by Poaceae (9). Therophytes were more with 42 species, followed by geophytes and Hemicryptophytes each with 3 species. Most species had mesophyllous leaf size (15), while nanophyllous (12) and microphyllous (11). Simple leaves were more common (28) than dissected leaves (22). Nonspiny species were (44) while only 6 had spines. Maximum plant species were fodder (35) and medicinal (10). In the study, four distinct weed communities were identified using quadrate method i.e. Cynodon-Anagallis-Melilotus, Arenaria-Anagallis-Cannabis, Cynodon-Parthenium-Coronopus and Rumex-Arenaria-Oxalis. These findings provide a valuable starting point for future in-depth investigations on the entire flora and vegetation of Nowshera, Pakistan.

Improved beekeeping practices, honey bee flora potential and flowering calendar in South Ethiopia.

In Ethiopia, improved hive technology dissemination was started before five-decades. However, the adoption of improved beekeeping technology is still very low. This study was conducted with the main objectives to evaluating improved beekeeping adoption level and honey yields of different hives and identification of major honey bee plants and flora calendar in the Gedeo zone, South Ethiopia. Three districts were selected purposively based on beekeeping potential and the number of improved hives own by beekeepers. The data was collected from 180 respondents using cross-sectional survey. The data was analyzed by using descriptive statistics such as mean, frequency and percentage and ANOVA. The result shown that the compositions of disseminated hives in the entire sampled respondents were 286, 476, 121 and 1494 Zander hive, Kenyan top bar hive (KTBH), Mud/Ethio-Ribrab hive (ERH) and Traditional hives respectively. Traditional beekeeping was the dominant system with 63% and intermediate followed by 25%, while modern beekeeping was only 12%. Based on overall mean honey yield, there was no significant difference (P = 0.244) between Zander and KTBH. However, the average honey yield of these improved hives were significantly (P<0.05) higher than Mud/ERH and Traditional hives. Gedeo zone had rich floral resource and diverse floral calendar. Hygenia abyssinica, Bidens ghedoensis, Erythrinia abyssinica, Eucalyptus species, Cordia africana, Coffee arabica, Vernonia species, Susbania susban and Persea americana were major honey bee flora in Gedeo zone. February-March was major honey harvesting season while May-July and October-December respectively were minor honey harvesting periods. Nevertheless, the majority of beekeepers have been practicing honey harvesting once a year from all hives due to lack of awareness and practical skills. Therefore, we recommend that the local government should focus on educating beekeepers to enable them utilizing exhaustively the opportunities of multi-floral season and improved hive technology to maximize honey yield in the area.

Flower or leaf characteristics, coloured or black and white illustrations – what helps student teachers to identify plants?

ABSTRACT For a sound understanding of biological diversity, it is not only important to identify species and recall their names, but to be able to distinguish between organisms based on a range of characteristic traits. However, whether flower or leaf characteristics are more important in identifying plant species and whether colour illustrations in identification books are more helpful than black and white ones is largely unexplored. With the help of a mobile eye-tracking device and pictures from two plant identification books, this study aimed to contribute to filling this knowledge gap. Thirty student teachers, all undergraduates in biology, were shown two freshly picked wildflowers (Medicago sativa and Echium vulgare) and asked to select the corresponding illustration from each of four plants on an identification sheet, which was either in colour or in black and white. For both plants, the number of fixations, and positively correlated fixation duration, were significantly higher for the flower than the leaf part. Although flowers and leaves were fixated longer and more frequently in the black-and-white illustrations, correct identifications were more likely with the coloured identification sheets. The results indicate that colour illustrations and sorting by flower characteristics are particularly helpful in identification aids for undergraduate students.

Pharmacognostic Study and Standardization of Leaves and Stem of Mentha spicata Linn.

