Method For Identification Of Species Research Articles

Using capillary electrophoresis to identify Anopheline species in routine sampling sites.

In the Anopheles genus, various mosquito species are able to transmit the Plasmodium parasites responsible for malaria, while others are non-vectors. In an effort to better understand the biology of Anopheles species and to quantify transmission risk in an area, the identification of mosquito species collected in the field is an essential but problematic task. Morphological identification requires expertise and cannot be checked after processing samples in a destructive treatment, while sequencing of numerous samples is costly. Here, we introduce a method of Species identification via Simple Observation Coupled with Capillary Electrophoresis Technology (SOCCET). This molecular technique of species identification is based on precise determination of ITS2 length combined with a simple visual observation, the colour of mosquito hindleg tip. DNA extracted from field-collected Anopheles mosquitoes was amplified with universal Anopheles ITS2 primers and analysed with a capillary electrophoresis device, which precisely determines the size of the fragments. We defined windows of amplicon sizes combined with fifth hind tarsus colour, which allows discrimination of the major Anopheles species found in our collections. We validated our parameters via Sanger sequencing of ITS2 amplicons. Using the SOCCET method, we characterised the composition of Anopheles populations in five locations of French Guiana, where we detected a total of nine species. Anopheles braziliensis and Anopheles darlingi were detected in four locations each and represented 13 and 67% of our samples, respectively. The SOCCET method can be particularly useful when working with routine sampling sites with a moderate species diversity, that is, when the number of local species is too high to define species-specific primers but low enough to avoid individual ITS2 sequencing. This tool will be of interest to evaluate local malaria transmission risk and this approach may be further implemented for other mosquito genera.

A Metric-Based Few-Shot Learning Method for Fish Species Identification with Limited Samples.

Fish species identification plays a vital role in marine fisheries resource exploration, yet datasets related to marine fish resources are scarce. In open-water environments, various fish species often exhibit similar appearances and sizes. To solve these issues, we propose a few-shot learning approach to identifying fish species. Our approach involves two key components. Firstly, the embedding module was designed to address the challenges posed by a large number of fish species with similar phenotypes by utilizing the distribution relationships of species in the embedding space. Secondly, a metric function was introduced, effectively enhancing the performance of fish species classification and successfully addressing the issue of limited sample quantity. The proposed model is trained end to end on fish species public datasets including the Croatian fish dataset, Fish4Knowledge and WildFish. Compared with the prototypical networks, our method performs more effectively and improves accuracy by 2% to 10%; it is able to identify fish effectively in small samples sizes and complex scene scenarios. This method provides a valuable technological tool for the development of fisheries resources and the preservation of fish biodiversity.

Geometric morphometric methods for identification of oyster species based on morphology.

Both genetic and environmental factors affect the morphology of oysters. Molecular identification is currently the primary means of species identification, but it is inconvenient and costly. In this research, we evaluated the effectiveness of geometric morphometric (GM) techniques in distinguishing between two oyster species, Crassostreagigas and C.ariakensis. We used traditional morphometric and GM methods, including principal component analysis (PCA), thin-plate spline analysis (TPS) and canonical variable analysis (CVA), to identify specific features that distinguish the two species. We found that differences in shape can be visualised using GM methods. The Procrustes analysis revealed significant differences in shell morphology between C.gigas and C.ariakensis. The shells of C.ariakensis are more prominent at the widest point and are more scattered and have a greater variety of shapes. The shells of C.gigas are more oval in shape. PCA results indicated that PC1 explained 45.22%, PC2 explained 22.09% and PC3 explained 10.98% of the variation between the two species, which suggests that the main morphological differences are concentrated in these three principal components. Combining the TPS analysis function plots showed that the shell shape of C.ariakensis is mainly elongated and spindle-shaped, whereas the shell shape of C.gigas is more oval. The CVA results showed that the classification rate for the two species reached 100% which means that C.ariakensis and C.gigas have distinct differences in shell morphology and can be completely separated, based on morphological characteristics. Through these methods, a more comprehensive understanding of the morphological characteristics of different oyster populations can be obtained, providing a reference for oyster classification and identification.

