Search

Accurate and timely monitoring of pests is an effective way to minimize the negative effects of pests in agriculture. Since deep learning-based methods have achieved good performance in object detection, they have been successfully applied for pest detection and monitoring. However, the current pest detection methods fail to balance the relationship between computational cost and model accuracy. Therefore, this paper proposes a lightweight, locality-aware faster R-CNN (LLA-RCNN) method for effective pest detection and real-time monitoring. The proposed model uses MobileNetV3 to replace the original backbone, reduce the computational complexity, and compress the size of the model to speed up pest detection. The coordinate attention (CA) blocks are utilized to enhance the locality information for highlighting the objects under complex backgrounds. Furthermore, the generalized intersection over union (GIoU) loss function and region of interest align (RoI Align) technology are used to improve pest detection accuracy. The experimental results on different types of datasets validate that the proposed model not only significantly reduces the number of parameters and floating-point operations (FLOPs), but also achieves better performance than some popular pest detection methods. This demonstrates strong generalization capabilities and provides a feasible method for pest detection on resource-constrained devices. [ABSTRACT FROM AUTHOR]

Simple Summary: This study investigated species diversity and seasonal abundance of biting flies, specifically Stomoxyinae and tabanid flies, which are important pests capable of spreading diseases to animals, on a beef cattle and a buffalo farm in Nakhon Si Thammarat province, southern Thailand. Over the course of a one-year study (December 2020 to November 2021), 1912 biting flies were collected and identified, comprising seven Stomoxyinae and nine tabanid species. The five most predominant species were Tabanus megalops, Haematobia irritans exigua, Stomoxys calcitrans, Stomoxys indicus, and Stomoxys uruma. A higher number of flies were collected from the beef cattle farm compared to the buffalo farm, with most species peaking during the rainy season, except for H. i. exigua, which was more prevalent during the dry season. Temperature, relative humidity, and rainfall influenced fly density, revealing different patterns depending on the species. This study provides important information that is crucial for designing effective fly control strategies to reduce the impact of these flies on livestock health. This study investigated species diversity and seasonal abundance of Stomoxyinae and tabanid flies, which are significant pests and vectors of animal pathogens, on a beef cattle and a buffalo farm in Nakhon Si Thammarat province, southern Thailand. During a one-year period from December 2020 to November 2021, flies were collected using Nzi traps from 6 a.m. to 6 p.m. over three consecutive days each month, resulting in the capture of 1912 biting flies, representing seven Stomoxyinae and nine tabanid species. The five most prevalent species were Tabanus megalops, Haematobia irritans exigua, Stomoxys calcitrans, Stomoxys indicus, and Stomoxys uruma. Fly density was notably higher on the beef cattle farm compared to the buffalo farm, with most species peaking during the rainy season, except for H. i. exigua, which was more abundant during the dry season. This study also examined the influence of temperature, relative humidity, and rainfall on fly density, revealing species-specific patterns. These findings offer updated insights into species diversity and seasonal trends, providing critical baseline data essential for the development of effective control strategies aimed at mitigating the impact of these flies on livestock health. [ABSTRACT FROM AUTHOR]

Strawberry crops are susceptible to a wide range of pests and diseases, some of which are insidious and diverse due to the shortness of strawberry plants, and they pose significant challenges to accurate detection. Although deep learning-based techniques to detect crop pests and diseases are effective in addressing these challenges, determining how to find the optimal balance between accuracy, speed, and computation remains a key issue for real-time detection. In this paper, we propose a series of improved algorithms based on the YOLOv8 model for strawberry disease detection. These include improvements to the Convolutional Block Attention Module (CBAM), Super-Lightweight Dynamic Upsampling Operator (DySample), and Omni-Dimensional Dynamic Convolution (ODConv). In experiments, the accuracy of these methods reached 97.519%, 98.028%, and 95.363%, respectively, and the F1 evaluation values reached 96.852%, 97.086%, and 95.181%, demonstrating significant improvement compared to the original YOLOv8 model. Among the three improvements, the improved model based on CBAM has the best performance in training stability and convergence, and the change in each index is relatively smooth. The model is accelerated by TensorRT, which achieves fast inference through highly optimized GPU computation, improving the real-time identification of strawberry diseases. The model has been deployed in the cloud, and the developed client can be accessed by calling the API. The feasibility and effectiveness of the system have been verified, providing an important reference for the intelligent research and application of strawberry disease identification. [ABSTRACT FROM AUTHOR]

The aim of this work was to determine the influence of chosen biostimulants and microbiological preparations on the yield of sweet corn and the occurrence of Ostrinia nubilalis Hbn, and diseases. In both years of the study, the preparations used in this experiment did not have a statistically significant effect on marketable yield; however, in 2017, the highest weight was observed in the cobs of plants treated with Rizocore and Polyversum WP while the lowest in the cobs treated with RhizoVital 42. The biostimulant Asahi SL and the biological fungicide Serenade ASO proved to be the most effective in protecting sweet corn against cob and shoot infections by fungi of the genus Fusarium. All the preparations reduced the development of the common smut in corn, especially on the cobs. There were no statistically significant differences in cob infection by the O. nubilalis in the combinations treated with different preparations, although the lowest number of cobs damaged by pest in both years were observed on plots treated with Serenade ASO and RhizoVital 42, while the highest on plots treated with Goëmar BM. [ABSTRACT FROM AUTHOR]

The accurate identification of tea tree pests is crucial for tea production, as it directly impacts yield and quality. In natural tea garden environments, identifying pests is challenging due to their small size, similarity in color to tea trees, and complex backgrounds. To address this issue, we propose TTPRNet, a multi-scale recognition model designed for real tea garden environments. TTPRNet introduces the ConvNext architecture into the backbone network to enhance the global feature learning capabilities and reduce the parameters, and it incorporates the coordinate attention mechanism into the feature output layer to improve the representation ability for different scales. Additionally, GSConv is employed in the neck network to reduce redundant information and enhance the effectiveness of the attention modules. The NWD loss function is used to focus on the similarity between multi-scale pests, improving recognition accuracy. The results show that TTPRNet achieves a recall of 91% and a mAP of 92.8%, representing 7.1% and 4% improvements over the original model, respectively. TTPRNet outperforms existing object detection models in recall, mAP, and recognition speed, meeting real-time requirements. Furthermore, the model integrates a counting function, enabling precise tallying of pest numbers and types and thus offering practical solutions for accurate identification in complex field conditions. [ABSTRACT FROM AUTHOR]

One of the most pressing issues in livestock farming is the protection of economically valuable livestock. The prevention and the treatment of infectious diseases are directly related to maintaining stable livestock output. Vermin is a primary source of livestock infection, resulting in the occurrence and expansion of epidemic diseases. To protect livestock against infections caused by epidemic diseases, this study proposes a vermin repulsion system called the Miyazaki Vermin Repulsion Robot (MiVeReR). Different from existing vermin repulsion systems, the development objective of MiVeReR is to repel vermin rather than kill them. In particular, MiVeReR generates changeable acousto-optic signals as repulsion signals for wild animals. Furthermore, MiVeReR employs image data to monitor the invasion of wild animals and their location data to track them, and accurately focuses the generated signals on them. These acousto-optic stimuli can be changed based on the reactions of the intruder through the feedback of the image data to ensure the effectiveness of the repulsion motions for vermin. Details on the hardware configuration of MiVeReR and its control scheme are explained. As a first step to develop MiVeReR, we attempted to repel vermin such as mice and wild cats from farm environments. Extensive experiments were conducted to verify the effectiveness of MiVeReR and the proposed control solution. Through experiments in wild environments, the feasibility of MiVeReR was inspected. The results of this study are concretely described. [ABSTRACT FROM AUTHOR]

The red palm weevil (Rhynchophorus ferrugineus) is a highly destructive pest, causing severe damage to palm trees and significantly reducing their productivity. This paper aims to develop and analyze a mathematical model that captures the interactions between palm trees, Rhynchophorus ferrugineus, and entomopathogenic nematodes as a means of integrated control. We identify the equilibrium points of the system and perform a stability analysis to assess the system's behavior. Additionally, we design a linear quadratic regulator (LQR) to limit the spread of the red palm weevil within a locally linearized framework. The feedback control law, which is both straightforward and immediately implementable, is employed to avoid the need for complex cost calculations, thus simplifying the solution to the optimal control problem. Numerical simulations demonstrate that the proposed control strategy is effective in reducing the number of infected palm trees. The results indicate that increasing the population of entomopathogenic nematodes can significantly decrease the red palm weevil population, offering a promising approach to mitigating this pest's impact. [ABSTRACT FROM AUTHOR]

