Leaf Texture Research Articles

First report of Tomato leaf curl New Delhi virus in Türkiye

A leaf curl disease has been observed frequently in greenhouses where cucumber (Cucumis sativus), melon (Cucumis melo) and squash (Cucurbita pepo) are produced in Antalya since 2019. The infected plants showed symptoms including apical leaf curl, vein swelling, severely stunted, wrinkled leaves, fruit shape and texture disorder and a conspicuous mosaic pattern (Figure 1-5). These symptoms are similar to those caused by Tomato leaf curl New Delhi virus (ToLCNDV), an important member of the genus Begomovirus, family Geminiviridae. ToLCNDV is transmitted by Bemisia tabaci in a persistent circulative manner, causing serious damage to a wide variety of plant species, especially in the Solanaceae and Cucurbitaceae families (Briddon, 2015). ToLCNDV was first identified on solanaceous crops in India (Padidam et al., 1995) but the virus is recognised as an emerging threat worldwide due to the severity of the disease and its increasing prevalence. Outbreaks have recently occurred in countries in Africa, Asia and Europe (European and Mediterranean Plant Protection Organization, 2023). Samples were collected from eight adjoined greenhouses in Antalya, four growing cucumber, two melon and two squash. Three leaf samples and one fruit sample were collected individually from a diseased plant in each of the greenhouses, that is 32 samples in total. Total nucleic acid was extracted from the leaf and fruit samples and analysed by PCR with specific ToLCNDV primers (ToA1-F and ToA1-R) which amplify a 504 bp fragment of viral DNA-A (Saez et al., 2016). The following conditions were used for PCR: 95°C for 5 min; 35 cycles of 30 s at 95°C, 45 s at 55°C and 45 s at 72°C, followed by a final 72°C extension step for 10 min. Sequences were obtained from samples from each of the eight plants and were found to be identical (GenBank Accession No. MZ458535). BLAST analysis showed that there was 99% identity with a ToLCNDV isolate (MH475397). Antalya is a major area of greenhouse and seed production in Türkiye and the Mediterranean basin. ToLCNDV and other plant viruses are serious threats to solanaceous and cucurbit crops grown in the region since these crops may be infected through mechanical contact, seeds and insects (Kil et al., 2020). Quarantine remains the most effective way to prevent and control such viral infections. Diseased plants in the affected greenhouses were destroyed and the houses sanitised using solarization and disinfectant. Further surveys were done in 2020 and 2021 in the affected and neighbouring greenhouses and potentially virus-infected plants (~ 84 cucurbit samples) were tested by PCR as described above. No ToLCDV infection was found indicating that the virus had been eradicated. To our knowledge, this is the first report of ToLCNDV in Türkiye.

Vertical plants: Plant design of Living walls – evaluation of 34 perennials in a textile based Living wall over a three years experiment

IntroductionUrban green can be complemented by Living walls (LW). Knowledge of LW, including technique or their cooling effects, is well discussed, but little published data on plant diversity, design and development in LWs exists. The plants themselves determine whether LWs achieve their intended benefits. However, LW plants are exposed to extreme conditions such as temperature or drought stress.Material and methodsTherefore, we observed plant development in a textile-based LW (mat) over a three-year experiment under a temperate oceanic climate in the south west of Germany. The aim was to establish higher plant diversity for use in LWs. We chose 34 perennials (shrubs, ferns, grasses, and geophytes) that require high soil moisture. The mat was soil-free and had to be overwatered with a nutrient solution. The perennials were grouped in the plant module “cascade” (tall, hanging plants) and “ground cover” (low-spreading plants). We created four experimental walls exposed to the south, north, west, and east and adapted the plant modules to the lighting conditions of the experiment wall. The modules were pre-cultivated and attached to the experimental walls in a randomised design and repetition of four. We determined the visual attractiveness and additional parameters of individual plants.ResultsWe observed that Tellima grandiflora ‘Rubra’, Waldsteinia ternata, Pachysandra terminalis, and Heuchera Hybride ‘Purple Petticoats’ were the most attractive all year. Ajuga tenorii ‘Mauro’, Alchemilla caucasica, Hosta sieboldii ‘Harry van Trier’, Glechoma hederacea, and Geum coccineum ‘Carlskaer’ showed a nice ornamental effect and flowering during summer. The ferns and Waldsteinia ternata showed delayed growth but nice leaf texture gradually.Discussion and conclusionWe saw differences in winter survival rates depending on minimum temperature in winter. The tested plants developed a special vertical growth form and height. We observed various results at different expositions but found suitable species for each exposition. With these results, we derived a table of plants along with their suitability for LWs and determining conditions.

