Species Recognition Research Articles

Linker Installation in a Metal-Organic Framework for Enhanced Quantitative Redox Species Recognition.

Linker installation has proven to be an effective strategy for introducing diverse functional groups into metal-organic frameworks (MOFs). Reductants and oxidants are found in various environments, but their accumulation poses a danger due to their high reactivity, necessitating prompt monitoring instantly, particularly in natural environments and industrial processes. In this study, a series of redox-active dyes were successfully incorporated into a flexible Zr-based MOF, PCN-700, through linker installation strategy. Notably, both the reduction of PCN-700-Resazurin towards oxidants and oxidation of PCN-700-Amplex Red towards reductants result in the formation of PCN-700-Resorufin, which exhibit visible color changes and largely elevated luminescent intensities, giving rise to the quantitative recognition of reductants and oxidants. This work presents a straightforward approach to developing efficient luminescent sensors for the rapid qualitative and quantitative detection of reductants and oxidants, extending the sensing mechanism from common energy transfer to electron transfer and demonstrating the MOF's versability as a highly designable sensing material for target analytes.

Linker Installation in a Metal‐Organic Framework for Enhanced Quantitative Redox Species Recognition

Linker installation has proven to be an effective strategy for introducing diverse functional groups into metal–organic frameworks (MOFs). Reductants and oxidants are found in various environments, but their accumulation poses a danger due to their high reactivity, necessitating prompt monitoring instantly, particularly in natural environments and industrial processes. In this study, a series of redox‐active dyes were successfully incorporated into a flexible Zr‐based MOF, PCN‐700, through linker installation strategy. Notably, both the reduction of PCN‐700‐Resazurin towards oxidants and oxidation of PCN‐700‐Amplex Red towards reductants result in the formation of PCN‐700‐Resorufin, which exhibit visible color changes and largely elevated luminescent intensities, giving rise to the quantitative recognition of reductants and oxidants. This work presents a straightforward approach to developing efficient luminescent sensors for the rapid qualitative and quantitative detection of reductants and oxidants, extending the sensing mechanism from common energy transfer to electron transfer and demonstrating the MOF’s versability as a highly designable sensing material for target analytes.

Recognition of Conus species using a combined approach of supervised learning and deep learning-based feature extraction.

Cone snails are venomous marine gastropods comprising more than 950 species widely distributed across different habitats. Their conical shells are remarkably similar to those of other invertebrates in terms of color, pattern, and size. For these reasons, assigning taxonomic signatures to cone snail shells is a challenging task. In this report, we propose an ensemble learning strategy based on the combination of Random Forest (RF) and XGBoost (XGB) methods. We used 47,600 cone shell images of uniform size (224 x 224 pixels), which were split into an 80:20 train-test ratio. Prior to performing subsequent operations, these images were subjected to pre-processing and transformation. After applying a deep learning approach (Visual Geometry Group with a 16-layer deep model architecture) for feature extraction, model specificity was further assessed by including multiple related and unrelated seashell images. Both classifiers demonstrated comparable recognition ability on random test samples. The evaluation results suggested that RF outperformed XGB due to its high accuracy in recognizing Conus species, with an average precision of 95.78%. The area under the receiver operating characteristic curve was 0.99, indicating the model's optimal performance. The learning and validation curves also demonstrated a robust fit, with the training score reaching 1 and the validation score gradually increasing to 95 as more data was provided. These values indicate a well-trained model that generalizes effectively to validation data without significant overfitting. The gradual improvement in the validation score curve is crucial for ensuring model reliability and minimizing the risk of overfitting. Our findings revealed an interactive visualization. The performance of our proposed model suggests its potential for use with datasets of other mollusks, and optimal results may be achieved for their categorization and taxonomical characterization.