Geometry of posterior larval spiracles to identify medically and forensically important calliphorids in Thailand

Fly identification is the primary step of analysis in forensic entomology. Although morphology and molecular techniques are considered satisfactory methods, some constraints may arise from a financial or even human point of view. Over the past decade, the geometric morphometric approach has been increasingly advocated for the classification and identification of arthropods. This study explored the method for species identification of 800 third-instar larvae of eight blow fly species of medical and forensic importance: Chrysomya chani Kurahashi, Chrysomya megacephala (Fabricius), Chrysomya (Ceylonomyia) nigripes Aubertin, Chrysomya pinguis (Walker), Chrysomya (Achoetandrus) rufifacies (Macquart), Hemipyrellia ligurriens (Wiedemann), Lucilia cuprina (Wiedemann), and Lucilia porphyrina (Walker). Based on the posterior spiracles geometry, the cross-validation revealed a relatively high percentage of correct classification in most species, ranking from 86% to 100%. The results of this study confirmed that the geometric morphometric (GM) analysis of posterior spiracles might be utilized as a larva identification tool. Therefore, this GM method represents one way of overcoming difficulties with the identification of blow fly larvae and can support further studies of these flies.

Artificial neuronal networks are revolutionizing entomological research

AbstractThe application of artificial intelligence (AI) in entomological research has gained significant attention in recent years. This review summarizes the current state of research on the potential of AI methods in various subfields of entomology, such as behavioural biology, biodiversity research, climate change research, pest management, and disease vector control. In some cases, AI‐based species identification methods based on deep learning neuronal network models have been shown to outperform traditional morphological identification methods in terms of accuracy and speed. Behavioural biology research has been enhanced through the use of AI‐based tracking systems that can classify insect behaviour and movement patterns. Habitat modelling has also been improved with the use of AI, allowing for the creation of more accurate models that can predict insect distribution and abundance. Climate change and biodiversity research have benefited from AI‐driven tools that can analyse large datasets and predict the impact of environmental changes on insect populations. In agriculture, pest management has been revolutionized by AI methods, with the development of smart traps and monitoring systems that can detect and identify pest species in real‐time, enabling targeted control measures. Disease vector control has also been improved through the use of AI‐based predictive models, which can identify areas at risk of disease transmission and aid in the development of effective control strategies. In conclusion, AI methods have the potential to revolutionize many aspects of entomological research. Future research should focus on developing more sophisticated AI tools and integrating them into entomological research to address even more complex ecological questions.

Molecular based identification and phylogenetic relationship by using cytochrome b gene of Pangasius pangasius.

Molecular appraoch for identification of unknown species by using Cytochrome b gene is an effective and reliable as compared with morphological based identification. For DNA barcoding universal molecular genes were used to identify the species. Cytochrome b is a specific gene used for identification purpose. DNA barcoding is a reliable and effective method compared to the different traditional morphological methods of specie identification. So,in the present study which was conducted to identify the species, a total of 50 fish samples were collected from five different sites. DNA was extracted by using the Phenol Chloroform method from muscle tissue. Five sequences were sequenced (one from each site), analyzed, and identified specific species as Pangasius pangasius. Identified sequences were variable in length from 369 bp (Site 1), 364 bp (Site 2), 364 bp (Site 3), 352 bp (Site 4), and 334 bp (Site 5). Identity matches on the NCBI database confirmed the specific specie as P. pangasius. A distancing tree was drawn to show maximum likelihood among the same and different species. Yet, in many cases fishes on diverse development stages are difficult to identify by morphological characters. DNA-based identification methods offer an analytically powerful addition or even an alternative tool for species identification and phylogenetic study. This work intends to provide an updated and extensive overview on the DNA based methods for fish species identification by using Cytochrome b gene as targeted markers for identification purpose.

Challenges and knowledge gaps in the management of non-tuberculous mycobacterial pulmonary disease in sub-Saharan African countries with a high tuberculosis burden: a scoping review

IntroductionIn sub-Saharan African (SSA) countries endemic for tuberculosis (TB), previous TB is a significant risk factor for non-tuberculous mycobacterial pulmonary disease (NTM-PD). The deployment of GeneXpert MTB/RIF in pulmonary TB...