Morpho-metric Analysis of Leaf and Fruit of Selected Mulberry Accessions: A Preliminary Measure for Diversity Analysis

Morus spp. exhibits wide variation in leaf morphology among different species and accessions within the same species. Some of the important silent morphological characteristics pertaining to mulberry leaf and fruit have been selected for the current study. Among all the ten selected genotypes ovate leaf shape was recorded to be the most common ones. Maximum leaf size of leaf was recorded in case of genotype S-1635 as 187cm and minimum in case of Kanva-2 as 28cm. Most of the genotypes were recorded with serrated to parted margins except C-4 with parted margin and smooth leaf texture with exceptions of coarse leaf in C-4, Chinese white and C-2038. Two most common types of leaf apex have been recorded as acuminate and acute with cordate, hastate and truncate leaf base. Maximum leaf length was recorded in S-1635 as 17 cm followed by Chakmajra as 15 cm and S-13 as 14 cm and 7 cm was recorded in C-4 and Kanva-2 and maximum in S-1635 as 11cm followed by S-13 and chakmajra as 8 cm and least in G-4 and Kanva-2 as 4 cm. Similarly maximum actual leaf area was recorded in genotype S-1635 as 71 cm2 and minimum in genotype C-2038 as 19.5 cm2. Fresh and dry weight of the leaf was recorded to be maximum in S-1635 as 11.4 g and minimum in Kanva-2 as 3.5 g and V-1 as 5.2 g respectively. In addition to fresh and dry leaf weight, moisture percentage and moisture retention capacity was recorded to be maximum of 72.4% in C-4 and minimum of 54.26% in S-1635 and maximum moisture retention capacity of 64% was recorded for G-4 genotype and minimum of 50% in C-2038. Maximum stomatal frequency was observed to be highest of 156 mm2 was recorded in S-1635 and least in Chinese white as 84 mm2 and stomatal index of 16% in V-1 and least in genotype S-13 as 11.1% and Cystolyth frequency was observed to be highest S-13 as 52% and minimum in genotype C-2038 as 24%. Thus, the current study could be used by plant breeders for genetic characterization and evaluation of different genotypes.

Response of Kentucky Bluegrass Turfgrass to Plant Growth Regulators

Plant growth regulators (PGRs) are widely used in turfgrass management. This study aimed to find the influence of different rates of PGRs on Kentucky bluegrass visual quality. Six PGRs were applied, Trinexapac Ethyl, Paclobutrazol, Flurprimidol, Mefluidide, Ethephon, and Gibberellic Acid. The measurement of the leaf color was performed using a spectrophotometer. The turfgrass visual quality was judged using a visual rating system. Trinexapac Ethyl and Flurprimidol applications improved the overall appearance of turfgrass. Paclobutrazol and Gibberellic Acid decreased the overall appearance of investigated Kentucky bluegrass cultivars. The leaf texture assessment was only improved by Gibberellic Acid. The color assessment was enhanced with Paclobutrazol but deteriorated with Gibberellic Acid. PGRs affected the wavelength in a range of 520 to 630 nm. Gibberellic Acid caused lighter leaves with higher green and yellow hues. Paclobutrazol caused darker leaves with a lower green and a reddish hue. Trinexapac Ethyl application resulted in a more reddish hue. PGR rates also affected the visual quality of Kentucky bluegrass turfgrass.