Potato is one of the most consumed crops worldwide. One strategy aimed at pathogen and pest management is the cultivation of resistant varieties. In this study, 352 genotypes from the Kazakhstan potato germplasm collection were screened for the presence of loci for resistance to the most harmful pathogens and pests using 30 DNA markers. 'Rucheek' and 'Spiridon', among the top global varieties, and 'Janaisan' and 'Fedor', among the top local varieties, were identified as bearing the most resistance loci in the collection, with at least 14 markers each. The specimens carrying the genes Ryadg (ADG1, ADG2), Nb (SPUD237), Ns (SC811, CP16), Rpi-phu1 (GP94), and GroV1 (X02), which demonstrate confirmed resistance to PVY, PVA, PVX, PVS, Phytophthora infestans, and Globodera rostochiensis, were most frequently found in the collection. Loci for resistance to Synchytrium endobioticum and Globodera pallida were less introgressed into the Kazakhstani cultivars and were almost absent in the germplasm collection. The less abundant loci found in the current potato collection were Ryadg (RysC3), Gro1-4 (Gro1-4), and Rladg (RGASC850). Screening of the potato collection showed that the markers SPUD237, CP60, 45/X1, and CT214 generated additional polymorphic amplicons, while markers Nl25, C237, GP179, and GP122718 were less applicable in robust large-scale screening. The results from this study may greatly contribute to marker-assisted selection and gene pyramiding strategies aimed at developing new potato varieties with multiple resistance to biotic stress [ABSTRACT FROM AUTHOR]

To address the issues of low detection accuracy and large model parameters in crop pest detection in natural scenes, this study improves the deep learning object detection model and proposes a lightweight and accurate method RTMDet++ for crop pest detection. First, the real-time object detection network RTMDet is utilized to design the pest detection model. Then, the backbone and neck structures are pruned to reduce the number of parameters and computation. Subsequently, a shortcut connection module is added to the classification and regression branches, respectively, to enhance its feature learning capability, thereby improving its accuracy. Experimental results show that, compared to the original model RTMDet, the improved model RTMDet++ reduces the number of parameters by 15.5%, the computation by 25.0%, and improves the mean average precision by 0.3% on the crop pest dataset IP102. The improved model RTMDet++ achieves a mAP of 94.1%, a precision of 92.5%, and a recall of 92.7% with 4.117M parameters and 3.130G computations, outperforming other object detection methods. The proposed model RTMDet++ achieves higher performance with fewer parameters and computations, which can be applied to crop pest detection in practice and aids in pest control research. [ABSTRACT FROM AUTHOR]

Tribolium castaneum is a challenging pest of stored products, causing significant economic losses. The present study explored the efficacy of Coridothymus capitatus essential oil and its primary constituent, carvacrol, as eco-friendly alternatives for managing this pest. To evaluate their insecticidal potential, repellency, fumigant toxicity, and antifeedant properties, progeny inhibition assays were performed. Carvacrol exhibited superior repellency compared to the essential oil, achieving a 92% repellency rate at 2 mg/cm2. Both compounds demonstrated significant fumigant toxicity against T. castaneum, with LC50 values of 168.47 and 106.5 μL/L for the essential oil and carvacrol, respectively, after 24 h. Carvacrol also outperformed the essential oil in antifeedant activity, inducing an 80.7% feeding deterrence at 1.17 mg/g. Moreover, both treatments effectively suppressed the development of the pest's progeny. These results collectively underscore the potent insecticidal properties of C. capitatus essential oil and carvacrol, particularly carvacrol, as promising candidates for the sustainable management of T. castaneum in stored product protection. [ABSTRACT FROM AUTHOR]

In the contemporary context, pest detection is progressively moving toward automation and intelligence. However, current pest detection algorithms still face challenges, such as lower accuracy and slower operation speed in detecting small objects. To address this issue, this study presents a crop pest target detection algorithm, GLU-YOLOv8, designed for complex scenes based on an enhanced version of You Only Look Once version 8 (YOLOv8). The algorithm introduces the SCYLLA-IOU (SIOU) loss function, which enhances the model generalization to various pest sizes and shapes by ensuring smoothness and reducing oscillations during training. Additionally, the algorithm incorporates the Convolutional Block Attention Module (CBAM) and Locality Sensitive Kernel (LSK) attention mechanisms to boost the pest target features. A novel Gated Linear Unit CONV (GLU-CONV) is also introduced to enhance the model's perceptual and generalization capabilities while maintaining performance. Furthermore, GLU-YOLOv8 includes a small-object detection layer with a feature map size of 160 × 160 to extract more features of small-target pests, thereby improving detection accuracy and enabling more precise localization and identification of small-target pests. The study conducted a comparative analysis between the GLU-YOLOv8 model and other models, such as YOLOv8, Faster RCNN, and RetinaNet, to evaluate detection accuracy and precision. In the Scolytidae forestry pest dataset, GLU-YOLOv8 demonstrated an improvement of 8.2% in mAP@0.50 for small-target detection compared to the YOLOv8 model, with a resulting mAP@0.50 score of 97.4%. Specifically, on the IP102 dataset, GLU-YOLOv8 outperforms the YOLOv8 model with a 7.1% increase in mAP@0.50 and a 5% increase in mAP@0.50:0.95, reaching 58.7% for mAP@0.50. These findings highlight the significant enhancement in the accuracy and recognition rate of small-target detection achieved by GLU-YOLOv8, along with its efficient operational performance. This research provides valuable insights for optimizing small-target detection models for various pests and diseases. [ABSTRACT FROM AUTHOR]

Efficient diagnosis of apple diseases and pests is crucial to the healthy development of the apple industry. However, the existing single-source image-based classification methods have limitations due to the constraints of single-source input image information, resulting in low classification accuracy and poor stability. Therefore, a classification method for apple disease and pest areas based on multi-source image fusion is proposed in this paper. Firstly, RGB images and multispectral images are obtained using drones to construct an apple diseases and pests canopy multi-source image dataset. Secondly, a vegetation index selection method based on saliency attention is proposed, which uses a multi-label ReliefF feature selection algorithm to obtain the importance scores of vegetation indices, enabling the automatic selection of vegetation indices. Finally, an apple disease and pest area multi-label classification model named AMMFNet is constructed, which effectively combines the advantages of RGB and multispectral multi-source images, performs data-level fusion of multi-source image data, and combines channel attention mechanisms to exploit the complementary aspects between multi-source data. The experimental results demonstrated that the proposed AMMFNet achieves a significant subset accuracy of 92.92%, a sample accuracy of 85.43%, and an F1 value of 86.21% on the apple disease and pest multi-source image dataset, representing improvements of 8.93% and 10.9% compared to prediction methods using only RGB or multispectral images. The experimental results also proved that the proposed method can provide technical support for the coarse-grained positioning of diseases and pests in apple orchards and has good application potential in the apple planting industry. [ABSTRACT FROM AUTHOR]

The European pepper moth (Duponchelia fovealis) is predominant in the main strawberry production areas, including Brazil, as an important invasive pest and causes substantial damage to the crop. This damage is mainly attributed to the lack of effective management strategies. A promising alternative for managing this pest is implementing biological control through releasing natural enemies. This study determined the dispersal capacity of Trichogramma pretiosum for the management of D. fovealis in a strawberry crop in a low tunnel system 24, 48, and 72 h after parasitoid release. The experiments were carried out on strawberry farms in the mountainous region of Espírito Santo. Tunnels measuring 1.20 m wide by 50 m long were selected, in which artificial infestations of 30, 60, 90, and 120 eggs of D. fovealis were made on both sides of the strawberry tunnel at distances of 3, 7, 11, and 15 m, respectively, from the central point where the parasitoids were released. After the initial 24 h, new eggs were placed to replace the infested ones; the replacement was repeated at 48 and 72 h. The results indicated that, in strawberry plantations, T. pretiosum was efficient in parasitism. There was no difference between parasitism 24 and 48 h after parasitoid release, but parasitism was substantially lower after 72 h. The dispersion capacity of T. pretiosum was 14.21 linear meters, corresponding to an area of 17.05 m2. It is recommended that 93,000 T. pretiosum females be released per hectare every three days. [ABSTRACT FROM AUTHOR]