Semantic segmentation network for mangrove tree species based on UAV remote sensing images

Mangroves are special vegetation that grows in the intertidal zone of the coast and has extremely high ecological and environmental value. Different mangrove species exhibit significant differences in ecological functions and environmental responses, so accurately identifying and distinguishing these species is crucial for ecological protection and monitoring. However, mangrove species recognition faces challenges, such as morphological similarity, environmental complexity, target size variability, and data scarcity. Traditional mangrove monitoring methods mainly rely on expensive and operationally complex multispectral or hyperspectral remote sensing sensors, which have high data processing and storage costs, hindering large-scale application and popularization. Although hyperspectral monitoring is still necessary in certain situations, the low identification accuracy in routine monitoring severely hinders ecological analysis. To address these issues, this paper proposes the UrmsNet segmentation network, aimed at improving identification accuracy in routine monitoring while reducing costs and complexity. It includes an improved lightweight convolution SCConv, an Adaptive Selective Attention Module (ASAM), and a Cross-Layer Feature Fusion Module (CLFFM). ASAM adaptively extracts and fuses features of different mangrove species, enhancing the network’s ability to characterize mangrove species with similar morphology and in complex environments. CLFFM combines shallow details and deep semantic information to ensure accurate segmentation of mangrove boundaries and small targets.Additionally, this paper constructs a high-quality RGB image dataset for mangrove species segmentation to address the data scarcity problem. Compared to traditional methods, our approach is more precise and efficient. While maintaining relatively low parameters and computational complexity (FLOPs), it achieves excellent performance with mIoU and mPA metrics of 92.21% and 95.98%, respectively. This performance is comparable to the latest methods using multispectral or hyperspectral data but significantly reduces cost and complexity. By combining periodic hyperspectral monitoring with UrmsNet-supported routine monitoring, a more comprehensive and efficient mangrove ecological monitoring can be achieved.These research findings provide a new technical approach for large-scale, low-cost monitoring of important ecosystems such as mangroves, with significant theoretical and practical value. Furthermore, UrmsNet also demonstrates excellent performance on LoveDA, Potsdam, and Vaihingen datasets, showing potential for wider application.

Identification of Six Novel Proteins Containing a ZP Module from Nemertean Species

During fertilization, a series of reactions between the eggs and spermatozoa proceed predominantly in a species-specific manner. The molecules mediating these species-specific reactions remain unknown except in a few organisms. In this study, we focused on two species belonging to the phylum Nemertea, Kulikovia alborostrata and K. fulva, and explored molecules involved in species-specific interactions between gametes. Orthologs of molecules known to be involved in species-specific reactions were not expressed in the ovaries of these two species. In contrast, we identified six novel proteins, named NeZPL1–NeZPL6, containing a ZP module. Among these, we found that NeZPL6 is located on the surface of an unfertilized egg and is suggested to be involved in its interaction with spermatozoa. Furthermore, we found an indel of three amino acids in the EGF-like domain of NeZPL6, which possibly confers species specificity to this interaction. Our results suggested the existence of a novel system for species recognition in animal gametes.

Producing plankton classifiers that are robust to dataset shift

AbstractModern plankton high‐throughput monitoring relies on deep learning classifiers for species recognition in water ecosystems. Despite satisfactory nominal performances, a significant challenge arises from dataset shift, which causes performances to drop during deployment. In our study, we integrate the ZooLake dataset, which consists of dark‐field images of lake plankton (Kyathanahally et al. 2021a), with manually annotated images from 10 independent days of deployment, serving as test cells to benchmark out‐of‐dataset (OOD) performances. Our analysis reveals instances where classifiers, initially performing well in in‐dataset conditions, encounter notable failures in practical scenarios. For example, a MobileNet with a 92% nominal test accuracy shows a 77% OOD accuracy. We systematically investigate conditions leading to OOD performance drops and propose a preemptive assessment method to identify potential pitfalls when classifying new data, and pinpoint features in OOD images that adversely impact classification. We present a three‐step pipeline: (i) identifying OOD degradation compared to nominal test performance, (ii) conducting a diagnostic analysis of degradation causes, and (iii) providing solutions. We find that ensembles of BEiT vision transformers, with targeted augmentations addressing OOD robustness, geometric ensembling, and rotation‐based test‐time augmentation, constitute the most robust model, which we call BEsT. It achieves an 83% OOD accuracy, with errors concentrated on container classes. Moreover, it exhibits lower sensitivity to dataset shift, and reproduces well the plankton abundances. Our proposed pipeline is applicable to generic plankton classifiers, contingent on the availability of suitable test cells. By identifying critical shortcomings and offering practical procedures to fortify models against dataset shift, our study contributes to the development of more reliable plankton classification technologies.

