Search

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: The red palm weevil is an exotic and highly endangered pest that is extremely harmful to palm plants. In order to effectively control this pest, we propose an algorithm to automatically detect and count adult red palm weevils in traps. Previously, the trapping and counting of adult red palm weevils was done manually. The population density and damage level were then inferred from the number of adults trapped to guide control efforts. However, the efficiency of this method is very low. The algorithm proposed in this paper solves the drawbacks of manual counting, and the recognition accuracy reaches 93.8%, which also improves the efficiency of agricultural monitoring. The red palm weevil (RPW, Rhynchophorus ferrugineus) is an invasive and highly destructive pest that poses a serious threat to palm plants. To improve the efficiency of adult RPWs' management, an enhanced YOLOv5 object detection algorithm based on an attention mechanism is proposed in this paper. Firstly, the detection capabilities for small targets are enhanced by adding a convolutional layer to the backbone network of YOLOv5 and forming a quadruple down-sampling layer by splicing and down-sampling the convolutional layers. Secondly, the Squeeze-and-Excitation (SE) attention mechanism and Convolutional Block Attention Module (CBAM) attention mechanism are inserted directly before the SPPF structure to improve the feature extraction capability of the model for targets. Then, 2600 images of RPWs in different scenes and forms are collected and organized for data support. These images are divided into a training set, validation set and test set following a ratio of 7:2:1. Finally, an experiment is conducted, demonstrating that the enhanced YOLOv5 algorithm achieves an average precision of 90.1% (mAP@0.5) and a precision of 93.8% (P), which is a significant improvement compared with related models. In conclusion, the enhanced model brings a higher detection accuracy and real-time performance to the RPW-controlled pest pre-detection system, which helps us to take timely preventive and control measures to avoid serious pest infestation. It also provides scalability for other pest pre-detection systems; with the corresponding dataset and training, the algorithm can be adapted to the detection tasks of other pests, which in turn brings a wider range of applications in the field of monitoring and control of agricultural pests. [ABSTRACT FROM AUTHOR]

Food security is a basic human right that guarantees humans an adequate amount of nutritious food. However, plant viruses and agricultural pests cause real damage to food sources, leading to negative impacts on meeting the human right of obtaining a sufficient amount of food. Understanding infectious disease dynamics can help us to design appropriate control and prevention strategies. Although cassava is among the most produced and consumed crops and greatly contributes to food security, cassava mosaic disease causes a decrease in photosynthesis and reduces cassava yield, resulting in a lack of crops. This paper developed a fractional model for cassava mosaic disease (CMD) dynamics based on the Caputo–Fabrizio (CF) fractional derivative to decrease cassava plant infection. We used fixed-point theory to study the existence of a unique solution in the form of the CMD model. A stability analysis of the model was conducted by using fixed-point theory and the Picard technique. A new numerical scheme was proposed for solving the nonlinear system of a fractional model in the sense of the CF-derivative and applied to obtain numerical simulations for a fractional model of the dynamics of CMD. The obtained results are described using figures that show the dynamics and behaviors of the compartments of CMD, and it is concluded that decreasing the population of whitefly vectors can prevent cassava plants from becoming infected better than increasing the recovery rate of the infected cassava plants. [ABSTRACT FROM AUTHOR]

Protecting crops from pests is a major issue in the current agricultural production system. The agricultural digital twin system, as an emerging product of modern agricultural development, can effectively achieve intelligent control of pest management systems. In response to the current problems of heavy use of pesticides in pest management and over-reliance on managers' personal experience with pepper plants, this paper proposes a digital twin system that monitors changes in aphid populations, enabling timely and effective pest control interventions. The digital twin system is developed for pest management driven by data and model fusion. First, a digital twin framework is presented to manage insect pests in the whole process of crop growth. Then, a digital twin model is established to predict the number of pests based on the random forest algorithm optimized by the genetic algorithm; a pest control intervention based on a twin data search strategy is designed and the decision optimization of pest management is conducted. Finally, a case study is carried out to verify the feasibility of the system for the growth state of pepper and pepper pests. The experimental results show that the virtual and real interactive feedback of the pepper aphid management system is achieved. It can obtain prediction accuracy of 88.01% with the training set and prediction accuracy of 85.73% with the test set. The application of the prediction model to the decision-making objective function can improve economic efficiency by more than 20%. In addition, the proposed approach is superior to the manual regulatory method in pest management. This system prioritizes detecting population trends over precise species identification, providing a practical tool for integrated pest management (IPM). [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]

Weeds are one of the most harmful agricultural pests that have a significant impact on crops. Weeds are responsible for higher production costs due to crop waste and have a significant impact on the global agricultural economy. The importance of this problem has promoted the research community in exploring the use of technology to support farmers in the early detection of weeds. Artificial intelligence (AI) driven image analysis for weed detection and, in particular, machine learning (ML) and deep learning (DL) using images from crop fields have been widely used in the literature for detecting various types of weeds that grow alongside crops. In this paper, we present a systematic literature review (SLR) on current state-of-the-art DL techniques for weed detection. Our SLR identified a rapid growth in research related to weed detection using DL since 2015 and filtered 52 application papers and 8 survey papers for further analysis. The pooled results from these papers yielded 34 unique weed types detection, 16 image processing techniques, and 11 DL algorithms with 19 different variants of CNNs. Moreover, we include a literature survey on popular vanilla ML techniques (e.g., SVM, random forest) that have been widely used prior to the dominance of DL. Our study presents a detailed thematic analysis of ML/DL algorithms used for detecting the weed/crop and provides a unique contribution to the analysis and assessment of the performance of these ML/DL techniques. Our study also details the use of crops associated with weeds, such as sugar beet, which was one of the most commonly used crops in most papers for detecting various types of weeds. It also discusses the modality where RGB was most frequently used. Crop images were frequently captured using robots, drones, and cell phones. It also discusses algorithm accuracy, such as how SVM outperformed all machine learning algorithms in many cases, with the highest accuracy of 99 percent, and how CNN with its variants also performed well with the highest accuracy of 99 percent, with only VGGNet providing the lowest accuracy of 84 percent. Finally, the study will serve as a starting point for researchers who wish to undertake further research in this area. [ABSTRACT FROM AUTHOR]