Glycoside hydrolases (GHs, also called glycosidases) catalyze the hydrolysis of glycosidic bonds in polysaccharides. Numerous GH genes have been identified from various organisms and are classified into 188 families, abbreviated GH1 to GH188. Enzymes in the GH32 family hydrolyze fructans, which are present in approximately 15% of flowering plants and are widespread across microorganisms. GH32 genes are rarely found in animals, as fructans are not a typical carbohydrate source utilized in animals. Here, we report the discovery of 242 GH32 genes identified in 84 animal species, ranging from nematodes to crabs. Genetic analyses of these genes indicated that the GH32 genes in various animals were derived from different bacteria via multiple, independent horizontal gene transfer events. The GH32 genes in animals appear functional based on the highly conserved catalytic blades and triads in the active center despite the overall low (35–60%) sequence similarities among the predicted proteins. The acquisition of GH32 genes by animals may have a profound impact on sugar metabolism for the recipient organisms. Our results together with previous reports suggest that the acquired GH32 enzymes may not only serve as digestive enzymes, but also may serve as effectors for manipulating host plants, and as metabolic enzymes in the non-digestive tissues of certain animals. Our results provide a foundation for future studies on the significance of horizontally transferred GH32 genes in animals. The information reported here enriches our knowledge of horizontal gene transfer, GH32 functions, and animal–plant interactions, which may result in practical applications. For example, developing crops via targeted engineering that inhibits GH32 enzymes could aid in the plant's resistance to animal pests. [ABSTRACT FROM AUTHOR]

Neonicotinoids are synthetic, nicotine-derived insecticides used worldwide to protect crops and domestic animals from pest insects. The reported evidence shows that they are also able to interact with mammalian nicotine receptors (nAChRs), triggering detrimental responses in cultured neurons. Exposure to high neonicotinoid levels during the fetal period induces neurotoxicity in animal models. Considering the persistent exposure to these insecticides and the key role of nAChRs in brain development, their potential neurotoxicity on mammal central nervous system (CNS) needs further investigations. We studied here the neurodevelopmental effects of different generations of neonicotinoids on CNS cells in mouse fetal brain and primary cultures and in neuronal cells and organoids obtained from human induced pluripotent stem cells (iPSC). Neonicotinoids significantly affect neuron viability, with imidacloprid (IMI) inducing relevant alterations in synaptic protein expression, neurofilament structures, and microglia activation in vitro, and in the brain of prenatally exposed mouse fetuses. IMI induces neurotoxic effects also on developing human iPSC-derived neurons and cortical organoids. Collectively, the current findings show that neonicotinoids might induce impairment during neuro/immune-development in mouse and human CNS cells and provide new insights in the characterization of risk for the exposure to this class of pesticides. [ABSTRACT FROM AUTHOR]

Detecting and recognizing pests are paramount for ensuring the healthy growth of crops, maintaining ecological balance, and enhancing food production. With the advancement of artificial intelligence technologies, traditional pest detection and recognition algorithms based on manually selected pest features have gradually been substituted by deep learning-based algorithms. In this review paper, we first introduce the primary neural network architectures and evaluation metrics in the field of pest detection and pest recognition. Subsequently, we summarize widely used public datasets for pest detection and recognition. Following this, we present various pest detection and recognition algorithms proposed in recent years, providing detailed descriptions of each algorithm and their respective performance metrics. Finally, we outline the challenges that current deep learning-based pest detection and recognition algorithms encounter and propose future research directions for related algorithms. [ABSTRACT FROM AUTHOR]

Simple Summary: Quinoa is an Andean grain that has gained global popularity due to its nutritional properties. The production area has expanded outside its Andean origins and the crop is now produced worldwide. However, new emerging pests cause serious problems in the crop and limit its production. This review discusses the status of the pests of quinoa in the world and the agricultural strategies implemented in the framework of integrated pest management (IPM). The literature regarding sampling methodologies for pest monitoring, determining economic threshold levels, cultural practices, and chemical and biological control is summarized, and a critical perspective on establishing IPM in quinoa is given. Since ancestral times, quinoa (Chenopodium quinoa Willd.) has been cultivated in the Andean regions. Recently, this pseudocereal has received increasing international attention due to its beneficial properties, such as adaptation and resilience in the context of global change, and the nutritional value of the grains. As a result, its production areas have not only increased in the highlands of South America but have also expanded outside of its Andean origins, and the crop is currently produced worldwide. The key pests of quinoa in the Andean region are the gelechiid moths Eurysacca melanocampta and Eurysacca quinoae; in other parts of the world, new pest problems have recently been identified limiting quinoa production, including the gelechiid Scrobipalpa atripicella in North America and Europe and the agromyzid fly Amauromyza karli in North America. In this review, the status of quinoa pests in the world is presented, and different aspects of their integrated management are discussed, including sampling methodologies for pest monitoring, economic threshold levels, and various control strategies. [ABSTRACT FROM AUTHOR]

Maize, as one of the most important crops in the world, faces severe challenges from various diseases and pests. The timely and accurate identification of maize leaf diseases and pests is of great significance for ensuring agricultural production. Currently, the identification of maize leaf diseases and pests faces two key challenges: (1) In the actual process of identifying leaf diseases and pests, complex backgrounds can interfere with the identification effect. (2) The subtle features of diseases and pests are difficult to accurately extract. To address these challenges, this study proposes a maize leaf disease and pest identification model called LFMNet. Firstly, the localized multi-scale inverted residual convolutional block (LMSB) is proposed to perform preliminary down-sampling on the image, preserving important feature information for the subsequent extraction of fine disease and pest features in the model structure. Then, the feature localization bottleneck (FLB) is proposed to improve the model's ability to focus on and locate disease and pest characteristics and to reduce interference from complex backgrounds. Subsequently, the multi-hop local-feature fusion architecture (MLFFA) is proposed, which effectively addresses the problem of extracting subtle features by enhancing the extraction and fusion of global and local disease and pest features in images. After training and testing on a dataset containing 19,451 images of maize leaf diseases and pests, the LFMNet model demonstrated excellent performance, with an average identification accuracy of 95.68%, a precision of 95.91%, a recall of 95.78%, and an F1 score of 95.83%. Compared to existing models, it exhibits significant advantages, offering robust technical support for the precise identification of maize diseases and pests. [ABSTRACT FROM AUTHOR]

Agriculture has a crucial impact on the economic, ecological, and social development of the world. More rapid and precise prevention and control work, especially for accurate classification and detection, is required due to the increasing severity of agricultural pests and diseases. However, the results of the image classification and detection are unsatisfactory because of the limitation of image data volume acquisition and the wide range of influencing factors of pests and diseases. In order to solve these problems, the vision transformer (ViT) model is improved, and a multi-scale and multi-factor ViT attention model (SFA-ViT) is proposed in this paper. Data augmentation considering multiple influencing factors is implemented in SFA-ViT to mitigate the impact of insufficient experimental data. Meanwhile, SFA-ViT optimizes the ViT model from a multi-scale perspective, and encourages the model to understand more features, from fine-grained to coarse-grained, during the classification task. Further, the detection model based on the self-attention mechanism of the multi-scale ViT is constructed to achieve the accurate localization of the pest and disease. Finally, experimental validation of the model, based on the IP102 and Plant Village dataset, is carried out. The results indicate that the various components of SFA-ViT effectively enhance the final classification and detection outcomes, and our model outperforms the current models significantly. [ABSTRACT FROM AUTHOR]

In recent years, the integration of smartphone technology with novel sensing technologies, Artificial Intelligence (AI), and Deep Learning (DL) algorithms has revolutionized crop pest and disease surveillance. Efficient and accurate diagnosis is crucial to mitigate substantial economic losses in agriculture caused by diseases and pests. An innovative Apple® and Android™ mobile application for citizen science has been developed, to enable real-time detection and identification of plant leaf diseases and pests, minimizing their impact on horticulture, viticulture, and olive cultivation. Leveraging DL algorithms, this application facilitates efficient data collection on crop pests and diseases, supporting crop yield protection and cost reduction in alignment with the Green Deal goal for 2030 by reducing pesticide use. The proposed citizen science tool involves all Farm to Fork stakeholders and farm citizens in minimizing damage to plant health by insect and fungal diseases. It utilizes comprehensive datasets, including images of various diseases and insects, within a robust Decision Support System (DSS) where DL models operate. The DSS connects directly with users, allowing them to upload crop pest data via the mobile application, providing data-driven support and information. The application stands out for its scalability and interoperability, enabling the continuous integration of new data to enhance its capabilities. It supports AI-based imaging analysis of quarantine pests, invasive alien species, and emerging and native pests, thereby aiding post-border surveillance programs. The mobile application, developed using a Python-based REST API, PostgreSQL, and Keycloak, has been field-tested, demonstrating its effectiveness in real-world agriculture scenarios, such as detecting Tuta absoluta (Meyrick) infestation in tomato cultivations. The outcomes of this study in T. absoluta detection serve as a showcase scenario for the proposed citizen science tool's applicability and usability, demonstrating a 70.2% accuracy (mAP50) utilizing advanced DL models. Notably, during field testing, the model achieved detection confidence levels of up to 87%, enhancing pest management practices. [ABSTRACT FROM AUTHOR]