Plant Species Classification Using Leaf Edge Feature Combination with Morphological Transformations and SIFT Key Point

This paper presents a new approach to plant classification by using leaf edge feature combination with Morphological Transformations and defining key points on leaf edge with SIFT. There are three steps in the process. Image preprocessing, feature extraction, and image classification. In the image preprocessing step, image noise is removed with Morphological Transformations and leaf edge detect with Canny Edge Detection. The leaf edge is identified with SIFT, and the plant leaf feature was extracted by CNN according to the proposed method. The plant leaves are then classified by random forest. Experiments were performed on the PlantVillage dataset of 10 classes, 5 classes of healthy leaves, and 5 classes of diseased leaves. The results showed that the proposed method was able to classify plant species more accurately than using features based on leaf shape and texture. The proposed method has an accuracy of 95.62%.

Niche evolution in a northern temperate tree lineage: biogeographical legacies in cork oaks (Quercus section Cerris).

Cork oaks (Quercus section Cerris) comprise 15 extant species in Eurasia. Despite being a small clade, they display a range of leaf morphologies comparable to the largest sections (>100 spp.) in Quercus. Their fossil record extends back to the Eocene. Here, we explore how cork oaks achieved their modern ranges and how legacy effects might explain niche evolution in modern species of section Cerris and its sister section Ilex, the holly oaks. We inferred a dated phylogeny for cork and holly oaks using a reduced-representation next-generation sequencing method, restriction site-associated DNA sequencing (RAD-seq), and used D-statistics to investigate gene flow hypotheses. We estimated divergence times using a fossilized birth-death model calibrated with 47 fossils. We used Köppen profiles, selected bioclimatic parameters and forest biomes occupied by modern species to infer ancestral climatic and biotic niches. East Asian and Western Eurasian cork oaks diverged initially in the Eocene. Subsequently, four Western Eurasian lineages (subsections) differentiated during the Oligocene and Miocene. Evolution of leaf size, form and texture was correlated, in part, with multiple transitions from ancestral humid temperate climates to mediterranean, arid and continental climates. Distantly related but ecologically similar species converged on similar leaf traits in the process. Originating in temperate (frost-free) biomes, Eocene to Oligocene ranges of the primarily deciduous cork oaks were restricted to higher latitudes (Siberia to north of Paratethys). Members of the evergreen holly oaks (section Ilex) also originated in temperate biomes but migrated southwards and south-westwards into then-(sub)tropical southern China and south-eastern Tibet during the Eocene, then westwards along existing pre-Himalayan mountain ranges. Divergent biogeographical histories and deep-time phylogenetic legacies (in cold and drought tolerance, nutrient storage and fire resistance) thus account for the modern species mosaic of Western Eurasian oak communities, which are composed of oaks belonging to four sections.

Nondestructive Determination of Leaf Nitrogen Content in Corn by Hyperspectral Imaging Using Spectral and Texture Fusion

The nitrogen content is an important indicator affecting corn plants’ growth status. Most of the standard hyperspectral imaging-based techniques for nondestructive detection of crop nitrogen content use a single feature as the input variable of the model, which reduces the generalization ability of the prediction model. To this end, a prediction model for the nitrogen content of corn leaves based on the fusion of image and spectral features is proposed. In this study, corn leaves at the modulation stage were studied, samples with different nitrogen levels were numbered, and their hyperspectral data in the wavelength range of 400~1100 nm were collected. The average spectrum of the models was used as valid spectral information. First-order derivatives, standard normal variables transformation (SNV), Savitzky-Golay (S-G) smoothing, and normalization were selected to preprocess the spectral features. The CARS-SPA algorithm was used to screen sensitive spectral variables. The gray level co-currency matrix (GLCM) was chosen to extract the texture image features of the test samples. Corn leaf spectral and texture image features were fused and modeled as target features. Partial least squares regression (PLSR) and support vector machine regression (SVR) were used to predict corn leaves’ nitrogen content. The results showed that the image and spectral-based fusion models improved the prediction performance to some extent compared to the univariate models. The PLSR model based on feature fusion predicted the best results, in which the RP2 and RMSEP were 0.987 and 0.047. This method provides a reliable theoretical basis and technical support for developing nondestructive and accurate detection of nitrogen content in corn leaves.