This paper describes a novel qualitative dataset regarding coffee pests based on the ancestral knowledge of coffee farmers in the Department of Cauca, Colombia. The dataset has been obtained from a survey applied to coffee growers with 432 records and 41 variables collected weekly from September 2020 to August 2021. The qualitative dataset includes climatic conditions, productive activities, external conditions, and coffee bio-aggressors. This dataset allows researchers to find patterns for coffee crop protection through the ancestral knowledge not detected by real-time agricultural sensors. As far as we are concerned, there are no datasets like the one presented in this paper with similar characteristics of qualitative value that express the empirical knowledge of coffee farmers used to detect triggers of causal behaviors of pests and diseases in coffee crops. Dataset:  https://doi.org/10.5281/zenodo.8275090. Dataset License: Licensed under Creative Commons Attribution 4.0 International (CC-BY-4.0). [ABSTRACT FROM AUTHOR]

Simple Summary: Reducing the use of pesticides that harm natural enemies of crop pests is important to pest management. Currently, there is limited information on how herbicides might affect natural enemies. We carried out an analysis of existing data to determine how herbicides affect natural enemies and which herbicides are the most harmful. Herbicides increased natural enemy mortality and reduced their longevity and efficacy as predators. Predatory mites and predatory true bugs were more susceptible to herbicides than other groups of natural enemies. Spiders and parasitoid wasps were the least susceptible. However, parasitoid wasps are often tested in their "protected" juvenile stages within their hosts, and the data may under-represent the sensitivity of adults. Some potential glyphosate replacement herbicides were more harmful than glyphosate. There was little or no data available for many herbicides and beneficial insects, indicating that much more research is needed on this topic. A critical component of integrated pest management is minimizing disruption of biological control by reducing the use of pesticides with significant non-target effects on natural enemies. Insecticide non-target effects testing for natural enemies has become increasingly common, but research examining the non-target effects of herbicides on natural enemies is scarce, and recommendations regarding herbicide selectivity are non-existent. We used meta-analysis to summarize laboratory bioassays testing non-target effects of herbicides on arthropod natural enemies and identify patterns in taxon susceptibility and active ingredient toxicity. Data were extracted from 78 papers representing 801 total observations. Herbicides increased natural enemy mortality and decreased longevity, reproduction, and predation. Mesostigmatan mites and hemipterans were the most sensitive to herbicides, and spiders, neuropterans, and hymenopterans were the least sensitive. Mortality was higher in juvenile predators versus parasitoids but did not differ between adults; parasitoid juveniles are likely better protected within the host. In terms of acute mortality, metribuzin, glufosinate, and oxyfluorfen were the most harmful herbicides. Only nicosulfuron, rimsulfuron, pendimethalin, phenmedipham, atrazine, and urea did not increase natural enemy mortality. The large effect size of glufosinate is particularly concerning, as it is the most likely replacement herbicide for glyphosate in many crops. Many active ingredients remain under-studied. Our analysis indicates that herbicides have a strong potential to disrupt biological control in cropping systems. [ABSTRACT FROM AUTHOR]

The use of Internet of Things (IoT) technology for real-time monitoring of agricultural pests is an unavoidable trend in the future of intelligent agriculture. This paper aims to address the difficulties in deploying models at the edge of the pest monitoring visual system and the low recognition accuracy. In order to achieve that, a lightweight GCSS-YOLOv5s algorithm is proposed. Firstly, we introduce the lightweight network GhostNet, use the Ghostconv module to replace the traditional convolution, and construct the C3Ghost module based on the CSP structure, drastically reducing the number of model parameters. Secondly, during the feature fusion process, we introduce the content-aware reassembly of features (CARAFE) lightweight up-sampling operator to enhance the feature integration capability of the pests by reducing the impact of redundant features after fusion. Then, we adopt SIoU as the bounding box regression loss function, which enhances the convergence speed and detection accuracy of the model. Finally, the traditional non-maximum suppression (NMS) was improved to Soft-NMS to improve the model's ability to recognize overlapping pests. According to the experimental results, the mean average precision (mAP) of the GCSS-YOLOv5s model reaches 90.5%. This is achieved with a 44% reduction in the number of parameters and a 7.4 G reduction in computation volume compared to the original model. The method significantly reduces the model's resource requirements while maintaining accuracy, which offers a specific theoretical foundation and technological reference for the future field of intelligent monitoring. [ABSTRACT FROM AUTHOR]

Simple Summary: Invasive alien species, such as Carpomya vesuviana Costa (Diptera: Tephritidae), threaten global biodiversity, agriculture, and public health. This study used advanced modelling techniques to predict the potential distribution of C. vesuviana and understand its environmental impacts. The findings suggest that climate change is driving the geographic expansion of C. vesuviana, primarily in Asia, Africa, and Australia. The species is projected to shift poleward by the 2090s, as the species will have shifted to the polar regions under the influence of climate change. Effective management strategies are crucial to mitigate the environmental and health impacts of its expansion. Invasive alien species (IAS) significantly affect global native biodiversity, agriculture, industry, and human health. Carpomya vesuviana Costa, 1854 (Diptera: Tephritidae), a significant global IAS, affects various date species, leading to substantial economic losses and adverse effects on human health and the environment. This study employed biomod2 ensemble models, multivariate environmental similarity surface and most dissimilar variable analyses, and ecological niche dynamics based on environmental and species data to predict the potential distribution of C. vesuviana and explore the environmental variables affecting observed patterns and impacts. Compared to native ranges, ecological niche shifts at invaded sites increased the invasion risk of C. vesuviana globally. The potential geographical distribution was primarily in Asia, Africa, and Australia, with a gradual increase in suitability with time and radiation levels. The potential geographic distribution centre of C. vesuviana is likely to shift poleward between the present and the 2090s. We also show that precipitation is a key factor influencing the likely future distribution of this species. In conclusion, climate change has facilitated the expansion of the geographic range and ecological niche of C. vesuviana, requiring effective transnational management strategies to mitigate its impacts on the natural environment and public health during the Anthropocene. This study aims to assess the potential threat of C. vesuviana to date palms globally through quantitative analytical methods. By modelling and analysing its potential geographic distribution, ecological niche, and environmental similarities, this paper predicts the pest's dispersal potential and possible transfer trends in geographic centres of mass in order to provide prevention and control strategies for the global date palm industry. [ABSTRACT FROM AUTHOR]