Intelligent pest detection algorithms are capable of effectively detecting and recognizing agricultural pests, providing important recommendations for field pest control. However, existing recognition models have shortcomings such as poor accuracy or a large number of parameters. Therefore, this study proposes a lightweight and accurate rice pest detection algorithm based on improved YOLOv8. Firstly, a Multi-branch Convolutional Block Attention Module (M-CBAM) is constructed in the YOLOv8 network to enhance the feature extraction capability for pest targets, yielding better detection results. Secondly, the Minimum Points Distance Intersection over Union (MPDIoU) is introduced as a bounding box loss metric, enabling faster model convergence and improved detection results. Lastly, lightweight Ghost convolutional modules are utilized to significantly reduce model parameters while maintaining optimal detection performance. The experimental results demonstrate that the proposed method outperforms other detection models, with improvements observed in all evaluation metrics compared to the baseline model. On the test set, this method achieves a detection average precision of 95.8% and an F1-score of 94.6%, with a model parameter of 2.15 M, meeting the requirements of both accuracy and lightweightness. The efficacy of this approach is validated by the experimental findings, which provide specific solutions and technical references for intelligent pest detection. [ABSTRACT FROM AUTHOR]

The need to use environmentally friendly substances in agriculture for pest control has become increasingly urgent in recent years. This was generated by humanity's awareness of the harmful effects of chemicals with increased persistence, which accumulated in nature and harmed living beings. Essential oils are among the most important biopesticides and could significantly contribute to the expansion of ecological agriculture, replacing traditional methods. However, for judicious use, it is necessary to have a thorough knowledge of the mechanisms by which these oils act on both harmful and useful insects. An important step in transitioning from theory to practice is adapting essential oil application technologies for open fields, overcoming the difficulties created by their high volatility and low remanence, which results in a rapid reduction in the toxic effect. The review proposes an in-depth, up-to-date analysis of the existing literature on these subjects, aiming to provide researchers with some potential future study directions and practitioners with a solid base of information regarding the interaction between insects and essential oils. [ABSTRACT FROM AUTHOR]

This paper proposes PestNet, a lightweight method for classifying crop pests, which improves upon MobileNet-V2 to address the high model complexity and low classification accuracy commonly found in pest classification research. Firstly, the training phase employs the AdamW optimizer and mixup data augmentation techniques to enhance the model's convergence and generalization capabilities. Secondly, the Adaptive Spatial Group-Wise Enhanced (ASGE) attention mechanism is introduced and integrated into the inverted residual blocks of the MobileNet-V2 model, boosting the model's ability to extract both local and global pest information. Additionally, a dual-branch feature fusion module is developed using convolutional kernels of varying sizes to enhance classification performance for pests of different scales under real-world conditions. Lastly, the model's activation function and overall architecture are optimized to reduce complexity. Experimental results on a proprietary pest dataset show that PestNet achieves classification accuracy and an F1 score of 87.62% and 86.90%, respectively, marking improvements of 4.20 percentage points and 5.86 percentage points over the baseline model. Moreover, PestNet's parameter count and floating-point operations are reduced by 14.10% and 37.50%, respectively, compared to the baseline model. When compared with ResNet-50, MobileNet V3-Large, and EfficientNet-B1, PestNet offers superior parameter efficiency and floating-point operation requirements, as well as improved pest classification accuracy. [ABSTRACT FROM AUTHOR]

Pests have caused significant losses to agriculture, greatly increasing the detection of pests in the planting process and the cost of pest management in the early stages. At this time, advances in computer vision and deep learning for the detection of pests appearing in the crop open the door to the application of target detection algorithms that can greatly improve the efficiency of tomato pest detection and play an important technical role in the realization of the intelligent planting of tomatoes. However, in the natural environment, tomato leaf pests are small in size, large in similarity, and large in environmental variability, and this type of situation can lead to greater detection difficulty. Aiming at the above problems, a network target detection model based on deep learning, YOLONDD, is proposed in this paper. Designing a new loss function, NMIoU (Normalized Wasserstein Distance with Mean Pairwise Distance Intersection over Union), which improves the ability of anomaly processing, improves the model's ability to detect and identify objects of different scales, and improves the robustness to scale changes; Adding a Dynamic head (DyHead) with an attention mechanism will improve the detection ability of targets at different scales, reduce the number of computations and parameters, improve the accuracy of target detection, enhance the overall performance of the model, and accelerate the training process. Adding decoupled head to Head can effectively reduce the number of parameters and computational complexity and enhance the model's generalization ability and robustness. The experimental results show that the average accuracy of YOLONDD can reach 90.1%, which is 3.33% higher than the original YOLOv5 algorithm and is better than SSD, Faster R-CNN, YOLOv7, YOLOv8, RetinaNet, and other target detection networks, and it can be more efficiently and accurately utilized in tomato leaf pest detection. [ABSTRACT FROM AUTHOR]

Simple Summary: This study discusses the effects of cyantraniliprole, a new insecticide, on two lepidopteran pests and a biological control agent. Cyantraniliprole showed higher toxicity to one pest species compared to the other, prolonged developmental stages, and increased detoxification activity in both pest species. It also had a negative but slight impact on the biological control agent at the recommended concentrations. The study suggests that cyantraniliprole can effectively control the pests while being compatible with the control agent, but further field studies are needed for validation. Cyantraniliprole is a novel anthranilic diamide insecticide registered for controlling chewing and sucking insect pests. Here, the lethal and sublethal effects of this insecticide on two destructive lepidopteran pests, Spodoptera littoralis Boisduval and Agrotis ipsilon Hufnagel, were evaluated. Because the effects of novel insecticides on beneficial and non-target arthropods must be considered, the impact of cyantraniliprole on a generalist biological control agent, Chrysoperla carnea [Stephens 1836], were also examined. Overall, our study revealed that cyantraniliprole was more toxic to A. ipsilon than to S. littoralis. Moreover, the LC15 and LC50 of the insecticide significantly prolonged the duration of the larval and pupal stages and induced enzymatic detoxification activity in both species. Treatment of the second-instar larvae of C. carnea with the recommended concentration of cyantraniliprole (0.75 mg/L) doubled the mortality rates and resulted in a slight negative effect on the biology and detoxification enzymes of C. carnea. Our results indicate that both sublethal and lethal concentrations of cyantraniliprole can successfully suppress S. littoralis and A. ipsilon populations. They also suggest that C. carnea, as a generalist predator, is compatible with cyantraniliprole under the modelled realistic field conditions. In future investigations, insights into the effects of cyantraniliprole on S. littoralis, A. ipsilon, and C. carnea under field conditions will be required to appropriately validate our results. [ABSTRACT FROM AUTHOR]

Simple Summary: In South Korea, the increase in growing tropical and subtropical crops due to climate change and consumer demand has brought along a challenge: invasive insect pests damaging these fruits. To address this issue, we explored using ethyl formate (EF) fumigation as a safer alternative to traditional methods. We focused on two types of aphids, common pests in the trade of fresh produce. We found that EF effectively controlled aphids across different stages of fruit cultivation and post-harvest storage, achieving 100% mortality without harming the plants. Importantly, EF levels rapidly decreased after fumigation, ensuring safety. These findings suggest that EF fumigation could be a valuable solution for protecting crops from pests in a changing climate. This research provides farmers and policymakers with a safer and more sustainable method for pest control in greenhouse and post-harvest storage, ensuring the availability and quality of tropical fruits for consumers while reducing environmental risks associated with traditional pesticides. Tropical and subtropical crops are being increasingly cultivated in South Korea, leading to an increase in damage by exotic insect pests. Consequently, ethyl formate (EF) is currently being considered for quarantine and pre-shipment fumigation. In this study, we evaluated the effectiveness of EF fumigation for controlling Aphis spiraecola Patch and Aphis gossypii Glover, two representative quarantine pests on passion fruit ("Pink Bourbon") during greenhouse cultivation and post-harvest storage. The efficacy of EF against both aphids in terms of the lethal concentration causing 50% mortality (LCt50%) and LCt99% was 1.36–2.61 g h/m3 and 3.73–7.55 g h/m3 under greenhouse conditions (23 °C), and 1.37–2.02 g h/m3 and 3.80–14.59 g h/m3 post-harvest (5 °C), respectively. EF at 4 g/m3 for 4 h resulted in 100% mortality of A. spiraecola, which was more resistant to EF, without causing phytotoxic damage to the trees in a 340 m3 greenhouse. Post-harvest fruit fumigation at 10 g/m3 for 4 h in a mid-size (0.8 m3) fumigation chamber resulted in complete disinfection. Moreover, the EF level decreased below the EF threshold within 10 min after natural ventilation in the greenhouse. Therefore, our results suggest EF fumigation as an effective method for controlling A. spiraecola and A. gossypii. [ABSTRACT FROM AUTHOR]