Morphological Character of Clove “Raja” (Syzygium aromaticum L.), Endemic to Maluku, Indonesia

Clove “Raja” is one of the local Maluku clove germplasm, which has characteristics similar to cultivated cloves and wild types. Until now, very limited information that are available on the morphological character of clove “Raja”. This study aims to provide basic information on the morphological diversity of “Raja”. The study was conducted at the location of the distribution of cloves “Raja” in Mamala village, Leihitu sub-district, Central Maluku district, Maluku province, in June-August 2022. The descriptors used referred to Tropical Fruit Descriptors, with some modifications. The clove “Raja” that were characterized belonged to the farmers and consisted of 30 accessions of cloves that were over twenty years old. The characterization variables included the characters of trees, stems, branches, leaves, flowers, fruits, and seeds. The results of Hierarchical Cluster Analysis (HCA) on 30 plant samples based on 54 morphological characters obtained two accession groups with a dissimilarity coefficient of 41%. The results of the Principle Component Analysis (PCA) got a total diversity of 70.5% where the first group consisted of accessions of cloves “Raja” group I having identifiable characters in the form of leaf area, leaf length, leaf width, and leaf tip shape; while the second group of clove accessions of “Raja” group I in the form of stem circumference, petiole length, flower length, fruit length, fruit width, and fruit weight. Characteristics of accession of “Raja” cloves group II had distinctive morphological traits in the form of crown shape, upper surface of leaves, lower surface of leaves, leaf thickness, leaf texture, old leaf color, shoot color, leaf tip color, leaf aroma, leaf spiciness, flower stalk length, and seed color.

Reaumuria soongorica-plant model to understand drought adaptive mechanisms of xerophyte and their potentials in improving stress tolerance in plants

Reaumuria soongorica plays critical role in withstanding wind-induced soil erosion and combating desertification due to its unique drought adaptive networks involved in physiological, morphological, biochemical, and molecular biological levels. This review was conceived to summarize the most updated information on drought adaptive mechanisms of R. soongorica to formulate valuable strategies for non-xerophytes crop species to be drought tolerant. Research indicates that R. soongorica can be drought resistant via posing a high root to shoot ratio, having salt secreting gland, subsidized stomata, hard leaf texture, pallet leaf shape, high seeds viability, actively working antioxidative enzymes, secondary metabolites, phytohormones, and differentially expressed drought resistant genes. These characteristics interlink at morpho-physiological, biochemical, metobolic, molecular, and genetic level in R. soongorica to adapt the extreme abitotic stress conditions in desert regions as a plant model in xerophyte. The potentials of using the genetic elements in R. soongorica to produce drought tolerant crop species for yield production on growing on marginal lands could be vital for maintaining future food security. However, functional gene cloning and their transformation in crop species should be conducted as pre-requisite. Key words: Abiotic stress, Crop improvement, Drought adaptive mechanisms, Reaumuria soongorica, Xerophytes

Low-velocity impact response of composite sandwich structure with grid–honeycomb hybrid core

Grid structures have great potential for engineering application, inspired by the leaf texture, the rectangular grid is innovatively added to the honeycomb to form the grid-honeycomb hybrid core. The low-velocity impact response of the composite sandwich structure with grid–honeycomb hybrid core was investigated by experimental and numerical simulation. Low-velocity impact tests with 30 J energy were conducted of the sandwich panel to analyze the mechanical response and damage morphology at typical locations (intersection, rib, and center). The results show that the impact resistance at the intersection was the strongest, the peak load, damage threshold load, and initial stiffness at the intersection were 14.74%, 15.54%, and 16.06% higher, and the maximum displacement and residual displacement were 12.09% and 33.71% lower, respectively than those at the rib, and the center was the weakest. Compared with honeycomb sandwich panel, the impact resistance of unit mass at the intersection and rib was stronger and the internal damage was smaller. In addition, the parametric study of the structural parameters of sandwich panel was conducted. The grid thickness had a significant effect on the impact resistance, while the effects of honeycomb wall thickness and honeycomb unit cell diameter were smaller and had almost no effect on initial stiffness and energy absorption. Finally, the impact resistance efficiency analysis was performed to obtain the optimal design area of structural parameters to provide design guidance.