The invasion of agricultural diseases and insect pests is a huge difficulty for the growth of crops. The detection of diseases and pests is a very challenging task. The diversity of diseases and pests in terms of shapes, colors, and sizes, as well as changes in the lighting environment, have a massive impact on the accuracy of the detection results. We improved the C2F module based on DenseBlock and proposed DCF to extract low-level features such as the edge texture of pests and diseases. Through the sensitivity of low-level features to the diversity of pests and diseases, the DCF module can better cope with complex detection tasks and improve the accuracy and robustness of the detection. The complex background environment of pests and diseases and different lighting conditions make the IP102 data set have strong nonlinear characteristics. The Mish activation function is selected to replace the CBS module with the CBM, which can better learn the nonlinear characteristics of the data and effectively solve the problems of gradient disappearance in the algorithm training process. Experiments show that the advanced Yolov8 algorithm has improved. Comparing with Yolov8, our algorithm improves the MAP50 index, Precision index, and Recall index by 2%, 1.3%, and 3.7%. The model in this paper has higher accuracy and versatility. [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]

Simple Summary: The reduviid genus Sycanus Amyot & Serville, 1843, possesses higher aesthetic value and plays a crucial role as a natural enemy in the control of agricultural and forestry pests. However, Sycanus from China has not undergone a comprehensive review for over four decades. Based on both molecular data and morphological evidence, we conducted a systematic review of the 14 Chinese Sycanus species, including a description of three new species. Due to the variability of body coloration and morphological similarity among closely related species, unresolved issues and debates still persist in the taxonomic study of the genus Sycanus from China. In this study, we conducted phylogenetic analyses and species delimitation for Sycanus in China based on a COI DNA barcoding dataset comprising 81 samples. The results revealed that all the samples could be classified into 12 species by integrating molecular analyses with morphological comparison. This paper provides a comprehensive systematic review of the Sycanus species found in China, including descriptions of three new species: S. taiwanensis Zhao & Cai sp. nov., S. flavicorius Li & Cai sp. nov., and S. hainanensis Wang & Cai sp. nov. Furthermore, it is proposed that S. croceovittatus Dohrn, 1859, S. leucomesus Walker, 1873, and S. villicus Stål, 1863, are three synonyms of S. bifidus (Fabricius, 1787); S. bicolor Hsiao, 1979, is a synonym of S. versicolor Dohrn, 1859; and S. hsiaoi Maldonado-Capriles, 1990, is a synonym of S. marginellus Putshkov, 1987. Additionally, brief biological information is provided for two species, S. falleni Stål, 1863, and S. croceus Hsiao, 1979. [ABSTRACT FROM AUTHOR]

Simple Summary: Grasshopper and cricket (Orthoptera) mass occurrences represent an unusually large increase in populations of certain species. Grasshopper species known as locusts are well known to cause severe damage to many crops. The severity of each outbreak depends on the species and on a wide range of ecological factors, including temperature and rainfall regime. In Croatia, a small country in SE Europe, there has never been systematic research on these Orthoptera species, and this phenomenon is regarded as a rare event despite several huge outbreaks being reported in the past. For the first time, all known mass occurrences of grasshoppers, locusts, crickets, bush-crickets, and mole crickets (of the order Orthoptera) from Croatia are summarized. The study represents a historical overview of all Orthoptera mass occurrences known based on the literature but also provides many new records. It seems that Orthoptera mass occurrences are not rare in the country at all, especially in the Mediterranean part. The present situation suggests that thorough research into locusts as agricultural pests in Croatia should be conducted to determine the potential threat to the local economy and with special emphasis on the Adriatic region. The trends of climate change in the Mediterranean imply a rise in locust destructiveness risk in the near future and invites further research. During the last century, well-known locust species, such as Calliptamus italicus and Dociostaurus maroccanus, have produced outbreaks of varying degrees in the Balkans. The literature data on outbreaks in the region are scarce, and Croatia is not an exception. This study summarized the data on 23 Orthoptera mass occurrences in Croatia from 1900 to 2023 from 28 localities, representing 12 species. This is a low level of outbreak activity compared with other locust and pest grasshopper species in other parts of the world. The species with the most reporting is C. italicus with altogether six mass occurrences, while second is Barbitistes ocskayi and Miramella irena with three records, and in the third, place D. maroccanus and Gryllotalpa sp., each with two mass occurrences having been reported. One of the most notable swarms is that of Anacridium aegyptium which occurred around Šibenik in 1998, and this paper provides the first account of it, 25 years after it took place. The most recent outbreaks took place in 2022, and the most notable one was that of D. maroccanus swarm in Štikovo. The 2022 and 2023 reports were brief and muted, despite the affected agriculturists claiming significant damages. [ABSTRACT FROM AUTHOR]

The damage caused by pests to crops results in reduced crop yield and compromised quality. Accurate and timely pest detection plays a crucial role in helping farmers to defend against and control pests. In this paper, a novel crop pest detection model named YOLOv5s-pest is proposed. Firstly, we design a hybrid spatial pyramid pooling fast (HSPPF) module, which enhances the model's capability to capture multi-scale receptive field information. Secondly, we design a new convolutional block attention module (NCBAM) that highlights key features, suppresses redundant features, and improves detection precision. Thirdly, the recursive gated convolution ( g 3 C o n v ) is introduced into the neck, which extends the potential of self-attention mechanism to explore feature representation to arbitrary-order space, enhances model capacity and detection capability. Finally, we replace the non-maximum suppression (NMS) in the post-processing part with Soft-NMS, which improves the missed problem of detection in crowded and dense scenes. The experimental results show that the mAP@0.5 (mean average precision at intersection over union (IoU) threshold of 0.5) of YOLOv5s-pest achieves 92.5% and the mAP@0.5:0.95 (mean average precision from IoU 0.5 to 0.95) achieves 72.6% on the IP16. Furthermore, we also validate our proposed method on other datasets, and the outcomes indicate that YOLOv5s-pest is also effective in other detection tasks. [ABSTRACT FROM AUTHOR]