Exploring the geographical distribution of forestry pests is crucial for formulating pest management strategies. Cyrtotrachelus buqueti (Guer) stands out as one of the primary pests among China's forestry hazards. This study employs the MaxEnt model, along with 19 bioclimatic variables and habitat characteristics, to predict the current and future distribution of C. buqueti under three typical emission scenarios for 2050 and 2070 (2.6 W/m2 (SSP1-2.6), 7.0 W/m2 (SSP3-7.0), and 8.5 W/m2 (SSP5-8.5)). Among the 19 bioclimatic variables, BIO 14 (precipitation of the driest month), BIO 8 (mean temperature of the wettest quarter), Elev, slope, and aspect were identified as significant contributors. These five variables are critical environmental factors affecting the suitability of habitats for C. buqueti and are representative of its potential habitat. The results indicate that C. buqueti predominantly inhabits southern regions such as Chongqing, Guizhou, Yunnan, Sichuan, Guangxi, Shaanxi, Hubei, Hainan, and Taiwan. Among them, Chongqing, Guizhou, and Yunnan are the primary distribution areas of high suitability. In the future, the centroid's movement direction will generally shift southward, with an expansion trend observed in the distribution areas of each province. This study enhances researchers' understanding of forestry pest dynamics and promotes proactive management strategies to mitigate their impact on forest ecosystems and agricultural productivity. [ABSTRACT FROM AUTHOR]

This study investigates the application of different ML methods for predicting pest outbreaks in Kazakhstan for grain crops. Comprehensive data spanning from 2005 to 2022, including pest population metrics, meteorological data, and geographical parameters, were employed to train the neural network for forecasting the population dynamics of Phyllotreta vittula pests in Kazakhstan. By evaluating various network configurations and hyperparameters, this research considers the application of MLP, MT-ANN, LSTM, transformer, and SVR. The transformer consistently demonstrates superior predictive accuracy in terms of MSE. Additionally, this work highlights the impact of several training hyperparameters such as epochs and batch size on predictive accuracy. Interestingly, the second season exhibits unique responses, stressing the effect of some features on model performance. By advancing our understanding of fine-tuning ANNs for accurate pest prediction in grain crops, this research contributes to the development of more precise and efficient pest control strategies. In addition, the consistent dominance of the transformer model makes it suitable for its implementation in practical applications. Finally, this work contributes to sustainable agricultural practices by promoting targeted interventions and potentially reducing reliance on chemical pesticides. [ABSTRACT FROM AUTHOR]

To address the current issues of complex structures and low accuracies in citrus pest identification models, a lightweight pest identification model was proposed. First, a parameterized linear rectification function was introduced to avoid neuronal death. Second, the model's attention to pest characteristics was improved by incorporating an improved mixed attention mechanism. Subsequently, the network structure of the original model was adjusted to reduce architectural complexity. Finally, by employing transfer learning, an SCHNet model was developed. The experimental results indicated that the proposed model achieved an accuracy rate of 94.48% with a compact size of 3.84 MB. Compared to the original ShuffleNet V2 network, the SCHNet model showed a 3.12% accuracy improvement while reducing the model size by 22.7%. The SCHNet model exhibited an excellent classification performance for citrus pest identification, enabling the accurate identification of citrus pests. [ABSTRACT FROM AUTHOR]

To investigate an effective physical pest control method for tea trees, we designed and manufactured a suction-based pest-capture machine (hereafter labeled the "pest vacuum") and conducted a test and field experiment to evaluate its effectiveness in the control of Empoasca vitis Göthe (E. vitis). Based on the proposed model, the minimum practical air velocity of the pest vacuum was 5.85 m s−1. The field experiment included two treatments and a blank control. In treatment 1, we used the pest vacuum along tea trees only once, while in treatment 2, the pest vacuum was used along trees twice, separately, in 2 consecutive periods, and with an interval of more than 30 min. The results show that a highly significant difference arose among the dropping rates of the two treatments and the blank control instantly after suction, a significant difference among the dropping rates 7 days later, and no significant difference 14 days later. The dropping rate and the effective rate of prevention of treatment 2 reached 81.87% and 80.60% instantly after suction. Moreover, the effective rate of prevention of nymphs was slightly higher than that of adults. Overall, the pest vacuum had a prominent, albeit short-term, effect on the control of E. vitis. Seven days after the suction, it is better to repeat the suction five days after the first suction. The pest vacuum provides a valid physical method for pest control, so more attention should be paid in future investigations to reducing the weight and working noise of the pest vacuum. [ABSTRACT FROM AUTHOR]

Pest target identification in agricultural production environments is challenging due to the dense distribution, small size, and high density of pests. Additionally, changeable environmental lighting and complex backgrounds further complicate the detection process. This study focuses on enhancing the recognition performance of tea pests by introducing a lightweight pest image recognition model based on the improved YOLOv8 architecture. First, slicing-aided fine-tuning and slicing-aided hyper inference (SAHI) are proposed to partition input images for enhanced model performance on low-resolution images and small-target detection. Then, based on an ELAN, a generalized efficient layer aggregation network (GELAN) is designed to replace the C2f module in the backbone network, enhance its feature extraction ability, and construct a lightweight model. Additionally, the MS structure is integrated into the neck network of YOLOv8 for feature fusion, enhancing the extraction of fine-grained and coarse-grained semantic information. Furthermore, the BiFormer attention mechanism, based on the Transformer architecture, is introduced to amplify target characteristics of tea pests. Finally, the inner-MPDIoU, based on auxiliary borders, is utilized as a replacement for the original loss function to enhance its learning capacity for complex pest samples. Our experimental results demonstrate that the enhanced YOLOv8 model achieves a precision of 96.32% and a recall of 97.95%, surpassing those of the original YOLOv8 model. Moreover, it attains an mAP@50 score of 98.17%. Compared to Faster R-CNN, SSD, YOLOv5, YOLOv7, and YOLOv8, its average accuracy is 17.04, 11.23, 5.78, 3.75, and 2.71 percentage points higher, respectively. The overall performance of YOLOv8 outperforms that of current mainstream detection models, with a detection speed of 95 FPS. This model effectively balances lightweight design with high accuracy and speed in detecting small targets such as tea pests. It can serve as a valuable reference for the identification and classification of various insect pests in tea gardens within complex production environments, effectively addressing practical application needs and offering guidance for the future monitoring and scientific control of tea insect pests. [ABSTRACT FROM AUTHOR]

Outbreaks of the oriental fruit fly, Bactrocera dorsalis (Hendel), present significant challenges to global fruit production, necessitating effective control measures that minimize environmental risks and pesticide resistance. This study aimed to develop and evaluate the effectiveness of four distinct push–pull control strategies for managing B. dorsalis outbreaks in a Nephelium lappaceum orchard. These strategies involved the inclusion of low-concentration abamectin, spraying repellent with a drone or manually, using methyl eugenol (ME) or food bait and employing either two types of attractants and repellents or a single type. The findings indicated that incorporating the low-concentration abamectin into the push–pull system, utilizing ME as an attractant instead of food lures and manually applying abamectin and attractants were all effective in reducing the B. dorsalis population size and minimizing fruit damage. While increasing the diversity of repellents and attractants enhanced the long-term effectiveness of the system, it did not result in a significant decrease in B. dorsalis population size or fruit damage rate compared to using a single repellent or attractant. In conclusion, the push–pull strategy emerged as a viable method for managing B. dorsalis outbreaks, offering potential benefits in reducing environmental risks and pesticide resistance. However, the study underscored the importance of the context-specific construction of push–pull strategies to optimize their effectiveness in orchard settings. [ABSTRACT FROM AUTHOR]

Traditional methods for pest recognition have certain limitations in addressing the challenges posed by diverse pest species, varying sizes, diverse morphologies, and complex field backgrounds, resulting in a lower recognition accuracy. To overcome these limitations, this paper proposes a novel pest recognition method based on attention mechanism and multi-scale feature fusion (AM-MSFF). By combining the advantages of attention mechanism and multi-scale feature fusion, this method significantly improves the accuracy of pest recognition. Firstly, we introduce the relation-aware global attention (RGA) module to adaptively adjust the feature weights of each position, thereby focusing more on the regions relevant to pests and reducing the background interference. Then, we propose the multi-scale feature fusion (MSFF) module to fuse feature maps from different scales, which better captures the subtle differences and the overall shape features in pest images. Moreover, we introduce generalized-mean pooling (GeMP) to more accurately extract feature information from pest images and better distinguish different pest categories. In terms of the loss function, this study proposes an improved focal loss (FL), known as balanced focal loss (BFL), as a replacement for cross-entropy loss. This improvement aims to address the common issue of class imbalance in pest datasets, thereby enhancing the recognition accuracy of pest identification models. To evaluate the performance of the AM-MSFF model, we conduct experiments on two publicly available pest datasets (IP102 and D0). Extensive experiments demonstrate that our proposed AM-MSFF outperforms most state-of-the-art methods. On the IP102 dataset, the accuracy reaches 72.64%, while on the D0 dataset, it reaches 99.05%. [ABSTRACT FROM AUTHOR]