Characterization of Some Cichorium Taxa Grown under Mediterranean Climate Using Morphological Traits and Molecular Markers

The verification of taxonomic identities is of the highest significance in the field of biological study and categorization. Morpho-molecular characterization can clarify uncertainties in distinguishing between taxonomic groups. In this study, we characterized five local taxa of the genus Cichorium using morphological and molecular markers for taxonomic authentication and probably future genetic improvement. The five Cichorium taxa grown under the Mediterranean climate using morphological traits and molecular markers showed variations. The examined taxa showed a widespread range of variations in leaf characteristics, i.e., shape, type, texture, margin, and apex and cypsela characteristics i.e., shape, color, and surface pattern. The phylogenetic tree categorized the Cichorium intybus var. intybus and C. intybus var. foliosum in a single group, whereas C. endivia var. endivia was grouped separately. However, C. endivia var. crispum and C. endivia subsp. pumilum were classified as a cluster. The recorded variance between classes using the molecular markers SCoT, ISSR, and RAPD was documented at 34.43%, 36.62%, and 40.34%, respectively. Authentication using molecular tools proved the usefulness of a dichotomous indented key, as revealed by morphological identification. The integrated methodology using morphological and molecular assessment could support improved verification and authentication of the various taxa of chicory. It seems likely that the Egyptian chicory belongs to C. endivia subsp. pumilum.

Self-Supervised Plant Phenotyping by Combining Domain Adaptation with 3D Plant Model Simulations: Application to Wheat Leaf Counting at Seedling Stage.

The number of leaves at a given time is important to characterize plant growth and development. In this work, we developed a high-throughput method to count the number of leaves by detecting leaf tips in RGB images. The digital plant phenotyping platform was used to simulate a large and diverse dataset of RGB images and corresponding leaf tip labels of wheat plants at seedling stages (150,000 images with over 2 million labels). The realism of the images was then improved using domain adaptation methods before training deep learning models. The results demonstrate the efficiency of the proposed method evaluated on a diverse test dataset, collecting measurements from 5 countries obtained under different environments, growth stages, and lighting conditions with different cameras (450 images with over 2,162 labels). Among the 6 combinations of deep learning models and domain adaptation techniques, the Faster-RCNN model with cycle-consistent generative adversarial network adaptation technique provided the best performance (R2 = 0.94, root mean square error = 8.7). Complementary studies show that it is essential to simulate images with sufficient realism (background, leaf texture, and lighting conditions) before applying domain adaptation techniques. Furthermore, the spatial resolution should be better than 0.6 mm per pixel to identify leaf tips. The method is claimed to be self-supervised since no manual labeling is required for model training. The self-supervised phenotyping approach developed here offers great potential for addressing a wide range of plant phenotyping problems. The trained networks are available at https://github.com/YinglunLi/Wheat-leaf-tip-detection.

Leaf-based Classification of Important Indigenous Tree Species by Different Feature Extraction Techniques and Selected Classification Algorithms

The machine learning algorithms, namely, k-Nearest Neighbor (KNN), Support Vector Machine (SVM), Back-Propagation (BP) networks, and Convolutional Neural Networks (CNN) are four of the mostly used classifiers. Different sets of features are required as input in different application domains. In this paper, a set of significant leaf features and classification model was determined with a high accuracy in classifying important indigenous tree species. Leaf images were acquired using a scanner to control the image quality. The image dataset was then duplicated into two sets. The first set was labeled with their correct classes, preprocessed, and segmented in preparation for feature extraction. The leaf features extracted were leaf shape, leaf color, and leaf texture. Then, training and classification was done by KNN, SVM, and BP networks. On the other hand, the second set was unlabeled for training and classification by CNN. A CNN model was built and chosen with the best training and validation accuracy and the least training and validation loss rate. The study concluded that using all three leaf features for classification by BP networks resulted in a 93.48% accuracy with training done by supervised learning. However, the CNN achieved a high accuracy rate of 98.5% making it the best approach for classification of tree species using digital leaf images in the context of this study.