Timely and effective pest detection is essential for agricultural production, facing challenges such as complex backgrounds and a vast number of parameters. Seeking solutions has become a pressing matter. This paper, based on the YOLOv5 algorithm, developed the PestLite model. The model surpasses previous spatial pooling methods with our uniquely designed Multi-Level Spatial Pyramid Pooling (MTSPPF). Using a lightweight unit, it integrates convolution, normalization, and activation operations. It excels in capturing multi-scale features, ensuring rich extraction of key information at various scales. Notably, MTSPPF not only enhances detection accuracy but also reduces the parameter size, making it ideal for lightweight pest detection models. Additionally, we introduced the Involution and Efficient Channel Attention (ECA) attention mechanisms to enhance contextual understanding. We also replaced traditional upsampling with Content-Aware ReAssembly of FEatures (CARAFE), which enable the model to achieve higher mean average precision in detection. Testing on a pest dataset showed improved accuracy while reducing parameter size. The mAP50 increased from 87.9% to 90.7%, and the parameter count decreased from 7.03 M to 6.09 M. We further validated the PestLite model using the IP102 dataset, and on the other hand, we conducted comparisons with mainstream models. Furthermore, we visualized the detection targets. The results indicate that the PestLite model provides an effective solution for real-time target detection in agricultural pests. [ABSTRACT FROM AUTHOR]

Flying insect detection, identification, and counting are the key components of agricultural pest management. Insect identification is also one of the most challenging tasks in agricultural image processing. With the aid of machine vision and machine learning, traditional (manual) identification and counting can be automated. To achieve this goal, a particular data acquisition device and an accurate insect recognition algorithm (model) is necessary. In this work, we propose a new embedded system-based insect trap with an OpenMV Cam H7 microcontroller board, which can be used anywhere in the field without any restrictions (AC power supply, WIFI coverage, human interaction, etc.). In addition, we also propose a deep learning-based insect-counting method where we offer solutions for problems such as the "lack of data" and "false insect detection". By means of the proposed trap and insect-counting method, spraying (pest swarming) could then be accurately scheduled. [ABSTRACT FROM AUTHOR]

Simple Summary: Various types of rice pests cause huge losses to rice production every year in China. In this paper, a deep neural network for pest detection and classification via digital images is proposed. The targeted optimization is improved for the pest characteristics. Our experiments determined that our model has a higher accuracy and detection speed compared with other methods. In addition, it can be more widely used in pest detection surveys for various crops. In recent years, the occurrence of rice pests has been increasing, which has greatly affected the yield of rice in many parts of the world. The prevention and cure of rice pests is urgent. Aiming at the problems of the small appearance difference and large size change of various pests, a deep neural network named YOLO-GBS is proposed in this paper for detecting and classifying pests from digital images. Based on YOLOv5s, one more detection head is added to expand the detection scale range, the global context (GC) attention mechanism is integrated to find targets in complex backgrounds, PANet is replaced by BiFPN network to improve the feature fusion effect, and Swin Transformer is introduced to take full advantage of the self-attention mechanism of global contextual information. Results from experiments on our insect dataset containing Crambidae, Noctuidae, Ephydridae, and Delphacidae showed that the average mAP of the proposed model is up to 79.8%, which is 5.4% higher than that of YOLOv5s, and the detection effect of various complex scenes is significantly improved. In addition, the paper analyzes and discusses the generalization ability of YOLO-GBS model on a larger-scale pest data set. This research provides a more accurate and efficient intelligent detection method for rice pests and others crop pests. [ABSTRACT FROM AUTHOR]

Simple Summary: Over the past two decades, researchers around the world have conducted studies to identify volatile compounds that serve as attractants for one of the most important agricultural pests, the western flower thrips (WFT). In this review, the preferred reporting items for systematic reviews and meta-analyses (PRISMA) guidelines were used to find published studies and to extract the information generated worldwide to determine the overall attraction of the reported compounds using a meta-analysis approach. This systematic review shows that the most-used compounds worldwide are those based on pyridines, which show a high attraction ratio. Methyl isonicotinate is the most studied of these compounds. Data from the meta-analysis accurately estimated the potential attraction of other novel compounds that could be used for integrated pest management strategies, such as monitoring WFT populations or mass trapping. A call for new research evaluating and developing new products with these novel compounds is made. The study of the semiochemicals of the western flower thrips (WFT), Frankliniella occidentalis, Pergande (Thysanoptera: Thripidae), is a relevant topic that spans the last two decades. Approximately a hundred articles published on this subject from 2000 to 2022 can be found in academic databases, representing approximately 5% of the research on this important pest. These topics have generated a platform for novel research with a high potential for development. However, to move on to a new research step, an effectiveness evaluation of the compounds discovered so far is necessary. This review conducted a systematic analysis of the research focused on the semiochemicals (kairomones, pheromones, and attractants) for this pest. Papers from the past three decades on WFT attraction to semiochemicals were collected from databases using the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) guidelines. The number of individuals attracted to compounds was extracted from the papers and compiled for analysis. With this information, an attraction ratio was calculated. Forty-one possible attractants were found in the literature, with methyl isonicotinate being the most-studied compound so far, with the third-highest attraction ratio. δ-Decalactone was the compound with the highest attraction ratio, but it was one of the least studied. A meta-analysis of the WFT choosing proportion was performed for the compounds with more trials found in the literature. The predicted mean choice percentages for methyl isonicotinate (MIN) and Lurem-TR, the MIN's commercial product, were 76.6% and 66.6%, respectively. There was a convergence among the analyzed studies showing a high degree of research focus on the same group of nitrogen-containing compounds (mainly the pyridine structure). These findings call for future research to diversify the discovery and evaluation of attractive compounds in this relevant study area. [ABSTRACT FROM AUTHOR]