Exploring Molecular Methods for Candida species Identification and Characterization

Candida species (CS) are significant fungal pathogens responsible for a wide range of infections in humans, making their precise and timely identification crucial for effective treatment and disease management. Traditional identification methods, such as phenotypic assays and culture-based techniques, often suffer from limitations, including prolonged processing times, limited accuracy, and inadequate differentiation between species. As a result, molecular techniques have gained prominence for their ability to rapidly and accurately identify and characterize various Candida species. This review discusses the shortcomings of conventional methods and highlights the array of molecular strategies that have been developed, such as polymerase chain reaction (PCR) assays, DNA sequencing, and matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF MS). These techniques leverage the unique genetic and proteomic profiles of Candida species to provide highly sensitive and specific identification, even distinguishing between closely related strains. Additionally, the review explores the use of molecular approaches in clinical diagnostics, epidemiological studies, and antifungal resistance monitoring, where they enable the rapid detection of Candida species from clinical samples, allowing for swift diagnosis and timely antifungal intervention. Furthermore, these techniques are instrumental in identifying clonal outbreaks and tracking transmission dynamics in healthcare settings. The review emphasizes the advantages of molecular methods—such as their precision, speed, and capacity to uncover cryptic species—while also calling for continued research to improve their efficacy and broader application in Candida species identification.

Evaluation of the wing cell contour to distinguish between Stomoxys bengalensis and Stomoxys sitiens (Diptera: Muscidae) using outline-based morphometrics

The blood-sucking flies of the genus Stomoxys Geoffroy, 1762 (Diptera: Muscidae) are significant ectoparasites that can cause irritation and transmit pathogens to both animals and humans. Within the genus Stomoxys, two species, Stomoxys bengalensis and Stomoxys sitiens, have similar morphology and coexist in the same habitat. Accurate species identification of these flies is crucial for understanding disease vectors and implementing effective control measures. In this study, we assessed the effectiveness of outline-based geometric morphometrics (GM) by analyzing the wing cell contour of the first posterior cell (R5) to distinguish between species and sexes of S. bengalensis and S. sitiens. Our results demonstrate that the outline-based GM method is highly effective in distinguishing between species and sexes of these flies based on contour shape, with accuracy scores ranging from 90.0% to 97.5%. Therefore, outline-based GM emerges as a promising alternative to landmark-based GM or as a supplementary tool in conjunction with traditional morphology-based methods for species identification.

Comparison of the VITEK® 2 System with Conventional Methods for Species Identification and Antimicrobial Susceptibility Pattern of Staphylococcal Carrier Isolates

Staphylococcus aureus, an opportunistic pathogen that inhabits 20% to 70% of human anterior nares and can cause infections, ranging from mild, superficial infections of the skin and soft tissues to severe conditions like sepsis, necrotizing pneumonia and toxic shock syndrome. Healthcare workers are potential asymptomatic nasal carriers, contribute to major infection transmission. The emergence of multidrug-resistant strains necessitates advanced treatment approaches. The study aimed to identify staphylococcal nasal carriers among dental students, and to compare the results obtained from automated identification system, VITEK® 2 with conventional methods for identifying Staphylococcus species and determining antibiotic susceptibility patterns. Anterior nasal swabs were collected from 42 study participants were processed as per standard microbiological culture techniques. All the conventionally identified S. aureus isolates were subjected to a further analysis using an automated VITEK® 2 SYSTEM. Surprisingly, the automated identification system classified all conventionally proven S. aureus isolates as other Staphylococci species (S. epidermidis (60%), S. warneri, and S. lentus), raising concerns about potential misdiagnosis. Overall, there was a 97.5% categorical agreement between VITEK® 2 system and the reference method, with minimal errors (0.8% very major, 0.6% major, and 1.17% minor). These discrepancies underscore the importance of accurate species identification and highlight the necessity for advanced techniques in infection control strategies, emphasizing the potential impact on decolonization decisions.

A snail species identification method based on deep learning in food safety.

In daily life, snail classification is an important mean to ensure food safety and prevent the occurrence of situations that toxic snails are mistakenly consumed. However, the current methods for snail classification are mostly based on manual labor, which is inefficient. Therefore, a snail detection and classification method based on improved YOLOv7 was proposed in this paper. First, in order to reduce the FLOPs of the model, the backbone of the original model was improved. Specifically, the original 3×3 regular convolution was replaced with 3×3 partial convolution, and the Conv2D_BN_SiLU module in the partial convolution was replaced with the Conv2D_BN_FReLU module. FReLU could enhance the model's representational capacity without increasing the number of parameters. Then, based on the specific features of snail images, in order to solve the problems of small and dense targets of diverse shapes, a receptive field enhancement module was added to the head to learn the different receptive fields of the feature maps and enhance the feature pyramid representation. In addition, the CIoU was replaced with the WIoU to make the model pay more attention to targets at the edge or difficult-to-regress accurate bounding boxes. Finally, the images of nine common types of snails were collected, including the Pomacea canaliculata, the Viviparidae, the Nassariidae, and so on. These images were then labeled using LabelImg software to create a snail image dataset. Experiments were conducted based on the dataset, and the results showed that the proposed method demonstrated the best performance compared to other state-of-the-art methods.