The significance of environmental considerations has been highlighted by the substantial impact of plant pests on ecosystems. Addressing the urgent demand for sophisticated pest management solutions in arboreal environments, this study leverages advanced deep learning technologies to accurately detect and classify common tree pests, such as "mole cricket", "aphids", and "Therioaphis maculata (Buckton)". Through comparative analysis with the baseline model ResNet-18 model, this research not only enhances the SE-RegNetY and SE-RegNet models but also introduces innovative frameworks, including GCT-Inception-ResNet-V3, SE-Inception-ResNet-V3, and SE-Inception-RegNetY-V3 models. Notably, the GCT-Inception-ResNet-V3 model demonstrates exceptional performance, achieving a remarkable average overall accuracy of 94.59%, average kappa coefficient of 91.90%, average mAcc of 94.60%, and average mIoU of 89.80%. These results signify substantial progress over conventional methods, outperforming the baseline model's results by margins of 9.1%, nearly 13.7%, 9.1%, and almost 15% in overall accuracy, kappa coefficient, mAcc, and mIoU, respectively. This study signifies a considerable step forward in blending sustainable agricultural practices with environmental conservation, setting new benchmarks in agricultural pest management. By enhancing the accuracy of pest identification and classification in agriculture, it lays the groundwork for more sustainable and eco-friendly pest control approaches, offering valuable contributions to the future of agricultural protection. [ABSTRACT FROM AUTHOR]

Corn (Zea mays L.) is an important cereal for food sovereignty, extensively planted due to its adaptation to various agroecological conditions. Climatic conditions and pests can affect its production. Concerning the latter, natural enemies could be considered in biological control programs. The objective of this study was to estimate the influence of the presence of insects, damage to plants and cobs, and their incidence on corn yield in two planting seasons. During the rainy (February to May) and dry seasons (Jun to October) of the year 2023, in Calceta, Lodana, and Quevedo, three important corn-growing areas on the Ecuadorian coast, corn plots of 1126 m2 were planted. The diversity of phytophagous and natural enemies was estimated. Damage to young plants and cobs was observed, and corn yield was determined. Of the 9073 insects observed, 44.2% and 55.8% constituted phytophagous and natural enemies, respectively. A moderate diversity (Shannon-H Index = 2.474–2.629 and Margalef Index = 2.734–3.110) of insects associated with corn was determined. Yield (range: 6.9 to 15.3 t) was negatively correlated with rainfall and cob damage (p < 0.05). Although precipitation is necessary for planting in rainy season, frequent and intense rains could be affect corn yield. [ABSTRACT FROM AUTHOR]

Simple Summary: The attraction of moths to light sources has long been used to reduce the damage of agricultural pests, starting in antiquity with controlled fires in the vicinity of crops. Coinciding with their development in the 18th century, light traps have been used to control pest populations by culling densities of adults lured to death at light sources (light trap-based mass trapping, or LTmt). Historically, the most extensive large-scale LTmt trials were conducted in the U.S.A. starting in the 1920s, validating in the process the hypothesis that crop damage can be reduced by removing egg-carrying females from the pest reproductive pool. Light-based mass trapping programs were phased out in the 1970s, coinciding with the implementation of pheromone-based pest management. With the advent of LEDs, solar power sources, and intelligent designs, recent years have seen an uptick of interest in LTmt, with the majority of contemporary studies conducted in Asia. As a rule, LTmt trials have been conducted exclusively in agricultural landscapes. A novel approach is proposed here to control epidemic populations of a tortricid forest pest, spruce budworm, in geographically isolated forests of balsam firs at a high risk of intense defoliation and mortality. The management of Lepidopteran pests with light traps (LTs) is often achieved by luring adults to death at light sources (light trap-based mass trapping, or LTmt). Large-scale LTmt programs against agricultural pests initiated in the late 1920s in the United States were phased out in the 1970s, coinciding with the rise of pheromone-based management research. The interest in LTmt has surged in recent years with the advent of light emitting diodes, solar power sources, and intelligent design. The first step in implementing LTmt is to identify a trapping design that maximizes the capture of target pests and minimizes the capture of non-target beneficial insects—with a cautionary note that high captures in LTs are not equivalent to the feasibility of mass trapping: the ultimate objective of LTmt is to protect crop plants from pest damage, not to trap adults. The captures of egg-carrying females in light traps have a greater impact on the efficiency of LTmt than the captures of males. When LTmt is defined as a harvesting procedure, the biomass of females in LTs may be viewed as the best estimator of the mass trapping yield; biomass proxy has universal application in LTmt as every living organism can be defined on a per weight basis. While research has largely focused on agricultural pests, an attempt is made here to conceptualize LTmt as a pest management strategy in forest ecosystems, using spruce budworm as a case study. The mass trapping of female budworms is impossible to achieve in endemic populations due to the large spatial scale of forest landscapes (implying the deployment of a prohibitively large number of LTs); in addition, ovipositing female budworms do not respond to light sources at a low density of conspecifics. The light-based mass trapping of female budworms may provide a realistic management option for geographically isolated forest stands heavily infested with budworms, as a tool to prevent tree mortality. Somehow unexpectedly, however, one factor obscuring the feasibility of LTmt is as follows: the complex ('unknowable') economic valuation of forest stands as opposed to agricultural landscapes. [ABSTRACT FROM AUTHOR]

Simple Summary: Today's society demands a better balance between the needs of agricultural production and environmental protection, particularly in reducing the application of pesticides. Compared to the past, fewer pesticide active ingredients are allowed and available in the European Union. One pest that is controlled by pesticides is our model pest, the pea moth (Cydia nigricana), which can cause damage to pea seeds (Pisum sativum). The aim of this study was to develop alternative and preventive strategies that can be used as crop protection in the shape of a GIS-based planning tool for crop rotation with a minimum distance to avoid specific pests. In our tool, the distance between current and previous pea sites was important, because insect pests follow their host plants. The hypothesis is that the greater the distance, the less infestation. We developed a web tool to create buffers with different distances around the previous pea sites to calculate the infestation risk for future pea sites. The web tool can be adapted in terms of distance and risk classes for other pests. Consequently, our tool helps to avoid pest infestation, and therefore, farmers can reduce pesticide applications, which protects the environment and strengthens biodiversity. Crop rotation is an important strategy for pest reduction. For mono-, or oligophagous pests that overwinter at a previously infested site, crop rotation means that the pests must find new host crop sites in the following year, and it is more efficient if a pest-specific distance is applied. Here, we report the development of a GIS-based tool for efficient cultivation planning using the example of the pest complex pea moth (Cydia nigricana) and grain and green peas (Pisum sativum). Monitoring data for four consecutive years (2016–2019) from 513 sites were used. Infestation of pea seeds and the distance to the previous year's pea sites were recorded. An adjustable Python script was developed by means of infestation–distance–correlation as a pest and crop-specific minimum migration distance (MD). The output of the tool is a risk map as decision support for cultivation planning. It shows different risk buffers with distances from 1261 m to 1825 m, depending on the cultivation type. The web tool is easily adjustable to other pests and crops anywhere in the world. The tool helps to prevent damages caused by agricultural, mono-, or oligophagous insect pests and consequently reduces pesticide applications for the benefit of the environment and biodiversity. [ABSTRACT FROM AUTHOR]

To maintain the continuous genetic variation and increase the genetic gain, appreciable germplasm diversity and its comprehensive characterization is necessary to further utilize gene sources for pre-breeding. The diversity of pepper forms, cultivation traditions and diverse fruit usages are typical for Balkan countries. Considering this rich diversity, 21 pepper accessions from the Balkan region were evaluated for morphological, biochemical, and insect resistance traits during 2018 and 2019 at Maritsa Vegetable Crops Research Institute, Plovdiv, Bulgaria. Among the studied accessions, the highest productivity was observed in pumpkin shape K1115 and kapia type K1081 accessions, with 0.74 kg and 0.70 kg per plant, respectively. Concerning fruit quality, the highest total polyphenols and ferric reducing antioxidant power (FRAP) were observed in pumpkin shape K712 (203.44 mg GAE/100 g FW) and K1103A (11.49 µmol Fe2+/g FW) accessions, respectively. Concerning insect resistance, 38% of studied accessions showed no infestation of green peach aphid. The kapia type K697 accession was seen as the most reliable resistance source, as it was not infested by aphids and had the least thrips (20% on plants) and cotton bollworm (6.67% on plants and 8.34% on fruit) damage. Based on examined traits, accessions were identified for enhanced fruit quality and promising insect resistance and have been included in further pre-breeding efforts. [ABSTRACT FROM AUTHOR]