The species in paleoanthropology

The species is the basic unit of analysis in systematic paleontology. Yet, for most of its history the subfield of paleoanthropology has lacked any coherent concept of what fossil species are, using the species epithet variously at different times – most recently, with the conspicuous effect of minimizing apparent diversity among the hominins. The application of molecular systematic techniques to the analysis of high-latitude early Homo sapiens Linnaeus, 1758 and its contemporaries thus offers a welcome opportunity to reappraise our approaches to species recognition in the rapidly expanding hominin fossil record. But it must be cautioned that evidence for hybridization among documented or hypothesized lineages cannot necessarily be taken as evidence for recoalescence among them, and that “braided stream” models of hominin evolution (which militate against speciation) cannot ­account for the diversity of historically and morphologically differentiated entities we see in that record.

Automated classification of tree species using graph structure data and neural networks

The classification of tree species in urban contexts is pivotal in assessing ecosystem services and fostering sustainable urban development. This paper explores using graph neural networks (GNNs) on graph structure data derived from quantitative structure models (QSMs) and tree structural measurement for appropriate species classification. The study addresses gaps in existing methods by integrating relationships between tree components, such as branches and cylinders, and considering the entire tree structure in a novel graph data format. The results demonstrate the efficacy of GNNs, particularly the Gated Graph Convolutional Network (GatedGCN), in appropriately classifying urban tree species. It gained an overall classification accuracy and weighted F1 score of 0.84. An analysis of confusion matrices revealed similarities in visual characteristics among several species, including A. platanoides and T. cordata, which pose significant challenges in accurately distinguishing between them. However, certain species, such as A. hippocastanum and P. nigra var. italica, have proved easier to classify than others. Furthermore, the results highlight the importance of relationships between different tree components in species recognition, such as the ratio between branch radius and parent branch radius, the factors often overlooked by previous methods. This underscores the novelty and effectiveness of the proposed approach in this study. Future research could explore integrating additional data sources, such as Leaf Area Density (LAD) calculated from LiDAR and hyperspectral data, to enhance classification accuracy. In conclusion, the evaluation results of the GatedGCN model demonstrated its effectiveness in classifying tree species using a novel data structure format derived from QSM tree characteristics. Advancing urban tree species classification through such methods can enhance future urban tree management using automated AI and robotics solutions.

PlantView: Integrating deep learning with 3D modeling for indoor plant augmentation

Indoor plant recognition poses significant challenges due to the variability in lighting conditions, plant species, and growth stages. Despite the growing interest in applying deep learning techniques to plant data, there still needs to be more research focused on the automatic recognition of indoor plant species, highlighting the need for real-time, automated solutions. To address this gap, this study introduces a novel approach for real-time identification and visualization of indoor plants using a Convolutional Neural Network (CNN)-based model called PlantView, integrated with Augmented Reality (AR) for enhanced user interaction. The proposed PlantView model not only accurately classifies the plant species but also visualizes them in a 3D AR environment, allowing users to interact with virtual plant models seamlessly integrated into their real-world surroundings. We developed a custom dataset comprising over 28,000 images of 48 different plant species at various growth stages, captured under diverse lighting conditions and camera settings. Our proposed approach achieves an impressive accuracy of 98.20 %. To validate the effectiveness of PlantView model, we conduct extensive experiments and compared its performance against state-of-the-art methods, demonstrating its superior accuracy and processing speed. The results indicate that our method is not only highly effective for real-time indoor plant recognition but also offers practical applications for enhancing indoor plant care and visualization. This research offers a comprehensive solution for indoor plant enthusiasts and professionals, combining advanced computer vision techniques with immersive AR visualization to revolutionize the way indoor plants are identified, visualized, and integrated into living spaces.

Phylogeny and species diversity of Armillaria in China based on morphological, mating test, and GCPSR criteria

ABSTRACT More than 600 Chinese specimens of Armillaria were identified by mating tests, Genealogical Concordance Phylogenetic Species Recognition (GCPSR), and comparison of morphological characteristics. Sixteen Chinese Biological Species (CBS) of Armillaria were identified by 30,340 mate pair combinations. Fifteen Chinese Phylogenetic Species (CPS) were recognised based on Independent Evolutionary Lineage (IEL) recognition and concatenated six-gene analysis (actin, h3h, hisps, LSU rDNA, rpb1, and tef1α). All the biological species and phylogenetic species were identical and possessed the same species boundary, except for CBS K (A. mellea) and CBS G (A. mellea ssp. nipponica) which were the same phylogenetic species. On the basis of CBS and CPS, eight new species of Armillaria in China were distinguished using macro and micro morphology, and they are described as A. algida, A. amygdalispora, A. bruneocystidia, A. luteopileata, A. pungentisquamosa, A. sinensis, A. tibetica, and A. violacea. This study indicates that the GCPSR approach provides the same resolution as mating tests in identification of Armillaria species.