This paper proposes a novel model for named entity recognition of Chinese crop diseases and pests. The model is intended to solve the problems of uneven entity distribution, incomplete recognition of complex terms, and unclear entity boundaries. First, a robustly optimized BERT pre-training approach-whole word masking (RoBERTa-wwm) model is used to extract diseases and pests' text semantics, acquiring dynamic word vectors to solve the problem of incomplete word recognition. Adversarial training is then introduced to address unclear boundaries of diseases and pest entities and to improve the generalization ability of models in an effective manner. The context features are obtained by the bi-directional gated recurrent unit (BiGRU) neural network. Finally, the optimal tag sequence is obtained by conditional random fields (CRF) decoding. A focal loss function is introduced to optimize conditional random fields (CRF) and thus solve the problem of unbalanced label classification in the sequence. The experimental results show that the model's precision, recall, and F1 values on the crop diseases and pests corpus reached 89.23%, 90.90%, and 90.04%, respectively, demonstrating effectiveness at improving the accuracy of named entity recognition for Chinese crop diseases and pests. The named entity recognition model proposed in this study can provide a high-quality technical basis for downstream tasks such as crop diseases and pests knowledge graphs and question-answering systems. [ABSTRACT FROM AUTHOR]

Following the rapid development of information and communication technology, and the huge amounts of data that have undergone explosive growth, artificial intelligence and machine learning have been used for predictive analysis in many fields. However, the prediction accuracy of these machine learning recognition models depends on the quality of the features selected for training. It is therefore very important to analyse characteristics that are meaningful and in line with the target variables as the training conditions for machine learning recognition models. In this paper, we analyse the correlation between features and target variables using the Pearson product-moment correlation coefficient, and integrate transfer learning technology for sequential feature extraction to enhance the prediction accuracy of a machine learning recognition model for the prediction of multiple crop pests and diseases as the performance verification target of the proposed method. The performance of our machine learning recognition model is compared with schemes in related work, and our approach is shown to increase the prediction accuracy by between 3% and 15%. [ABSTRACT FROM AUTHOR]

With the rapid development of precision agriculture technology worldwide, plant protection unmanned aerial vehicles (UAVs) have been widely applied in the prevention and control of agricultural pests and diseases due to their advantages such as unrestricted terrain, strong maneuverability, hover capability, and high operational efficiency. In view of the fact that most of the current path planning methods for plant protection UAVs are mainly applicable to large fields with relatively flat terrain, and there is a lack of three-dimensional path planning methods applicable to hilly orchards, as well as a lack of intuitive evaluation of the advantages and disadvantages of the paths by utilizing the amount of energy consumption, this paper proposes a three-dimensional (3D) path planning method for plant protection UAVs in hilly orchards. The method utilizes the three-dimensional (3D) coordinates of the operational area obtained from a realistic 3D model of the area, and determines the 3D operational path through the use of Boustrophedon Cellular Decomposition and the height variations of the operational area. Based on the induced power used by the plant protection UAV for flight and the power needed to overcome wind resistance, combined with the change of the load of the plant protection UAV and the supply situation, the relative energy consumption model of the plant protection UAV is constructed. Then, by optimizing the operational heading angle (1–180°), the 3D path with the minimum relative energy consumption is obtained. Through a simulation test, it is demonstrated that the path with the minimum relative energy consumption (operational heading angle of 133°) reduces the average relative energy consumption by 62.44% and 47.21% compared to the path with the maximum relative energy consumption (operational heading angle of 51°) and the average relative energy consumption, respectively. This proves the feasibility of the proposed path planning method in hilly orchard environments and provides a reference for the application of plant protection UAVs in such orchards. [ABSTRACT FROM AUTHOR]

Mycopesticides are living preparations that use fungal cells, such as spores and hyphae, as active ingredients. They mainly include mycoinsecticides, mycofungicides, mycoherbicides and nematophagous fungi. The utilization of fungi for controlling agricultural pests can be traced back to approximately 1880, when entomopathogenic fungi were initially employed for this purpose. However, it was not until 1965 that the world's first mycopesticide, Beauveria bassiana, was registered as Boverin® in the former Soviet Union. In past decades, numerous novel mycopesticides have been developed for their lower R&D costs, as well as the environmentally friendly and safe nature. In this review, we investigated the mycopesticides situation of registration in USA, EU, China, Canada and Australia. Superisingly, it was found that the registered mycopesticides are extremely raised in recent years. Currently, the insecticides, fungicides (nematocides) and herbicides were respectively registered 27, 53 and 8 fungal strains. This paper also analyzes the main problems currently faced by mycopesticides and offers suggestions for their future development. [ABSTRACT FROM AUTHOR]

Timely detection of pests and diseases in crops is essential to mitigate severe damage and economic losses, especially in the context of climate change. This paper describes a method for detecting the presence of coffee leaf rust (CLR) using two databases: RoCoLe and a database obtained from an unmanned aerial vehicle (UAV) equipped with an RGB camera. The developed method follows a two-stage approach. In the first stage, images are processed using ImageJ software, while, in the second phase, Python is used to implement morphological filters and the Hough transform for rust identification. The algorithm's performance is evaluated using the chi-square test, and its discriminatory capacity is assessed through the generation of a Receiver Operating Characteristic (ROC) curve. Additionally, Cohen's kappa method is used to assess the agreement among observers, while Kendall's rank correlation coefficient (KRCC) measures the correlation between the criteria of the observers and the classifications generated by the method. The results demonstrate that the developed method achieved an efficiency of 97% in detecting coffee rust in the RoCoLe dataset and over 93.5% in UAV images. These findings suggest that the developed method has the potential to be implemented in the future on a UAV for rust detection. [ABSTRACT FROM AUTHOR]

Fruit flies (Diptera: Tephritidae) are serious pests that affect fruit production and marketing. Both third instar larvae and pupae are biological stages that persist in the soil until adult emergence. Entomopathogenic nematodes (ENs) are biological control agents that are used to control agricultural pests in greenhouse or field conditions. Several studies have been carried out under laboratory and field conditions showing how ENs can be applied within an area-wide integrated pest management approach to control fruit fly species in orchards and backyard fruit trees. In this review, we analyze how soil physical characteristics and biotic factors affect the performance of these biological control agents. Of the reviewed papers, more than half evaluated the influence of soil texture, humidity, temperature, and other factors on the performance of infective juveniles (IJs). Abiotic factors that significantly influence the performance of IJs are temperature, humidity, and texture. Among the biotic factors that affect IJs are fungi, bacteria, mites, insects, and earthworms. We conclude that ENs have the potential to be applied in the drip area of fruit trees that are infested by fruit flies and contribute to their suppression. This approach, in conjunction with an area-wide pest management approach, may contribute to pest suppression and increase the sustainability of agroecosystems. [ABSTRACT FROM AUTHOR]