Background:: Various Mentha species are cultivated all over the world due to their aroma and valuable therapeutic constituents. Along with its traditional use as a food flavor, it is well-established folklore medicine for treating digestive and cardiovascular problems. Mentha spicata L. is a perennial, aromatic herb belonging to the Lamiaceae family. M. spicata leaves have been used in traditional systems of medicines for treating various digestive system disorders since old times. Aim:: The present research work encompasses the pharmacognostic study, phytochemical screening and physicochemical parameter estimation of leaves and stem of M. spicata L. for standardization of Mentha plant. Materials and Methods:: Morpho-anatomical characterization, physicochemical analysis and preliminary phytochemical investigation of leaves and stems were performed. These investigations were done as per WHO guidelines to determine the main diagnostic characteristics for correct identification and standardization of whole plant and powdered drug of M. spicata L. Results:: The dimensions, size, color, and surface texture characteristics of fresh crude drug (leaf and stem) were determined. Compound microscope images of the transverse section (TS) of M. spicata leaf and stem revealed the cellular arrangement and main identification characters. Phytochemical and physicochemical analysis of powdered drugs confirmed the presence of important phytoconstituents such as phytosterol, terpeneoids, phenolic compounds, saponins, volatile oil, etc. Conclusion:: The results obtained are helpful for the characterization of the crude drug. Morphoanatomical characterization and physicochemical analysis are inexpensive methods and serve as a quality control tool for stem and leaf standardization. The ethanolic and aqueous extract of leaves and stem showed the presence of valuable medicinally active phytoconstituents.

Acquisition and recognition of Lycoris spp. fingerprint patterns using artificial intelligence-enhanced electrochemical sensors

This study developed an AI-enhanced electrochemical sensing platform for the acquisition and recognition of fingerprint patterns from 17 Lycoris species. Differential pulse voltammetry (DPV) was employed to record the electrochemical fingerprints of the Lycoris pollen extracts using graphene oxide-modified screen-printed carbon electrodes. Principal component analysis (PCA) revealed distinct clustering and separation of species based on their fingerprints, with the first three PCs explaining 78.6 % of the total variance. A multilayer perceptron (MLP) neural network achieved an overall accuracy of 96.2 % in classifying the Lycoris species, while a support vector machine (SVM) model attained an accuracy of 94.8 %. The AI-based classification results showed high congruence with the traditional palynological analysis. This study demonstrates the potential of integrating electrochemical sensors with AI techniques for rapid, cost-effective, and automated plant species identification.

Hazard Identification and Risk Analysis of Liquid Effluent Treatment Plant Apply in Chemical Process Industry

The chemical process industry is one of the categories of highly polluting industries and generates strong wastewater of high COD along with hazardous waste which requires effective treatment and disposal/reuse of effluents. In this review, the various sources of wastewaters in the chemical industry are identified and the best available technologies to remove them are critically evaluated. The aim of the present research work was to determine the behavior of various parameters of the chemical wastewater. During the entire study evaluate, monitor, and check various environmental parameters whether they are complying with a given standard or not given by regulatory authority at chemical Industry,. The India based industry produced bulk drugs, fatty acids, fatty alcohol, food additives, personal care products, and others. The monitoring data of the effluent treatment plant will give information on the pollution control by the company and the management of waste. Overall analysis showed that there is no significant difference in pH, BOD, COD, and ammoniacal Nitrogen. The use of conventional treatment methods along with membrane reactors and advanced post-treatment methods resulting in a Coagulation wastewater treatment technology appears to be the best

Sem Studies on Spermoderm of some Species of &lt;i&gt;Medicago&lt;/i&gt; (Papilionoideae-Trifolieae)

Seeds of 9 species of Medicago have been investigated under light and scanning electron microscope to find out the systematic significance of spermoderm pattern. Under light microscope, the surface is smooth in all the species except M. monantha and M. orbicularis where it is tuberculate. Under scanning electron microscope, majority of species viz., M. laciniata , M. lupulina, M. minima, M. orbicularis. M. polymorpha var. vulgaris and M. × varia show tuberculate (papillose) pattern while M. edgeworthii, M. monantha and M. sativa show false reticulate, reticulate and rugulate patterns respectively. The nature of tubercules differs from species to species and thus spermoderm pattern can be used in the identification of plants at specific level.