Black rot disease incited by Indian race 1 of Xanthomonas campestris pv. campestris in Brassica juncea L. cv. Pusa Bold in India.

Mustard (Brassica juncea L.) is an important oil seed crop in the Brassicaceae family. It is widely cultivated in India for its edible leaves, oil and medicinal properties. In January 2022, we noticed necrotic symptoms typical black rot disease on Brassica juncea (L.) cv. Pusa Bold grown in Indian Agricultural Research Institute, India. Initially, chlorotic lesions emerged on the leaf margin, which progressed to angular V-shaped necrotic lesions and blackened veins. Disease progression became a necrotic appearance in the leaf results browning and papery leaf texture appeared. The suspected causal agent was isolated from three different diseased plants of Pusa Bold on nutrient sucrose agar medium that formed pale yellow, mucoid, and fluidal colonies. Three representative isolates originated from three different plants were sub-cultured on YGCA medium. These isolates are Gram-negative, oxidase negative, KOH positive, nonfluorescent on King's Medium B agar, and positive for starch hydrolysis test (Schaad and White 1974). The 16S ribosomal RNA gene and avirulence genes - AvrBs1 and AvrGf1 were amplified and sequenced in these three isolates with other Xanthomonas campestris pv. campestris (Xcc) isolates. The DNA sequence analysis revealed that these isolates are within the species of X. campestris. The race 1 specific marker namely xcc-b100_4389 was used to characterized the race by detection of 1090bp fragment respectively from gDNA of Xcc isolates (Rubel et al., 2017). The pathogenicity of these isolates was tested twice on youngest leaves of 30-day-old plants of Pusa Bold to convey Koch postulates. Inoculum of three isolates were prepared in nutrient broth at 28°C for 48-h. The pathogenicity test was conducted by small scissors dipped in a bacterial suspension (~ 108 cfu/ml) to cut leaf near margins at 10 points per leaf and the three youngest leaves per plant with three replications. The number of infected points per leaf and the severity of symptoms were assessed 15 and 30 days after inoculation (Singh et al., 2011; 2016). The chlorotic lesions with V-shaped symptoms were appeared on all inoculated plants after 15 and 30 dpi (days post-inoculation). The bacteria were reisolated from inoculated plants and has the same identity as original isolates by using 16S rRNA, avr genes and race 1 specific marker PCR, thereby confirming Koch's postulates. The bacterial inoculation was repeated and the same symptoms appear. Most of the crucifers are infected with black rot disease e.g., cauliflower, cabbage, Brussels, sprout etc. (Vicente et al., 2001). The nucleotide BLAST analysis of 16S rRNA, AvrBs1, AvrGf1 showed a 100% identity with different Xcc strains reported from Germany (B100; AM920689), Brazil (ATCC 33913; AE008922), India (Xcc-C7; CP077958), France (CFBP 5817; CM002673) and China (8004; CP000050) (Singh et al. 2022). Whilst, the nBLAST analysis of xcc-b100_4389 showed 100% nucleotide identity with Xcc race 1 (B100; AM920689), Germany. The sequences were deposited in GenBank (16S rRNA: OM839780; AvrBs1: OM994397; AvrGf1: OM994398; xcc-b100_4389: OM994399). The XccAK1 strain (ITCCBH_0014) was deposited in Indian Type Culture Collection, ICAR-IARI, New Delhi, India. Presently, it is a first report of necrotic black rot on B. juncea cv. Pusa Bold incited by Xcc race 1, India. Previous research reported the black rot disease on other species of the Brassica genus e.g., B. oleracea, and B. napus in Serbia (Popovic et al., 2013) and Argentina (Gaetan et al., 2005).

Intelligent image analysis recognizes important orchid viral diseases.