Agriculture is regarded as one of the key food sources for humans throughout history. In some countries, more than 90% of the population lives on agriculture. However, pests are regarded as one of the major causes of crop loss worldwide. Accurate and automated technology to classify pests can help pest detection with great significance for early preventive measures. This paper proposes the solution of a residual convolutional neural network for pest identification based on transfer learning. The IP102 agricultural pest image dataset was adopted as the experimental dataset to achieve data augmentation through random cropping, color transformation, CutMix and other operations. The processing technology can bring strong robustness to the affecting factors such as shooting angles, light and color changes. The experiment in this study compared the ResNeXt-50 (32 × 4d) model in terms of classification accuracy with different combinations of learning rate, transfer learning and data augmentation. In addition, the experiment compared the effects of data enhancement on the classification performance of different samples. The results show that the model classification effect based on transfer learning is generally superior to that based on new learning. Compared with new learning, transfer learning can greatly improve the model recognition ability and significantly reduce the training time to achieve the same classification accuracy. It is also very important to choose the appropriate data augmentation technology to improve classification accuracy. The accuracy rate of classification can reach 86.95% based on the combination of transfer learning + fine-tuning and CutMix. Compared to the original model, the accuracy of classification of some smaller samples was significantly improved. Compared with the relevant studies based on the same dataset, the method in this paper can achieve higher classification accuracy for more effective application in the field of pest classification. [ABSTRACT FROM AUTHOR]

Spraying systems to protect crops against pests are still necessary to maintain food production at the rates demanded by the current population. However, today, it is crucial to use precision agriculture to reduce the negative effects of pesticides and other agrochemicals such as fungicides. In particular, pressure fluctuations related to transient states when using pulse-width-modulated nozzles (PMW) have been reported to decrease the accuracy of preset flow rates in air-assisted orchard sprayers. The objective of this paper is to analyze the vibrations induced in the spraying system of a vineyard blast sprayer controlled by pulse-width-modulated nozzles, considering the instantaneous duty cycle (DC) as the control variable. An air-assisted vineyard sprayer was modified to host 24 solenoid shutoff valves with hollow disc–cone nozzles. A triaxial accelerometer was mounted to track the effect of duty cycle (20%, 30%, 50%, and 70%). In addition to accelerations, high-speed images were recorded, and the pressure according to time and the flow were estimated. The hydraulic system of the sprayer, when controlled in real time by the PWM solenoids, created pulsating impacts at the nozzle level with the same frequency of 10 Hz of the PMW system. The impact effect was significantly higher for low duty cycles under 40% DC. In addition, to demonstrate the inaccuracy of opening and closing the valves at a precisely specified time, this study also confirmed the divergence between the theoretical duty cycles commanded by the sprayer's control unit and the actual ones measured in real time. The results of the analysis showed the difficulty of opening and closing the valves with precision to obtain accurate duty cycles in the practical implementation of smart sprayers and the importance of understanding the vibration effects of pulses in arrangements of multiple PWM nozzles working simultaneously. [ABSTRACT FROM AUTHOR]

Pest birds are a salient problem in agriculture all around the world due to the damage they can cause to commercial or high-value crops. Recent advancements in Unmanned Aerial Vehicles (UAVs) have motivated the use of drones in pest bird deterrence, with promising success already being demonstrated over traditional bird control techniques. This paper presents a novel bird deterrence solution in the form of tethered UAVs, which are attached and arranged in a grid-like fashion across a vineyard property. This strategy aims to bypass the power and endurance limitations of untethered drones while still utilising their dynamism and scaring potential. A simulation model has been designed and developed to assess the feasibility of different UAV arrangements, configurations, and strategies against expected behavioural responses of incoming bird flocks, despite operational and spatial constraints imposed by a tether. Attempts at quantifying bird persistence and relative effort following UAV-induced deterrence are also introduced through a novel bird energy expenditure model. This aims to serve as a proxy for selecting control techniques that reduce future foraging missions. The simulation model successfully isolated candidate configurations, which were able to deter both single and multiple incoming bird flocks using a centralised multi-UAV control strategy. Overall, this study indicates that a grid of autonomous ground-tethered UAV platforms is viable as a bird deterrence solution in agriculture, a novel solution not seen nor dealt with elsewhere to the authors' knowledge. [ABSTRACT FROM AUTHOR]

Simple Summary: Bt (Cry1Ac) cotton has been commercialized in China since 1997. Two tactics have mainly been used in targeted pest resistance management for small farmers. The first is the use of natural refuges composed of corn, soybeans, vegetables, peanuts, and other crops to delay the development of the resistance of multi-host crop pests such as the cotton bollworm (Helicoverpa armigera) to Bt cotton. The second is to use the offspring of F2 generation hybrids (Bt and non-Bt cotton hybrids) to produce a 25% seed mix refuge formed by non-Bt cotton, further delaying the evolution of resistance of single cotton-eating target pests such as the pink bollworm (Pectinophora gossypiella). The 25-year production practice has demonstrated that this dual strategy of Bt cotton resistance management in China has been very successful to date, with no failures observed in lepidopteran pest control in the production process. China is one of the major cotton producers globally with small farmers. Lepidopteran pests have always been the main factor affecting cotton production. To reduce the occurrence of and damage caused by lepidopteran pests, China has employed a pest control method focused on planting Bt (Cry1Ac) cotton since 1997. Chinese resistance management tactics for the main target pests, the cotton bollworm and pink bollworm, were also implemented. For polyphagous (multiple hosts) and migratory pests such as the cotton bollworm (Helicoverpa armigera), the "natural refuge" strategy, consisting of non-Bt crops such as corn, soybean, vegetables, peanuts, and other host crops, was adopted in the Yellow River Region (YRR) and Northwest Region (NR). For a single host and weak migration ability pest, such as the pink bollworm (Pectinophora gossypiella), the seed mix refuge strategy yields a random mixture within fields of 25% non-Bt cotton by sowing second-generation (F2) seeds. According to field monitoring results for more than 20 years in China, practical resistance (Bt cotton failure) of target pests was avoided, and there were no cases of Bt (Cry1Ac) failure of pest control in cotton production. This indicated that this Chinese resistance management strategy was very successful. The Chinese government has decided to commercialize Bt corn, which will inevitably reduce the role of natural refuges; therefore, this paper also discusses adjustments and future directions of cotton pest resistance management strategies. [ABSTRACT FROM AUTHOR]