Plant Taxonomy - Its Past Role and Future Lines of Action in India

The history of floristic and taxonomic research in India is briefly reviewed and the decline and revival of floristic studies in India is traced.Modern concepts in plant taxonomy are towards the synthesis of orthodox taxonomic practices and modern methodologies. There need not be any clash between the so called alpha and omega taxonomists. All data that can be readily scanned for the species is useful for the taxonomist. The only aspect that has to be considered is the utillty of classification for a specified purpose. A field, or forest botanist needs diagnostic keys based on superficial morphological characters for identification of plants in the field. Characters based on anatomy, embryology chromosome structure and number, palynology, plant alkaloids and protein serum analysis are useful tools for finding out the systematic position of plants of doubtful affinity; however,. these characters cannot be readily used in the field for identification of plants. The herbarium identification of plants is the simple method of retrieval of plant identity through standard specimens properly authenticated by an expert. It does not give legality for the concept of fixity of species as wrongly alluded to by some non-taxonomists, since Nomenclatural Type is a constituent element of a taxon and it is not necessarily the most representative element.Some of the lines where taxonomists could play a major role are the inventory listing of plants for the conservation of species, monitoring rate of decline and spread of species, establishment of botanical record centres, environmental education and collaboration with universities for reorientation of teaching methods.The necessity for floristic training is stressed and a syllabus drawn up.

Molecular Identification and Characterization of Novel Taxonomic Subgroups and New Host Plants in 16SrI and 16SrII Group Phytoplasmas and Their Evolutionary Diversity on Hainan Island, China.

Phytoplasmas are a group of plant prokaryotic pathogens distributed worldwide. To comprehensively reveal the diversity of the pathogens and the diseases they cause on Hainan, a tropical island with abundant biodiversity in China, a survey of phytoplasmal diseases was performed from 2009 to 2022. Herein, molecular identification and genetic analysis were conducted based on the conserved genes of phytoplasmas. The results indicated that phytoplasmas could be detected in 138 samples from 18 host plants among 215 samples suspected to be infected by the pathogens. The phytoplasma strains from 27 diseased samples of 4 host plants belonged to the 16SrI group and the strains from 111 samples of 14 hosts belonged to the 16SrII group. Among them, 12 plants, including important tropical cash crops such as Phoenix dactylifera, cassava, sugarcane, and Piper nigrum, were first identified as hosts of phytoplasmas on Hainan Island. Based on BLAST and iPhyClassifier analyses, seven novel 16Sr subgroups were proposed to describe the relevant phytoplasma strains, comprising the 16SrI-AP, 16SrI-AQ, and 16SrI-AR subgroups within the 16SrI group and the 16SrII-Y, 16SrII-Z, 16SrII-AB, and 16SrII-AC subgroups within the 16SrII group. Genetic variation and phylogenetic analysis indicated that the phytoplasma strains identified in this study and those reported previously on Hainan Island mainly belong to four 16Sr groups (including I, II, V, and XXXII) and could infect 44 host plants, among which the 16SrI and 16SrII groups were the prevalent 16Sr groups associated with 43 host plant species. The diversity of host plants infected by the phytoplasmas made it difficult to monitor and control their related diseases. Therefore, strengthening inspection and quarantine during the introduction and transit of the related phytoplasmal host crops would effectively curb the spread and prevalence of the phytoplasmas and their related lethal diseases.

HarvestMate Your Digital Companion in Agriculture

HarvestMate is a comprehensive agricultural platform designed to revolutionize farming practices through the integration of advanced technology. Leveraging a range of modules including agro weather forecasting, plant identification using the Trefle API, and an intuitive Agro Shop section, HarvestMate provides farmers and enthusiasts with powerful tools to enhance productivity and efficiency. The cornerstone of HarvestMate is its real-time agro weather forecasting feature, which delivers accurate and timely weather updates to users. By leveraging this data, farmers can make informed decisions about planting, harvesting, and crop management, ultimately optimizing yields and minimizing risks associated with adverse weather conditions another key component of HarvestMate is its plant identification module, powered by the Trefle API. This feature enables users to easily identify various plant species, empowering them with valuable knowledge about their crops and surrounding vegetation. Whether in the field or the garden, users can quickly access detailed information about plants, including their characteristics, growing requirements, and potential uses. Furthermore, HarvestMate boasts an integrated Agro Shop section, providing users with access to a curated marketplace featuring a wide range of agricultural products and services. From seeds and fertilizers to farming equipment and tools, users can explore and purchase essential items directly through the platform yields. HarvestMate is built on a robust technology stack, including HTML, CSS, Bootstrap, and JavaScript for the frontend, and Python with the Flask.