New herb gall wasps (Hymenoptera: Cynipidae: Aulacideini) from Kyrgyzstan, with description of a new genus and a review of the genus Panteliella Kieffer, 1901.

We describe three new aulacideine herb gall wasp species (Hymenoptera: Cynipidae: Aulacideini) from Kyrgyzstan, a country from which only two Aulacideini species were previously known. One of our new species represents a new genus, which we describe here as Soparia oshensis Nastasi gen. and sp. nov. We describe Panteliella rugosa Nastasi sp. nov., representing a new genus record for Kyrgyzstan. To further facilitate species recognition in Panteliella, we redescribe the genus and the species P. fedtschenkoi; provide a translated description of P. bianchii Vyrzhikovskaya, 1962; comment on complications affecting this genus; and provide a key to Panteliella species. Lastly, we describe Isocolus barakus Nastasi sp. nov., a species with morphology atypical of Isocolus. We provide a key to the Kyrgyz genera of Aulacideini to ensure that they remain diagnosable for future study. Our findings illustrate the continued unveiling of a diverse herb cynipid fauna in Central Asia and a need for further taxonomic study in the region.

Phlebotomine sand fly survey, blood meal source identification, and description of Sergentomyia imihra n. sp. in the central Sahara of Algeria

BackgroundPhlebotomine sand flies (Diptera: Psychodidae) are important vectors of various pathogens, mainly Leishmania parasites. In the Old World, the most important genus in term of pathogens transmission is the genus Phlebotomus, which includes many proven or suspected vectors of several Leishmania species, while the genus Sergentomyia remains so far unproven as a vector of human pathogens. Algeria is one of the most affected countries by human leishmaniasis.MethodsIn the present study, an entomological survey was carried out in two provinces, Ghardaïa and Illizi, located in the north and central Sahara, respectively, where cases of human leishmaniasis are recorded. Our goal was to understand the role of the local sand fly species in the transmission of Leishmania parasites and to analyze their blood meal preferences. Collected sand flies were identified by a combination of morphological and molecular approaches that included DNA-barcoding and matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF MS) protein profiling. In addition, female blood meals were analyzed by peptide mass mapping using MALDI-TOF MS.ResultsIn total, 640 sand fly specimens belonging to Phlebotomus and Sergentomyia genera were collected in the two provinces. Sergentomyia antennata and Se. fallax were most abundant species in Ghardaïa, and Ph. papatasi and Ph. alexandri in Illizi. In addition, a new sand fly species was described in Illizi named Sergentomyia (Sergentomyia) imihra n. sp. Blood meal analysis of the engorged females revealed various mammalian hosts, especially goats, but also humans for Phlebotomus papatasi and Ph. alexandri, suggesting that these vector species are opportunistic feeders.ConclusionsIntegrative approach that combined morphological analysis, sequencing of DNA markers, and protein profiling enabled the recognition and description of a new Sergentomyia species, raising the number of the Algerian sand fly fauna to 27 species. Further sand fly surveillance in the central Sahara is recommended to identify the thus-far unknown males of Se. imihra n. sp.Graphical