Lavender is in the research spotlight due to its increasing economic importance, while market demand is expected to continue to grow. Among the hundreds of essential-oil-bearing plants, Lavandula angustifolia Mill. remains one of the most valuable. This paper explores the lavender chain timeline from crop to products, examining the expanding knowledge on the characteristics, phytochemical profile and functional potential of lavender that could lead to new products and uses. Lavender crops can be expanded without competing for productive land, instead using marginal, contaminated or unproductive land. A novel cultivation trend proposes leveraging agri-background biodiversity, arbuscular mycorrhiza and the natural enemies of pests for healthy crops. Together with breeding efforts targeting highly performant genotypes with complex volatile profiles coupled with resistance to specific biotic (particularly Phytoplasma) and abiotic (salt, heavy metals) stressors, industry could have a steady supply of high-quality raw material. Besides the expansion of the uses of essential oil in cosmetics, pharmaceuticals, food and environmental and agri-applications, novel channels have appeared for the use of the solid by-product, which is rich in polyphenols and polysaccharides; these channels have the potential to create additional streams of value. The stabilization and optimization of techno-functional delivery systems through the encapsulation of essential oil can extend shelf-life and enhance biological activity efficiency. [ABSTRACT FROM AUTHOR]

Insect pests and crop diseases are considered the major problems for agricultural production, due to the severity and extent of their occurrence causing significant crop losses. To increase agricultural production, it is significant to protect the crop from harmful pests which is possible via soft computing techniques. The soft computing techniques are based on traditional machine and deep learning-based approaches. However, in the traditional methods, the selection of manual feature extraction mechanisms is ineffective, inefficient, and time-consuming, while deep learning techniques are computationally expensive and require a large amount of training data. In this paper, we propose an efficient pest detection method that accurately localized the pests and classify them according to their desired class label. In the proposed work, we modify the YOLOv5s model in several ways such as extending the cross stage partial network (CSP) module, improving the select kernel (SK) in the attention module, and modifying the multiscale feature extraction mechanism, which plays a significant role in the detection and classification of small and large sizes of pest in an image. To validate the model performance, we develop a medium-scale pest detection dataset that includes the five most harmful pests for agriculture products that are ants, grasshopper, palm weevils, shield bugs, and wasps. To check the model's effectiveness, we compare the results of the proposed model with several variations of the YOLOv5 model, where the proposed model achieved the best results in the experiments. Thus, the proposed model has the potential to be applied in real-world applications and further motivate research on pest detection to increase agriculture production. [ABSTRACT FROM AUTHOR]

Camouflaged target segmentation has been widely used in both civil and military applications, such as wildlife behaviour monitoring, crop pest control, and battle reconnaissance. However, it is difficult to distinguish camouflaged objects and natural backgrounds using traditional grey-level feature extraction. In this paper, a compressive bidirectional reflection distribution function-based feature extraction method is proposed for effective camouflaged object segmentation. First, multidimensional grey-level features are extracted from multiple images with different illumination angles in the same scene. Then, the multidimensional grey-level features are expanded based on Chebyshev polynomials. Next, the first several coefficients are integrated as a new optical feature, which is named the compressive bidirectional reflection distribution function feature. Finally, the camouflaged object can be effectively segmented from the background by compressive feature clustering. Both qualitative and quantitative experimental results prove that our method has remarkable advantages over conventional single-angle or multi-angle grey-level feature-based methods in terms of segmentation precision and running speed. [ABSTRACT FROM AUTHOR]

Because our civilization has relied on pesticides to fight weeds, insects, and diseases since antiquity, the use of these chemicals has become natural and exclusive. Unfortunately, the use of pesticides has progressively had alarming effects on water quality, biodiversity, and human health. This paper proposes to improve farming practices by replacing pesticides with a laser-based robotic approach. This study focused on the neutralization of aphids, as they are among the most harmful pests for crops and complex to control. With the help of deep learning, we developed a mobile robot that spans crop rows, locates aphids, and neutralizes them with laser beams. We have built a prototype with the sole purpose of validating the localization-neutralization loop on a single seedling row. The experiments performed in our laboratory demonstrate the feasibility of detecting different lines of aphids (50% detected at 3 cm/s) and of neutralizing them (90% mortality) without impacting the growth of their host plants. The results are encouraging since aphids are one of the most challenging crop pests to eradicate. However, enhancements in detection and mainly in targeting are necessary to be useful in a real farming context. Moreover, robustness regarding field conditions should be evaluated. [ABSTRACT FROM AUTHOR]

The Moroccan locust has been considered one of the most dangerous agricultural pests in the Mediterranean region. The economic importance of its outbreaks diminished during the second half of the 20th century due to a high degree of agricultural industrialization and other human-caused transformations of its habitat. Nevertheless, in Sardinia (Italy) from 2019 on, a growing invasion of this locust species is ongoing, being the worst in over three decades. Locust swarms destroyed crops and pasture lands of approximately 60,000 ha in 2022. Drought, in combination with increasing uncultivated land, contributed to forming the perfect conditions for a Moroccan locust population upsurge. The specific aim of this paper is the quantification of land cover land use (LCLU) influence with regard to the recent locust outbreak in Sardinia using remote sensing data. In particular, the role of untilled, fallow, or abandoned land in the locust population upsurge is the focus of this case study. To address this objective, LCLU was derived from Sentinel-2A/B Multispectral Instrument (MSI) data between 2017 and 2021 using time-series composites and a random forest (RF) classification model. Coordinates of infested locations, altitude, and locust development stages were collected during field observation campaigns between March and July 2022 and used in this study to assess actual and previous land cover situation of these locations. Findings show that 43% of detected locust locations were found on untilled, fallow, or uncultivated land and another 23% within a radius of 100 m to such areas. Furthermore, oviposition and breeding sites are mostly found in sparse vegetation (97%). This study demonstrates that up-to-date remote sensing data and target-oriented analyses can provide valuable information to contribute to early warning systems and decision support and thus to minimize the risk concerning this agricultural pest. This is of particular interest for all agricultural pests that are strictly related to changing human activities within transformed habitats. [ABSTRACT FROM AUTHOR]