Two-Dimensional High-Performance Thin-Layer Chromatography with Bioautography for Distinguishing Angelicae Dahuricae Radix Varieties: Chemical Fingerprinting and Antioxidant Profiling.

Angelicae Dahuricae Radix (ADR) holds a prominent place in traditional medicine for its remarkable antioxidative, anti-allergic, and antiproliferative capabilities. Recognized within the Korean Pharmacopoeia (KP 12th), Angelica dahurica (Hoffm.) Benth. and Hook.f. ex Franch. and Sav. (AD) and Angelica dahurica var. formosana (H. Boissieu) Yen (ADF) serve as the botanical origins for ADR. Differentiating these two varieties is crucial for the formulation and quality control of botanical drugs, as they are categorized under the same medicinal label. This research utilized two-dimensional high-performance thin-layer chromatography (2D-HPTLC) to effectively distinguish AD from ADF. Additionally, a quantitative analysis reveals significant differences in the concentrations of key active constituents such as oxypeucedanin, imperatorin, and isoimperatorin, with AD showing higher total coumarin levels. We further enhanced our investigative depth by incorporating a DPPH bioautography, which confirmed known antioxidant coumarins and unearthed previously undetected antioxidant profiles, including byakangelicin, byakangelicol, falcarindiol in both AD and ADF, and notably, 2-linoleoyl glycerol detected only in AD as an antioxidant spot. This comprehensive approach affords a valuable tool set for botanical drug development, emphasizing the critical need for accurate source plant identification and differentiation in ensuring the efficacy and safety of herbal medicine products.

Do demographic factors impact plant knowledge and plant awareness disparity?

AbstractSince 1999, plant blindness, now known as plant awareness disparity (PAD), has gained great awareness. However, no study to date has explored the impact of multiple demographic factors, including those of an indigenous population, in understanding plant knowledge. Specifically, this study assessed how race, gender, rurality, and college type of general biology students influenced their self‐perceived plant knowledge and where that knowledge was learned. A total of 702 students across six different colleges, including three tribal and three non‐tribal colleges, completed the survey. The survey included demographic questions, five‐point Likert questions, and choose all that apply questions to assess students’ confidence in their plant knowledge, plant identification skills, where they learned that plant knowledge, and from whom they learned it. College type (tribal vs. non‐tribal) and race (American Indian/Alaskan Native vs. White) showed little differences across most analyses. However, rurality (rural vs. urban) and gender (male vs. female) were often significantly different (p ≤ 0.05). Similar findings were reflected in confidence in identifying specific plant categories. In most cases, participants disagreed when answering that they were confident in identifying categories of plants, with the only exception being gardening. The types of plants participants knew the most about were food, herbs, and foraging plants, which corresponded with gardening and foraging being the activities that taught them most about plants. Parent(s)/guardian(s) were the most important source of plant knowledge followed by school. The information in this study can aid educators, resource managers, and researchers in improving education, curriculum, and PAD.

Robust deep learning method for fruit decay detection and plant identification: enhancing food security and quality control.