Electrophoretic Methods for Identifying the Species of Seafood and Its Derivatives

The identification of the species of seafood and their products, whether they are fresh or cooked, is one of the key concerns of food regulations in many countries that have a significant intake of seafood. In point of fact, a commercial fraud happens when a species that is less value is intentionally substituted for a species that is more valuable, and a sanitary fraud takes place when a product that is potentially harmful is introduced into the market. A primary responsibility of veterinary inspection of seafood products is the detection of harmful species with the aim of removing them from the retail trade (Council Directive 91/493/ECC). Two efficient methods for seafood species identification are molecular biology methods and protein electrophoresis. Classic electrophoretic methods have been used for a long time to authenticate seafood; they are simple, accurate, and inexpensive compared to molecular biological methods, which are the wave of the future in food safety labs. The purpose of this article is to offer an overview of the electrophoretic methods commonly used to identify different species of seafood, including sodium dodecyl sulfate–polyacrylamide gel electrophoresis (SDS–PAGE), native or urea-isoelectric focusing electrophoresis (IEF), two-dimensional electrophoresis (2-DE), and capillary electrophoresis (CE).

Optimization of Molecular Genetic Method for Identification of Dairy Raw Materials

Introduction: This article addresses the pressing issue of ensuring the quality and safety of dairy products by combating adulteration, a challenge that continues to plague the dairy industry. Adulteration, often driven by cost-cutting motives, involves altering the composition, quality, or origin of dairy products, even in the face of tightened control measures and improved monitoring systems. Specifically, this study hones in on the problem of species-specific adulteration, particularly the substitution of goat milk with cow milk due to the significant cost differential. Detecting and identifying such adulteration is crucial, and while traditional methods like electrophoresis and chromatography have been used, they are often expensive and labor-intensive. The article explores the use of molecular genetic methods, particularly polymerase chain reaction (PCR), as a more efficient and accurate means of identifying species-specific milk adulteration. Methods like PCR offer high specificity, sensitivity, speed, and the ability to perform quantitative and multiplex analyses.Purpose: The objective of this study is to optimise a method for species identification of dairy products by PCR-based screening using DNA isolated from cow’s and goat’s milk comatic cells.Materials and Methods: This research conducted at the Central Laboratory of Microbiology, All-Russian Research Institute of Dairy Industry, focuses on milk species identification of cattle and small ruminants using a specific set of primers targeting the polymorphic amylogenin gene. The study involves PCR screening with DNA extracted from cow’s and goat’s raw milk utilizing a MiniAmp instrument for the analysis. Qualitative and quantitative assessments of DNA preparations were performed, measuring DNA concentration with a Qubit 4 fluorimeter and Qubit dsDNA BR Assay Kit. PCR analysis was carried out in 25 μl reactions, including key components such as 5xScreen Mix, specific primers, DNA samples, and mQ H2O. The amplification program comprised denaturation, annealing, and elongation steps over a series of cycles.Results: The experiment was aimed at assessing the suitability of primers SE47 and SE48 for amplification of nuclear DNA of milk somatic cells of cattle (Bos taurus) and goats (Capra hircus). Initially, a calculated annealing temperature of 56 °C was used in the PCR reaction, yielding in numerous nonspecific fragments appeared on the electropherogram. To solve this problem, we gradually increased the annealing temperature, which resulted in a significant decrease in the nonspecific fragments number and their complete absence at annealing temperature of 70°C.Conclusion: We succeeded in optimizing a PCR-based detection system for the milk species identification of cattle and small ruminants. The results obtained confirm the possibility of using genomic DNA of milk somatic cells for the successful amplification of species-specific nuclear markers, but there remains a need for further research to determine the sensitivity of the PCR system and the possibility of its use in the analysis of milk processing products.