Pest detection: This process is essential for the early warning of pests in the agricultural sector. However, the challenges posed by agricultural pest datasets include but are not limited to species diversity, small individuals, high concentration, and high similarity, which greatly increase the difficulty of pest detection and control. To effectively solve these problems, this paper proposes an innovative object detection model named MACNet. MACNet is optimized based on YOLOv8s, introducing a content-based feature sampling strategy to obtain richer object feature information, and adopts distribution shifting convolution technology, which not only improves the accuracy of detection but also successfully reduces the size of the model, making it more suitable for deployment in the actual environment. Finally, our test results on the Pest24 dataset verify the good performance of MACNet; its detection accuracy reaches 43.1 A P which is 0.5 A P higher than that of YOLOv8s, and the computational effort is reduced by about 30%. This achievement not only demonstrates the efficiency of MACNet in agricultural pest detection, but also further confirms the great potential and practical value of deep learning technology in complex application scenarios. [ABSTRACT FROM AUTHOR]

The tea industry, as one of the most globally important agricultural products, is characterized by pests and diseases that pose a serious threat to yield and quality. These diseases and pests often present different scales and morphologies, and some pest and disease target sizes can be tiny and difficult to detect. To solve these problems, we propose TeaViTNet, a multi-scale attention-based tea pest and disease detection model that combines CNNs and Transformers. First, MobileViT is used as the feature extraction backbone network. MobileViT captures and analyzes the tiny pest and disease features in the image via a self-attention mechanism and global feature extraction. Second, the EMA-PANet network is introduced to optimize the model's learning and attention to the Apolygus lucorum and leaf blight regions via an efficient multi-scale attention module with cross-space learning, which improves the model's ability to understand multi-scale information. In addition, RFBNet is embedded in the module to further expand the perceptual range and effectively capture the information of tiny features in tea leaf images. Finally, the ODCSPLayer convolutional block is introduced, aiming to focus on acquiring richer gradient flow information. The experimental results show that the TeaViTNet model proposed in this paper has an average accuracy of 89.1%, which is a significant improvement over the baseline network MobileViT and is capable of accurately detecting Apolygus lucorum and leaf blight of different scales and complexities. [ABSTRACT FROM AUTHOR]

This study investigated the efficacy of three spray adjuvants (Coerce, Wetcit, and Silwet408) in enhancing dinotefuran permeation in rice leaves. Different concentrations of these adjuvants were tested using an external standard method. The rice leaf surface was analyzed by using the van Oss–Chaudhury–Good method to establish a link between surface free energy (SFE) and dinotefuran permeation. All of the adjuvants effectively increased dinotefuran permeation in rice leaves, with the highest permeation of 8.496 mg/kg achieved using Wetcit at 1000 mg/L. The SFE of the rice leaf surface was determined to be 29.28 mJ/m2. A notable correlation was observed between the energy difference (the SFE of the pesticide liquid versus the SFE of the rice leaf surface) and permeation. Various fitting methods, including linear, exponential, logarithmic, polynomial, and power methods, were applied. Polynomial fitting demonstrated the highest coefficient of determination (R2 > 0.9000). The relationship between the permeation (y) and energy difference (Δγ) conformed to the polynomial equation y = aΔγ2 + bΔγ + c, where a, b, and c are constants. This model provides a predictive tool for the optimal dosage of spray adjuvants according to target plant characteristics, enhancing the understanding of the interaction between pests and pesticides. [ABSTRACT FROM AUTHOR]

Simple Summary: While feeding, the larvae of pygmy moths (Nepticulidae) consume part of a leaf's photosynthetic tissue, thus causing damage to the host plant. Although these insects play a natural role in terrestrial ecosystems, they are perceived as pests in horticulture. This study investigates the identity of a potential Nepticulidae pest infesting plum trees in the Caucasus, initially presumed to be the widespread European Stigmella plagicolella (Stainton). Contrary to expectations, our detailed taxonomic analysis revealed a new species of pygmy moth with distinct male genitalia morphology and molecular differences from its European counterpart. This discovery challenges previous records and highlights the need for accurate pest identification. We hypothesize that the proximity of the Caucasus to Europe emphasizes the importance of monitoring and preventing unintentional pest spread, particularly given potential climate change impacts on the distribution and behavior of pests. Our findings contribute to both practical pest management and scientific understanding of evolutionary processes shaping the Caucasian and European biota. In instances of severe infestations, Nepticulidae larvae can inflict damage on cultivated plants. Previously, it was assumed that the Prunus-feeding Nepticulidae have continuous distribution from Europe to the neighboring Caucasus. During recent fieldwork in the Caucasus, leaf mines were found on plum trees that initially resembled those of Stigmella plagicolella (Stainton) in Europe. However, upon rearing the adults, significant differences emerged, leading to the hypothesis that a different Prunus-feeding species exists in the Caucasus; this challenges previous records in Western Asia. This paper presents the outcomes of our morphological, molecular, and statistical investigations, unveiling S. colchica sp. nov., a previously unknown potential plum-tree pest. Distinguished by male genitalia characteristics, the new species differs from S. plagicolella. The inter- and intraspecific divergences between S. colchica sp. nov. and S. plagicolella range from 3.5% to 6.02%. Moreover, the utilized delimitation algorithms reliably clustered two species separately, as does our mitotype network. A statistical analysis also shows a discernible trend between the leaf mines of S. colchica sp. nov. and S. plagicolella. This unexpected discovery not only documents a new potential pest, enhancing our understanding of the Caucasian fauna, but also contributes to the broader biological inventory. [ABSTRACT FROM AUTHOR]

Simple Summary: An outbreak of the unique pest Erannis jacobsoni Djak in Mongolia would severely impact the forest ecosystem. Therefore, this study employed a combination mode of UAV-RGB vegetation indices and texture features, utilizing the sequential projection algorithm to extract sensitive features and machine learning algorithms to construct a damage level recognition model, achieving low-cost, rapid, and effective pest detection. The results indicate that the combined mode of the RGB vegetation indices and texture features yielded good pest detection results, with an overall accuracy of 89%. This could provide an important experimental foundation for subsequent large-scale forest pest monitoring with a high spatiotemporal resolution. Erannis jacobsoni Djak (Lepidoptera, Geometridae) is a leaf-feeding pest unique to Mongolia. Outbreaks of this pest can cause larch needles to shed slowly from the top until they die, leading to a serious imbalance in the forest ecosystem. In this work, to address the need for the low-cost, fast, and effective identification of this pest, we used field survey indicators and UAV images of larch forests in Binder, Khentii, Mongolia, a typical site of Erannis jacobsoni Djak pest outbreaks, as the base data, calculated relevant multispectral and red–green–blue (RGB) features, used a successive projections algorithm (SPA) to extract features that are sensitive to the level of pest damage, and constructed a recognition model of Erannis jacobsoni Djak pest damage by combining patterns in the RGB vegetation indices and texture features (RGBVI&TF) with the help of random forest (RF) and convolutional neural network (CNN) algorithms. The results were compared and evaluated with multispectral vegetation indices (MSVI) to explore the potential of UAV RGB images in identifying needle pests. The results show that the sensitive features extracted based on SPA can adequately capture the changes in the forest appearance parameters such as the leaf loss rate and the colour of the larch canopy under pest damage conditions and can be used as effective input variables for the model. The RGBVI&TF-RF440 and RGBVI&TF-CNN740 models have the best performance, with their overall accuracy reaching more than 85%, which is a significant improvement compared with that of the RGBVI model, and their accuracy is similar to that of the MSVI model. This low-cost and high-efficiency method can excel in the identification of Erannis jacobsoni Djak-infested regions in small areas and can provide an important experimental theoretical basis for subsequent large-scale forest pest monitoring with a high spatiotemporal resolution. [ABSTRACT FROM AUTHOR]

In response to the shortcomings of traditional pest detection methods, such as inadequate accuracy and slow detection speeds, a lightweight forestry pest image recognition model based on an improved YOLOv8 architecture is proposed. Initially, given the limited availability of real deep forest pest image data in the wild, data augmentation techniques, including random rotation, translation, and Mosaic, are employed to expand and enhance the dataset. Subsequently, the traditional Conv (convolution) layers in the neck module of YOLOv8 are replaced with lightweight GSConv, and the Slim Neck design paradigm is utilized for reconstruction to reduce computational costs while preserving model accuracy. Furthermore, the CBAM attention mechanism is introduced into the backbone network of YOLOv8 to enhance the feature extraction of crucial information, thereby improving detection accuracy. Finally, WIoU is employed as a replacement for the traditional CIOU to enhance the overall performance of the detector. The experimental results demonstrate that the improved model exhibits a significant advantage in the field of forestry pest detection, achieving precision and recall rates of 98.9% and 97.6%, respectively. This surpasses the performance of the current mainstream network models. [ABSTRACT FROM AUTHOR]