This paper presents a robust deep learning method for fruit decay detection and plant identification. By addressing the limitations of previous studies that primarily focused on model accuracy, our approach aims to provide a more comprehensive solution that considers the challenges of robustness and limited data scenarios. The proposed method achieves exceptional accuracy of 99.93%, surpassing established models. In addition to its exceptional accuracy, the proposed method highlights the significance of robustness and adaptability in limited data scenarios. The proposed model exhibits strong performance even under the challenging conditions, such as intense lighting variations and partial image obstructions. Extensive evaluations demonstrate its robust performance, generalization ability, and minimal misclassifications. The inclusion of Class Activation Maps enhances the model's capability to identify distinguishing features between fresh and rotten fruits. This research has significant implications for fruit quality control, economic loss reduction, and applications in agriculture, transportation, and scientific research. The proposed method serves as a valuable resource for fruit and plant-related industries. It offers precise adaptation to specific data, customization of the network architecture, and effective training even with limited data. Overall, this research contributes to fruit quality control, economic loss reduction, and waste minimization.

Cannabis sativa Plant Identification and Its Look-Alikes

The purpose of this document is to provide an identification guide for Cannabis sativa to be used by growers and land managers by showing key factors to distinguish it from similar-looking plants. The general public and aspiring botanists may also use this document to see how a plant is defined botanically and how those characteristics can distinguish a plant of interest from other look-alike plants. Written by Cliff G. Martin and Zachary T. Brym, and published by the UF/IFAS Agronomy Department, March 2024.

Improved random forest classification model combined with C5.0 algorithm for vegetation feature analysis in non-agricultural environments

In response to the challenges posed by the high computational complexity and suboptimal classification performance of traditional random forest algorithms when dealing with high-dimensional and noisy non-agricultural vegetation satellite data, this paper proposes an enhanced random forest algorithm based on the C5.0 algorithm. The paper focuses on the Liaohe Plain, selecting two distinct non-agricultural landscape patterns in Shenbei New District and Changtu County as research objects. High-resolution satellite data from GF-2 serves as the experimental dataset. This paper introduces an ensemble feature method based on the bagging concept to improve the original random forest classification model. This method enhances the likelihood of selecting features beneficial to classifying positive class samples, avoiding excessive removal of useful features from negative samples. This approach ensures feature importance and model diversity. The C5.0 algorithm is then employed for feature selection, and the enhanced vegetation index (EVI) is utilized for vegetation coverage estimation. Results indicate that employing a multi-scale parameter selection tool, combined with limited field-measured data, facilitates the identification and classification of plant species in forest landscapes. The C5.0 algorithm effectively selects classification features, minimizing information redundancy. The established object-oriented random forest classification model achieves an impressive accuracy of 94.02% on the aerial imagery for forest classification dataset, with EVI-based vegetation coverage estimation demonstrating high accuracy. In experiments on the same test set, the proposed algorithm attains an average accuracy of 90.20%, outperforming common model algorithms such as bidirectional encoder representation from transformer, FastText, and convolutional neural network, which achieve average accuracies ranging from 84.41 to 88.33% in identifying non-agricultural artificial habitat vegetation features. The proposed algorithm exhibits a competitive edge compared to other algorithms. These research findings contribute scientific evidence for protecting agricultural ecosystems and restoring agricultural ecosystem biodiversity.

Design and test of target application system between rice plants based on light and tactile sensing

Excessive chemical spraying can lead to waste, damage rice plants, and reduce yield. To resolve this problem, the precise spraying of interplant areas through targeting methods was investigated in this study. The touch-sensing data for identification and positioning was extracted by the trigger rule of binocular diffuse reflection sensors. Wavelet transform decomposition is used to extract time-domain and frequency-domain features from identification data. These combined features build a rice plant identification model based on support vector machine. The model could determine whether the light sensing system was triggered by rice plants or weed. Positioning data was divided into several regions based on the light sensing system. Then, maximum voltage was extracted from the positioning regions. The relative position of the rice plants was determined by fitting previous coordinates and maximum values. Finally, the nozzle position was corrected by the lateral movement of robot arms to achieve the precise targeted spraying. Field performance tests showed that the targeted intermittent spraying had 12.78% and 17.66% less spraying coverage rates in the non-targeted root and interline areas, respectively, and 21.9% more spraying coverage rates in the targeted interplant areas. The overall spraying dosages were 7.81 and 9.41 L for the targeted intermittent and non-targeted continuous spraying, respectively; the spraying dosage saved was 18%. The targeting application system proposed in this paper can achieve a significant reduction in chemical dosage. This research results provide a practical method for reduced herbicide application in rice paddies.