A SURVEY REGARDING MANGO FRUIT BORER INFESTATION IN MANGO ORCHARDS OF PUNJAB PAKISTAN

Mango is an important tropical fruit crop grown in most parts of the world including India, Pakistan, China, Bangladesh, Burma, Thailand, Japan, New Zealand, Australia, Indonesia, Africa, Brazil, Mexico and some US states. Mangan o is an important fruit crop for Pakistan due to its delicious taste, rich in vitamins A and C-and high-income returns to mango growers. However, in recent years a new pest problem mango fruit borer extensively damaged mango fruit crop in all mango growing districts of Punjab and Sindh. This insect was previously not even recognized as an important pest of mangoes in Pakistan among farmers and the scientific community, however since 2017, very serious complaints have been received from mango orchard owners regarding damage caused by MFB in the fruit clusters. Hence a survey was conducted in four districts of Punjab Pakistan viz., Multan, Muzaffargarh, Khanewal, and Rahim Yar Khan. About 145 mango growers were randomly chosen for interviews to learn about farmer perceptions and management of mango fruit borer. A series of open-ended and closed-ended questions were asked. Data was analyzed through the Chi-square test using Statistix 8.1 software. Farmers were asked various questions regarding farmers' identification of MFB stages and the nature of the damage, varietal preference of MFB, resting or hibernating places of the pest, insecticides used to control the pest, weeds as the reservoir of the pest and many more. Overall, most of the farmers were primarily qualified, males and had orchard sizes of 2 to 10 acres. Farmers reported that Sindhri was mostly affected by variety. Farmers used insecticides to control the pest menace and achieved around 40-80 % control. The knowledge about species recognition was very low among farmers. Based on this survey, we recommend farmer training programs regarding pest management, enhancing awareness among farmers regarding pest attacks, pest scouting, pest recognition and incorporation of cultural control techniques along with insecticides as a necessary part of pest management should be explained.

Few-shot learning based on dual-attention mechanism for orchid species recognition

Few-shot learning based on dual-attention mechanism for orchid species recognition

The ornate rubbernose pleco (Siluriformes, Loricariidae, Chaetostoma), a new species from the Ucayali River Basin, Peru

A new species in the rubbernose catfish genus Chaetostoma is described from the Aguaytia, Pisqui and Palcazu Rivers, which drain the Pampa de Sacramento Region in the Ucayali River drainage of central Peru. The new species is distinguished from congeners, except C. anomalum, C. branickii, C. dorsale, C. leucomelas, C. microps, C. nudirostre, C. palmeri and C. thomsoni by having distinct, white, variably-shaped spots or vermiculations ½–2× nostril diameter on dark grey to black background on the head (vs. spots absent or black on light-coloured background). The new species is distinguished from C. anomalum, C. branickii, C. dorsale, C. microps, C. nudirostre and C. thomsoni by having highly variable, distinct white spots, vermiculations or bands ½–10× nostril diameter on the body, from C. leucomelas by having dorsal and caudal fin indistinctly and variably-patterned with zero to four bands (vs. dorsal and caudal fin consistently having five or more uniform bands) and from C. palmeri by having two predorsal plates (vs. three), supraoccipital excrescence present (vs. absent) and pelvic-fin insertion slightly posterior to dorsal-fin insertion (vs. pelvic-fin insertion at middle of dorsal-fin base). Species delimitation analyses of the COI and Cytb genes further support the recognition of this new species.

Ceratozamia guatemalensis (Zamiaceae): A new cycad species from Mesoamerica

Ceratozamia guatemalensis, a new cycad species from the Sierra de los Cuchumatanes, Huehuetenango, Guatemala, is described and compared with the geographically proximal congeners C. vovidesii and C. matudae, with which C. guatemalensis has been historically confused based on their pendulous seed cones, a rare trait in the genus. Nonetheless, a recent phylogenetic study suggests that C. guatemalensis and C. vovidesii are sister species, while C. matudae belongs to distant clade. The new taxon is easily distinguishable from both C. vovidesii and C. matudae by qualitative and quantitative traits based on vegetative and reproductive structures. Remarkably, C. guatemalensis is characterized by having significant morphometric differences from the other two species, such as the wider median leaflets and wider leaflet articulations, and qualitative traits such as the seed cones of green color. The description of C. guatemalensis represents the recognition of the first endemic Ceratozamia species from Guatemala. It should be considered Critically Endangered (CR) due to limited populations and the ongoing destruction of its habitat.

Five new species of endophytic Penicillium from rubber trees in the Brazilian Amazon.