The extraction of entities and relationships is a crucial task in the field of natural language processing (NLP). However, existing models for this task often rely heavily on a substantial amount of labeled data, which not only consumes time and labor but also hinders the development of downstream tasks. Therefore, with a focus on enhancing the model's ability to learn from small samples, this paper proposes an entity and relationship extraction method based on the Universal Information Extraction (UIE) model. The core of the approach is the design of a specialized prompt template and schema on cotton pests and diseases as one of the main inputs to the UIE, which, under its guided fine-tuning, enables the model to subdivide the entity and relationship in the corpus. As a result, the UIE-base model achieves an accuracy of 86.5% with only 40 labeled training samples, which really solves the problem of the existing models that require a large amount of manually labeled training data for knowledge extraction. To verify the generalization ability of the model in this paper, experiments are designed to compare the model with four classical models, such as the Bert-BiLSTM-CRF. The experimental results show that the F1 value on the self-built cotton data set is 1.4% higher than that of the Bert-BiLSTM-CRF model, and the F1 value on the public data set is 2.5% higher than that of the Bert-BiLSTM-CRF model. Furthermore, experiments are designed to verify that the UIE-base model has the best small-sample learning performance when the number of samples is 40. This paper provides an effective method for small-sample knowledge extraction. [ABSTRACT FROM AUTHOR]

This study aimed to analyze farmers' perceptions of maize production constraints and determine the effects of push–pull technology (PPT) on crop yield, pest control, and improving soil fertility status. Increasing fertilizer prices and pesticide prices, FAWs (fall armyworms) and stemborers, declining soil fertility, and drought are the main maize production constraints in the area. Seventy percent of the respondents indicated that an increase in input prices such as those of fertilizer and seeds is the major constraint in the area, while FAWs (55%) and stemborers (44.3%) were ranked the third and fourth major constraints. About 67% of farmers reported that stemborer damage to maize in PPT plots was either minimal or non-existent. Fifty-five percent of farmers stated that the damage caused to maize by FAWs was low or that there was no damage in PPT plots. PPT reduced stem borer infestation from 83% to 44%. The yield gained from PPT plots ranged from 18% to 31%. Soil samples taken from PPT plots showed improved soil organic carbon, organic matter, total nitrogen, and cation exchange capacity. [ABSTRACT FROM AUTHOR]

Due to the challenges of pest detection in complex environments, this research introduces a lightweight network for tobacco pest identification leveraging enhancements in YOLOv8 technology. Using YOLOv8 large (YOLOv8l) as the base, the neck layer of the original network is replaced with an asymptotic feature pyramid network (AFPN) network to reduce model parameters. A SimAM attention mechanism, which does not require additional parameters, is incorporated to improve the model's ability to extract features. The backbone network's C2f model is replaced with the VoV-GSCSP module to reduce the model's computational requirements. Experiments show the improved YOLOv8 model achieves high overall performance. Compared to the original model, model parameters and GFLOPs are reduced by 52.66% and 19.9%, respectively, while mAP@0.5 is improved by 1%, recall by 2.7%, and precision by 2.4%. Further comparison with popular detection models YOLOv5 medium (YOLOv5m), YOLOv6 medium (YOLOv6m), and YOLOv8 medium (YOLOv8m) shows the improved model has the highest detection accuracy and lightest parameters for detecting four common tobacco pests, with optimal overall performance. The improved YOLOv8 detection model proposed facilitates precise, instantaneous pest detection and recognition for tobacco and other crops, securing high-accuracy, comprehensive pest identification. [ABSTRACT FROM AUTHOR]

The Apiaceae family, known for aromatic plants producing bioactive essential oils (EOs), holds significance across sectors, including agrochemicals. This study evaluated the insecticidal potential of four Apiaceae EOs from Crithmum maritimum L., Trachyspermum ammi (L.) Sprague ex Turrill, Smyrnium olusatrum L., and Elwendia persica (Boiss.) Pimenov and Kljuykov against various significant storage pests (Sitophilus oryzae (L.), Trogoderma granarium Everts, Rhyzopertha dominica (F.), Tribolium castaneum (Herbst), T. confusum Jacquelin du Val, Oryzaephilus surinamensis (L.), Alphitobius diaperinus (Panzer), Acarus siro L., and Tenebrio molitor L.) on wheat. Insect mortality rates were monitored at intervals of 1, 2, 3, 4, 5, 6, and 7 days. Smyrnium olusatrum EO exhibited the highest efficacy, followed by T. ammi, C. maritimum, and E. persica EOs, although efficacy varied by species, developmental stage, and concentration. Notably, complete mortality occurred for several pests at 1000 ppm of S. olusatrum and T. ammi EOs. Gas chromatography–mass spectrometry (GC–MS) analysis revealed key compounds in these EOs, including myrcene, germacrone, and curzerene in S. olusatrum EO, and thymol, γ-terpinene, and p-cymene in T. ammi EO. These findings emphasize their potential as botanical insecticides. Smyrnium olusatrum and T. ammi EOs emerge as promising eco-friendly pest management options due to their efficacy, highlighted compound composition, and availability of biomass from both wild and cultivated sources. [ABSTRACT FROM AUTHOR]

The escalating global food demand driven by a gradually expanding human population necessitates strategies to improve agricultural productivity favorably and mitigate crop yield loss caused by various stressors (biotic and abiotic). Biotic stresses are caused by phytopathogens, pests, and nematodes, along with abiotic stresses like salt, heat, drought, and heavy metals, which pose serious risks to food security and agricultural productivity. Presently, the traditional methods relying on synthetic chemicals have led to ecological damage through unintended impacts on non-target organisms and the emergence of microbes that are resistant to them. Therefore, addressing these challenges is essential for economic, environmental, and public health concerns. The present review supports sustainable alternatives, emphasizing the possible application of fungal endophytes as innovative and eco-friendly tools in plant stress management. Fungal endophytes demonstrate capabilities for managing plants against biotic and abiotic stresses via the direct or indirect enhancement of plants' innate immunity. Moreover, they contribute to elevated photosynthesis rates, stimulate plant growth, facilitate nutrient mineralization, and produce bioactive compounds, hormones, and enzymes, ultimately improving overall productivity and plant stress resistance. In conclusion, harnessing the potentiality of fungal endophytes represents a promising approach toward the sustainability of agricultural practices, offering effective alternative solutions to reduce reliance on chemical treatments and address the challenges posed by biotic and abiotic stresses. This approach ensures long-term food security and promotes environmental health and economic viability in agriculture. [ABSTRACT FROM AUTHOR]

The Siberian moth, Dendrolimus sibiricus Tschetv., 1908 (Lepidoptera: Lasiocampidae) is a conifer pest that causes unprecedented forest mortality in Northern Asia, leading to enormous ecological and economic losses. This is the first study summarizing data on the parasitoid diversity and parasitism of this pest over the last 118 years (1905–2022). Based on 860 specimens of freshly reared and archival parasitoids, 16 species from two orders (Hymenoptera and Diptera) were identified morphologically and/or with the use of DNA barcoding. For all of them, data on distribution and hosts and images of parasitoid adults are provided. Among them, the braconid species, Meteorus versicolor (Wesmael, 1835), was documented as a parasitoid of D. sibiricus for the first time. The eastern Palaearctic form, Aleiodes esenbeckii (Hartig, 1838) dendrolimi (Matsumura, 1926), status nov., was resurrected from synonymy as a valid subspecies, and a key for its differentiation from the western Palaearctic subspecies Aleiodes esenbeckii ssp. esenbecki is provided. DNA barcodes of 11 parasitoid species from Siberia, i.e., nine hymenopterans and two dipterans, represented novel records and can be used for accurate molecular genetic identification of species. An exhaustive checklist of parasitoids accounting for 93 species associated with D. sibirisus in northern Asia was compiled. Finally, the literature and original data on parasitism in D. sibiricus populations for the last 83 years (1940–2022) were analysed taking into account the pest population dynamics (i.e., growth, outbreak, decline, and depression phases). A gradual time-lagged increase in egg and pupal parasitism in D. sibiricus populations was detected, with a peak in the pest decline phase. According to long-term observations, the following species are able to cause significant mortality of D. sibiricus in Northern Asia: the hymenopteran egg parasitoids Telenomus tetratomus and Ooencyrtus pinicolus; the larval parasitoids Aleiodes esenbeckii sp. dendrolimi, Cotesia spp., and Glyptapanteles liparidis; and the dipteran pupal parasitoids Masicera sphingivora, Tachina sp., and Blepharipa sp. Their potential should be further explored in order to develop biocontrol programs for this important forest pest. [ABSTRACT FROM AUTHOR]