Automated Medicinal Plant Identification and Use Case Generation: A Convolutional Neural Network-Xception Approach

Abstract: In the realm of botany, pharmacology, and herbal medicine, the identification of medicinal plants stands as a crucial yet labor-intensive endeavor. This project presents a pioneering approach to automate plant identification through the utilization of advanced deep learning techniques, specifically employing the Xception architecture within a Convolutional Neural Network (CNN). The methodology involves the acquisition of plant images, followed by preprocessing and dimension reduction to 299x299 pixels. Subsequently, the model undergoes rigorous training, achieving commendable accuracies of approximately 85% in training, 93% in validation, and 94% in testing phases. The trained model is then deployed through a user-friendly web interface, allowing seamless interaction for uploading images and receiving comprehensive plant classification results. Leveraging Flask for backend integration, this system bridges the gap between cutting-edge technology and botanical expertise, enabling researchers, botanists, pharmacologists, and herbalists to expedite plant identification processes with heightened accuracy and efficiency. Furthermore, this innovation not only streamlines identification tasks but also provides detailed insights into the diverse applications and attributes of medicinal plants, thereby fostering advancements in research, conservation, and utilization for the betterment of human health and well-being..

Medicinal Plant Identification using Machine Learning

Medicinal plants play a crucial role in traditional and modern medicine due to their properties. In this study, we propose the identification of medicinal plants using machine learning. The proposed system comprises several key components: data collection, feature extraction, model training, and prediction. Initially, a comprehensive dataset of medicinal plant images is gathered from databases. Next, relevant features such as leaf shape, texture, and colour are extracted from images using image processing techniques. Subsequently, ML algorithms such as Convolutional Neural Networks (CNNs) are employed to train a classification model on the extracted features. The trained model is then capable of accurately identifying medicinal plants from input images. To facilitate user interaction, a user-friendly interface may be developed, allowing users to upload images and receive instant identification results. Furthermore, the system's performance is evaluated in real-world scenarios to assess its practical utility and reliability. Overall, the proposed automated medicinal plant identification system represents a significant advancement in leveraging ML technology to streamline the identification process

Decoding Evolution of Rubioideae: Plastomes Reveal Sweet Secrets of Codon Usage, Diagnostides, and Superbarcoding.

Galium genus belongs to the Rubiaceae family, which consists of approximately 14,000 species. In comparison to its well-known relatives, the plastomes of the Galium genus have not been explored so far. The plastomes of this genus have a typical, quadripartite structure, but differ in gene content, since the infA gene is missing in Galium palustre and Galium trfidum. An evaluation of the effectiveness of using entire chloroplast genome sequences as superbarcodes for accurate plant species identification revealed the high potential of this method for molecular delimitation within the genus and tribe. The trnE-UUC-psbD region showed the biggest number of diagnostides (diagnostic nucleotides) which might be new potential barcodes, not only in Galium, but also in other closely related genera. Relative synonymous codon usage (RSCU) appeared to be connected with the phylogeny of the Rubiaceae family, showing that during evolution, plants started preferring specific codons over others.

Medicinal Plant Identification using Machine Learning Algorithm

The identification of medicinal plants plays a crucial role in various fields including pharmacology, traditional medicine, and biodiversity conservation. Traditional methods of plant identification are often time-consuming, labor-intensive, and require expertise in botanical taxonomy. In recent years, the application of Convolutional Neural Networks (CNNs) has shown promising results in automating the process of plant species recognition. This paper provides a comprehensive review of recent advances in medicinal plant identification using CNNs. This study discuss the methodology, challenges, and opportunities associated with CNN-based approaches, as well as their potential applications in pharmacological research and healthcare. Furthermore, we highlight key datasets, architectures, and performance metrics used in CNN-based plant identification systems. Finally, we identify future research directions and potential areas for improvement in this rapidly evolving field