Development of specific barcodes for identification of Aloe species based on chloroplast DNA barcoding

DNA barcoding is a widely used taxonomic tool for correctly identifying plant species. The chloroplast matK and rbcL are some of the most extensively studied variable coding genes of angiosperms and have been recommended as a universal barcode for terrestrial plants. Genus Aloe contains around 500 species, and most Aloe species have extensive traditional medicinal usage worldwide, viz., A. arborescens, A. ferox, A. maculate, and A. vera. This study evaluated the two chloroplast DNA barcodes (matK and rbcL) to develop a theoretical base for species identification and germplasm conservation of Aloe species. The Maximum Parsimony analysis was conducted to study the evolutionary relatedness of Aloe sequences using matK and rbcL sequences obtained from the NCBI nucleotide database. The results revealed that 49 Aloe accessions were segregated into four major clades using matK phylogenetic analysis. Likewise, the 29 Aloe accessions were allocated into two clades based on the rbcL phylogeny. Additionally, specific barcodes have been developed for the following species: A. vera, A. boylei, A. ciliaris, A. karasbergensis, and A. sinkatana based on SNP (Single Nucleotide Polymorphism) site analysis of barcode sequences and the corresponding DNA QR (quick response) code of each sequence was generated. This study provides a unique method for species identification of the genus Aloe and indicates the possibility of correctly identifying, discriminating, and documenting the Aloe species.

Qualitative and quantitative studies of multicomponent gas by CNN-KPCA-RF model

To improve the accuracy of multi-component gas analysis in infrared spectroscopy and simplify the workflow, an infrared spectroscopy gas detection method based on an improved convolutional neural network is proposed. This method can not only identify a variety of gas categories but also finely identify the concentration of gas. To verify the model identification effect proposed in this paper, eight kinds of gases such as CH4 and C2H6 were used as the sample gases for gas identification and concentration classification, and the corresponding hardware was used to complete the development of the system. The experimental results show that the accuracy of the model method for gas species identification can reach 90%, and the accuracy for concentration identification is the same. In addition, compared with the traditional CNN method, the recognition effect is significantly improved. With the improvement of the data set, the number of gas categories detected by this method and the measurement accuracy will be improved.

COL1A2 Barcoding: Bone Species Identification via Shotgun Proteomics.

Species identification of fragmentary bones remains a challenging task in archeology and forensics. A species identification method for such fragmentary bones that has recently attracted interest is the use of bone collagen proteins. Here, we describe a method similar to DNA barcoding that reads collagen protein sequences in bone and automatically determines the species by performing sequence database searches. The method is almost identical to conventional shotgun proteomics analysis of bone samples, except that the database used by the SEQUEST search engine consisted only of entries for collagen type 1 alpha 2 (COL1A2) proteins from various vertebrates. Accordingly, the COL1A2 peptides that differ in sequence among species act as species marker peptides. In SEQUEST-based shotgun proteomics, the protein entries that contain more marker peptide sequences are assigned higher scores; therefore, the highest-scoring protein entry will be the COL1A2 entry for the species from which the analyzed bone was derived. We tested our method using bone samples from 30 vertebrate species and found that all species were correctly identified. In conclusion, COL1A2 can be used as a bone protein barcode and can be read through shotgun proteomics, allowing for automatic bone species identification. Data are available via ProteomeXchange with the identifier PXD045402.

Molecular Characterization of Liver Fluke Isolated from Sheep, Goat and Cattle in Sulaymaniyah, Iraq.

We aimed to determine species of liver fluke that predominately cause fascioliasis in sheep, goats, and cattle in the Sulaymaniyah Province, Iraq using the molecular technique of DNA sequencing and restriction fragment length polymorphism (RFLP). The samples were collected from November 2021 to May 2022. The flukes were collected from infected livers of livestock at the slaughterhouse of Sulaymaniyah Governorate, Iraq. A total of 205 flukes were collected from 56 hosts, cattle (n=22), sheep (n=28), and goats (n=6). The specific primers for FCOX1 and 28S rDNA gene amplification were used. The PCR products were subjected to restriction fragment polymorphism (RFLP) assay using Hpy188III and Dra II restriction enzymes, besides DNA sequencing. The results showed the genetic polymorphisms among the flukes. Three patterns of RFLP were observed Fasciola hepatica, F. gigantica, and F. intermediate, where 28 of them displayed F. hepatica (sheep, n=14, goat, n=3 and cattle, n= 11), whereas 24 samples displayed the F. gigantica (sheep, n=12, goat, n=3 and cattle, n= 9), and only four samples belonged to F. intermediate (sheep n=3 and cattle, n=1). In addition, the result of the ribosomal DNA (28S rDNA) sequencing confirmed that the isolated flukes belonged to F. hepatica, F. gigantica and F. intermediate. All three main species are present in the study area and F. hepatica predominated among the animal species in this area also, our results concluded that PCR-RFLP is a rapid and reliable method for liver fluke species identification.