Phalaenopsis orchids are one of the most important exporting commodities for Taiwan. Most orchids are planted and grown in greenhouses. Early detection of orchid diseases is crucially valuable to orchid farmers during orchid cultivation. At present, orchid viral diseases are generally identified with manual observation and the judgment of the grower's experience. The most commonly used assays for virus identification are nucleic acid amplification and serology. However, it is neither time nor cost efficient. Therefore, this study aimed to create a system for automatically identifying the common viral diseases in orchids using the orchid image. Our methods include the following steps: the image preprocessing by color space transformation and gamma correction, detection of leaves by a U-net model, removal of non-leaf fragment areas by connected component labeling, feature acquisition of leaf texture, and disease identification by the two-stage model with the integration of a random forest model and an inception network (deep learning) model. Thereby, the proposed system achieved the excellent accuracy of 0.9707 and 0.9180 for the image segmentation of orchid leaves and disease identification, respectively. Furthermore, this system outperformed the naked-eye identification for the easily misidentified categories [cymbidium mosaic virus (CymMV) and odontoglossum ringspot virus (ORSV)] with the accuracy of 0.842 using two-stage model and 0.667 by naked-eye identification. This system would benefit the orchid disease recognition for Phalaenopsis cultivation.

Classification of nutrient deficiency in oil palms from leaf images using convolutional neural network

Oil palm is a perennial plant that thrives well in tropical climate. Apart from humid environment, the plant also requires a wide variety of nutrients. Any deficiencies will directly affect its growth and palm oil production. These can often be detected from the change of leaf colour and texture. Deviations from the standard dark green colour indicates lack of certain nutrients. Therefore, this study proposes convolutional neural network (CNN) to classify nutrient deficiency in oil palms using leaf images. A total of 180 leaf images are acquired using standardized protocol. The samples are evenly distributed into healthy, nitrogen-deficient, and potassium-deficient groups. Residual network (ResNet)-50, visual geometry group-16 (VGG16), Densely connected network (DenseNet)-201, and AlexNet are trained and tested using the randomized samples. Each attained classification accuracies of 96.7%, 100%, 98.3%, and 100% respectively. Despite yielding similar performance, AlexNet is the more computational efficient architecture with less convolutional layers compared to VGG-16.

KLASIFIKASI TUMBUHAN ANGIOSPERMAE MENGGUNAKAN ALGORITMA K-NEAREST NEIGHBOR BERDASARKAN PADA BENTUK DAUN

About 250,000 living plant species are plants of the Angiosperms group. The diversity of Angiosperm plants in Indonesia makes it difficult for someone to carry out the process of identifying plants into the monocotyledonous or dicotyledonous class. This is the background for doing this research by classifying Angiosperms plants using the K-Nearest Neighbor algorithm. Research related to classifying manga plants using the Backpropagation algorithm with feature extraction using GLCM produces an accuracy of 49%. Furthermore, the classification of plants using the K-Nearest Neighbor algorithm with leaf morphological features extraction resulted in an accuracy of 92%. There is also a classification of citrus plants using the K-Nearest Neighbor algorithm with leaf texture feature extraction using GLCM resulting in an accuracy of 81.48%. In this study, the K-Nearest Neighbor classification algorithm is used with feature extraction using a population matrix with the aim of examining the level of classification accuracy using population matrix feature extraction. The data used is a digital leaf image which will extract its shape features using a population matrix feature by doing image pre-processing and detection first. The data is then divided into training data of 70%, and test data of 30%. The results of this study are the accuracy of the test data obtained by 85% with the number of neighbors k=1. After testing, an evaluation of the model will be carried out using a confusion matrix, which consists of accuracy, precision, recall, and f-1 score.

Morphological, ecological, and molecular phylogenetic approaches reveal species boundaries and evolutionary history of Goodyeracrassifolia (Orchidaceae, Orchidoideae) and its closely related taxa.