The Amazon rainforest is the world's most diverse ecosystem, full of fauna and flora. Among the trees that make up the forest are the rubber trees of the genus Hevea (H. brasiliensis and H. guianensis), which stand out for the industrial use of latex. It was previously shown that endophytic fungi colonize the leaves, stems, and roots of Hevea spp. In this study, 47 Penicillium spp. and three Talaromyces spp. isolates were analyzed using specific DNA barcodes: internal transcribed spacers region (ITS), β-tubulin (BenA), calmodulin (CaM), and the DNA-dependent RNA polymerase II second largest subunit (RPB2) genes and additionally, for species delimitation, the genealogical concordance phylogenetic species recognition (GCPSR) criteria were applied. The phylogenetic analyses placed the Penicillium isolates into four sections Lanata-Divaricata, Sclerotiora, Citrina, and Fasciculata. The morphological and molecular characteristics resulted in the discovery of five new species (P. heveae sp. nov., P. acrean sp. nov., P. aquiri sp. nov., P. amazonense sp. nov., and P. pseudomellis sp. nov.). The five new species were also compared to closely related species, with observations on morphologically distinguishing features and colony appearances. Bayesian inference and maximum likelihood analysis have supported the placement of P. heveae sp. nov. as a sister group to P. globosum; P. acrean sp. nov. and P. aquiri sp. nov. as sister groups to P. sumatrense; P. amazonense sp. nov. closely related to isolates of P. rolfsii, and P. pseudomellis sp. nov. closely related to P. mellis. The study of endophytic Penicillium species of rubber trees and the description of five new taxa of Penicillium sect. Citrina, Lanata-Divaricata, and Sclerotiora as endophytes add to the fungal biodiversity knowledge in native rubber trees. Reports of fungi in native tropical plants may reveal taxonomic novelties, potential pathogen control agents, and producers of molecular bioactive compounds of medical and agronomic interest.

A shift in substrate requirement might cause speciation of the lichenized fungi, Varicellaria hemisphaerica and V. lactea (Pertusariales, Ascomycota)

Proper species recognition is required to correctly estimate species preferences and their vulnerability or for eco-evolutionary inference. Varicellaria hemisphaerica and Varicellaria lactea are almost completely morphologically homogeneous species with unclear identification features. To evaluate the importance of morphological, chemical, and ecological characteristics used in recognition of these species, we tested 670 specimens, of which 42 were analyzed phylogenetically using nucITS rDNA, SSU rDNA, and LSU rDNA markers. This integrated taxonomical approach showed that V. hemisphaerica is distinct from V. lactea, and that substrate requirements, together with phylogenetic differences and the size of soredia, differentiate these species. The chemical composition of secondary lichen metabolites in both analyzed species showed similar variation and, therefore, this feature is not diagnostic in species recognition, although suggested by previous studies. The potential speciation of the two species seems to be caused by the shift in the substrate requirements.

Towards a Spectral Library of Medicinal and Aromatic Plant species (MAPs): Plant Discrimination and Wavelength Selection

The recognition and identification of Medicinal and Aromatic Plants species (MAPs) is a challenge for researchers and professionals in the field. To address this issue, this study aimed to examine the potential of using hyperspectral remote sensing, chemometrics and Machine Learning in discriminating between MAP species. Specifically, we tested the applicability of UV-Near-infrared Spectroscopy (UV-NIR), PCA and Partial Least-Squares Discriminant Analysis (PLS-DA) as tools for discrimination. The spectral signature data were obtained by UV-near infrared spectroscopy, covering a range of 325–1075 nm. Principal component analysis (PCA) was applied to reduce data dimensionality in order to minimize errors in PLS-DA model. This model was used to build a discriminant model based on the wavelengths obtained from PCA. The results show that it is effective to combine UV-NIR spectral features and PLS-DA to establish a discriminant model for accurately classifying the MAP species. The key wavelengths most involved in the discrimination were found in the NIR region and especially in ranges 516–548 and 628–1070 nm.

High-speed camera system for efficient monitoring of invasive plant species along roadways

Invasive plant species pose ecological threats to native ecosystems, particularly in areas adjacent to roadways, considering that roadways represent lengthy corridors through which invasive species can propagate. Traditional manual survey methods for monitoring invasive plants are labor-intensive and limited in coverage. This paper introduces a high-speed camera system, named CamAlien, designed to be mounted on vehicles for efficient invasive plant species monitoring along roadways. The camera system captures high-quality images at rapid intervals, to monitor the full roadside when following traffic speed. The system utilizes a global shutter sensor to reduce distortion and geotagging for precise localistion. The camera system makes it possible to collect extensive data sets, which can be used for a digital library of the invasive species and their locations, but also subsequent training of machine learning algorithms for automated species recognition.