Analysis and comparison of machine learning methods for species identification utilizing ATR-FTIR spectroscopy

Accurate identification of insect species holds paramount significance in diverse fields as it facilitates a comprehensive understanding of their ecological habits, distribution range, and impact on both the environment and humans. While morphological characteristics have traditionally been employed for species identification, the utilization of empty pupariums for this purpose remains relatively limited. In this study, ATR-FTIR was employed to acquire spectral information from empty pupariums of five fly species, subjecting the data to spectral pre-processing to obtain average spectra for preliminary analysis. Subsequently, PCA and OPLS-DA were utilized for clustering and classification. Notably, two wavebands (3000–2800 cm−1 and 1800–1300 cm−1) were found to be significant in distinguishing A. grahami. Further, we established three machine learning models, including SVM, KNN, and RF, to analyze spectra from different waveband groups. The biological fingerprint region (1800–1300 cm−1) demonstrated a substantial advantage in identifying empty puparium species. Remarkably, the SVM model exhibited an impressive accuracy of 100 % in identifying all five fly species. This study represents the first instance of employing infrared spectroscopy and machine learning methods for identifying insect species using empty pupariums, providing a robust research foundation for future investigations in this area.

Rapid RNase H-dependent PCR lateral flow assay for the detection of red snapper

Red snapper (Lutjanus campechanus or Lutjanus purpureus) is one of the most commercially important and commonly mislabeled seafood species in the United States. Existing molecular methods for species identification are expensive and require being sent to an off-site laboratory, which takes multiple days to process. In this study, we have standardized a rapid rhPCR-coupled lateral flow assay for the identification of red snapper species. Our assay involved a simple heat-lysis DNA extraction procedure and a multiplex PCR reaction, consisting of a red snapper single nucleotide polymorphism (SNP)-specific rhPCR primer, thermotolerant RNase H2 enzyme, and an internal amplification control (IAC) for their onsite identification. Amplicons generated in the PCR reaction were detected using dual target lateral flow strips. The standardized assay was validated with 108 barcoded fish samples. Samples identified as Lutjanus campechanus or L. purpureus by DNA barcoding formed three distinct bands, while other fish species formed only two bands on the lateral flow strips. A minimum of 0.37 ng of crude DNA was detectable in the rhPCR reaction and generated a visible band on the lateral flow dipstick. The assay showed 100% specificity and took 90–120 min to complete. The assay generated results that can be used to authenticate red snapper at the wholesale and retail levels of seafood processing and commerce. Our results confirm the ability of rhPCR-lateral flow assays to be an alternative tool for onsite species authentication for the seafood industry.

GTCBS-YOLOv5s: A lightweight model for weed species identification in paddy fields

Accurate and rapid weed species identification contributes to selective herbicide spraying or robotic weeding. An image-based method for automatic identification of weed species in paddy fields is highly desirable. However, water reflection, soil background, occlusion, and varying growth and illumination make the development of this method challenging. To address this issue, an improved deep learning model GTCBS-YOLOv5s was proposed to identify six weed species in paddy fields, where Ghost, C3Trans and convolutional block attention module (CBAM) were employed to improve weed feature extraction in complex environments. The bidirectional feature pyramid network (BiFPN) coupled with Concat structure was introduced in the Neck network to achieve the multi-scale feature fusion for identifying various weed species. Three different output feature maps in Detect network were utilized to identify weeds of varying sizes. A more comprehensive scale-sensitive intersection over union (SIoU) loss function was adopted to eliminate the redundant generating boxes. The results showed that GTCBS-YOLOv5s model achieved a mean average precision (mAP) of 91.1 % for the test set, and the identification speed reached 85.7 FPS. Robustness tests demonstrated that GTCBS-YOLOv5s obtained satisfactory performance in identifying weeds under various lighting conditions, with precision (P), recall (R) and mAP all greater than 85 %. Occluded weeds were identified with P, R and average precision (AP) greater than 89.8 %, 90.1 % and 90.3 %, respectively. Furthermore, GTCBS-YOLOv5s had good performance in identifying weeds at different growth stages, with P, R and mAP higher than 90.1 %, 89.5 %, and 90.3 % respectively. Compared with the state-of-the-art models, GTCBS-YOLOv5s was highly promising for deployment to the embedded devices for real-time field detection due to its high accuracy, lightweight and robust attributes, as well as fast inference.