Species delimitation within the genus Goodyera is challenging among closely related species, because of phenotypic plasticity, ecological variation, and hybridization that confound identification methods based solely on morphology. In this study, we investigated the identity of Goodyeracrassifolia H.-J.Suh, S.-W.Seo, S.-H.Oh & T.Yukawa, morphologically similar to Goodyeraschlechtendaliana Rchb.f. This recently described taxon has long been known in Japan as "Oh-miyama-uzura" or "Gakunan" and considered a natural hybrid of G.schlechtendaliana and G.similis Blume (= G.velutina Maxim. ex Regel). Because the natural hybrid between G.schlechtendaliana and G.similis was described as G.×tamnaensis N.S.Lee, K.S.Lee, S.H.Yeau & C.S.Lee before the description of G.crassifolia, the latter might be a synonym of G.×tamnaensis. Consequently, we investigated species boundaries and evolutionary history of G.crassifolia and its closely related taxa based on multifaceted evidence. Consequently, morphological examination enabled us to distinguish G.crassifolia from other closely related species owing to the following characteristics: coriaceous leaf texture, laxly flowered inflorescence, long pedicellate ovary, large and weakly opened flowers, and column with lateral appendages. Ecological investigation indicates that G.crassifolia (2n = 60) is agamospermous, requiring neither pollinators nor autonomous self-pollination for fruit set, whereas G.schlechtendaliana (2n = 30) is neither autogamous nor agamospermous but is obligately pollinator-dependent. MIG-seq-based phylogenetic analysis provided no evidence of recent hybridization between G.crassifolia and its close congeners. Thus, molecular phylogeny reconstructed from MIG-seq data together with morphological, cytological, and ecological analyses support the separation of G.crassifolia as an independent species.

Shelf Life of Greenhouse- and Garden-grown Kale in Nitrogen-enriched and Nonenriched Packaging

Over half of global food waste occurs in retail and households, highlighting the importance of improving shelf life. Many factors affect shelf life, including storage temperature, harvest time, processing method, and packaging. Modified atmosphere packaging (MAP), such as nitrogen (N2), has been used to improve the shelf life of produce. This study aimed to determine the effect of nitrogen-enriched packaging on the shelf life of greenhouse- and garden-grown kale in raised beds outdoors. Five kale cultivars (Black Magic, Darkibor, Lacinato, Red Russian, and Westlander) were grown in the greenhouse, and four cultivars (Curly Roja, Dwarf Green Curled, Meadowlark, and Vates) outdoors in raised beds, harvested and stored in nitrogen-enriched or nonenriched bags for 6 days. Leaf water content, water activity, color, visual score, and texture were measured for each replicate. Nitrogen-enriched packaging did not affect the kale shelf life. Garden-grown kale exhibited significantly lower water activity (0.979 vs. 0.999) and noticeably lower water content (88.6 vs. 90.6%) than greenhouse-grown kale. The cultivars were significant for all factors tested except for texture on day 4 and change in light to dark (Δ L*) and blue to yellow (Δ b*) color ratios. At the end of the study, cultivars Darkibor and Curly Roja had the highest visual score (4.4) and texture (305 g), respectively. The high performance of ‘Darkibor’ and ‘Curly Roja’ in visual score and texture may be due to decreased (Δ L*) and (Δ b*) values and decreased water content and water activity values. Future breeding efforts focused on the shelf life of kale should use the top-performing cultivars identified in this study and a diverse genetic population tested in a range of environments to develop cultivars with a longer shelf life.

Evaluasi jenis dan penataan tanaman median jalan Sunset Road, Kuta untuk keselamatan pengendara

This study aims to evaluate the type and arrangement of plants on the median of Sunset Road with a length of 1,561 m which is divided into 7 segments based on road characteristics and driver safety criteria. The survey method with a qualitative descriptive analysis approach and data collection techniques in the form of observation, interviews and literature study were used in this study. The results of the evaluation showed that 12.5% of plant species were categorized as unsuitable and potentially dangerous to motorists, 50% were suitable and 37.5% were very suitable to be planted on the Sunset Road median. Plants in the median of the road should have more than 1 function, based on each function, 93.8% of plants on Sunset Road have a directing function, 62.5% have a function as a vehicle light blocking, 56.5% have a separator function and 18.8% of plants have a safety function. Completeness of plant composition in terms of leaf texture, height and color in each segment ranged from 56-89%. In addition, improper arrangement was also found in several segments, especially segments 2-5. It can be concluded that there is a mismatch of species and plant arrangement in the median of Sunset Road in terms of the driver safety criteria used in this study.