The harm of agricultural pests presents a remarkable effect on the quality and safety of edible farm products and the monitoring and identification of agricultural pests based on the Internet of Things (IoT) produce a large amount of data to be transmitted. To achieve efficient and real-time transmission of the sensors' data for pest monitoring, this paper selects 235 geographic coordinates of agricultural pest monitoring points and uses genetic algorithm (GA), particle swarm optimization (PSO), and simulated annealing (SA) to optimize the data transmission paths of sensors. The three intelligent algorithms are simulated by MATLAB software. The results show that the optimized path based on PSO can make the shortest time used for transmitting data, and its corresponding minimum time is 4.868012 s. This study can provide a reference for improving the transmission efficiency of agricultural pest monitoring data, provide a guarantee for developing real-time and effective pest control strategies, and further reduce the threat of pest damage to the safety of farm products. [ABSTRACT FROM AUTHOR]

Entomological radar is a specially designed instrument that can measure the behavioral and biological characteristics of high-altitude migrating insects. Its application is of great significance for the monitoring, early warning, and control of agricultural pests. As an important component of the local migratory biomass, insects fly in the air during the day and night. The fully polarimetric entomological radar was carefully designed with all-day, all-weather, and multi-function measurement capabilities. The fully polarimetric entomological radar measures the mass of a single insect based on the radar cross-sectional (RCS) measurement and then calculates the biomass of migrating insects. Therefore, the measurement accuracy of the insect RCS is the key indicator affecting the accuracy of migratory biomass statistics. Due to the radar's lack of in-beam angle measurement ability, the insect RCS is usually measured based on the assumption that the insect is on the beam center. Therefore, the measured RCS will be smaller than true value if the insect deviates from the beam center due to the gain curve of the antenna. This leads to measurement errors in regard to the insect mass and migratory biomass. In order to solve this problem, a biomass estimation method, reported in this paper, was designed under the assumption of a uniform distribution of migrating insects in the radar monitoring airspace. This method can estimate the individual RCS expectation of migrating insects through a statistical method without measuring the position of the insects in the beam and then obtain the migratory biomass. The effectiveness of the model and algorithm is verified by simulations and entomological radar field measurements. [ABSTRACT FROM AUTHOR]

Considering the population growth rate of recent years, a doubling of the current worldwide crop productivity is expected to be needed by 2050. Pests and diseases are a major obstacle to achieving this productivity outcome. Therefore, it is very important to develop efficient methods for the automatic detection, identification, and prediction of pests and diseases in agricultural crops. To perform such automation, Machine Learning (ML) techniques can be used to derive knowledge and relationships from the data that is being worked on. This paper presents a literature review on ML techniques used in the agricultural sector, focusing on the tasks of classification, detection, and prediction of diseases and pests, with an emphasis on tomato crops. This survey aims to contribute to the development of smart farming and precision agriculture by promoting the development of techniques that will allow farmers to decrease the use of pesticides and chemicals while preserving and improving their crop quality and production. [ABSTRACT FROM AUTHOR]

The integrated management of a serious agricultural pest, the common vole (Microtus arvalis), should be based on modern and empirically proven approaches. The aim of this paper was to map the historical development of the monitoring and control practices of the common vole in the Czech Republic (CR) territory. Published records of vole population outbreaks and heavy crop damage have been documented in the Czech literature since the turn of the 20th century, and even in crops planted in highly fragmented and diversified agricultural landscapes. In the CR, systematic state monitoring was introduced in 1955. In the 1930's, there were more than 100 various rodent preparations against the common vole, which were formulated as smoke generators, gases, baits, dusts, toxic mushy mass, and insecticide sprays. Currently, there are only six preparations with three active ingredients registered in the CR. Zinc phosphide is the only active ingredient that has been used from the 1940s to the present, whereas anticoagulants were banned for vole control in 2011 owing to the high environmental risks. The poisoning of nontarget animals by rodenticides is not a new phenomenon tied to synthetic pesticides; poisoning by botanical extracts (strychnine) was documented more than 100 years ago. This review may provide both historical lessons for current practice and new incentives for future research. [ABSTRACT FROM AUTHOR]

Simple Summary: The green peach aphid (Myzus persicae (Sulzer)) is considered one of the main pests of economically valuable crops. In the last decades, it has developed resistance to several chemical pesticides. More effective and environmentally friendly solutions for green peach aphid management, including plant essential oils, are being tested as alternatives to chemical pesticides. Repellents have gained interest because lower doses can be used against agricultural pests, with a reduced risk of developing insect resistance. In this study, three different types of caraway (Carum carvi L.) seed essential oils against green peach aphids were tested. Repellent activity testing was carried out using a bridge method and host plants of white cabbage. The aphids were placed on the bridge, and their choice was recorded depending on whether they went to the treatment side (containing the selected essential oil) or the control side (no essential oil). All the selected caraway essential oils showed that they repel aphids to various degrees. The optimal essential oil dose was determined in the same way. In addition, the essential oil was mixed with different surfactants to create a formulation basis for ready-to-use products, but the testing showed decreased repellent activity of such mixtures. An in vivo dual choice bioassay with white cabbage as a host plant was used to determine the repellent effect of three different accessions of caraway (Carum carvi L.) essential oils (EOs) against the green peach aphid Myzus persicae (Sulzer). The dominant components of the EO were D-Carvone (47.3–74.4%) and D-limonene (25.2–51.9%), which accounted for 99.2–99.5% of the EOs determined by GC/MS. The EO with the highest D-limonene content (51.9%) showed the highest repellence (Repellency Index (RI) = +41%), which was stable up to 330 min. The incorporation of several surfactants with different hydrophilic-lipophilic balance values (from 12.4 to 16.7) with caraway EO caused a general inhibition of the repellent effect during the testing period (RI from +41% to −19%). Overall, the findings indicate that caraway EO could be used as a green peach aphid repellent, but more work is needed to formulate the EO into a ready-to-use product. [ABSTRACT FROM AUTHOR]

In the realm of smart agriculture technology's rapid advancement, the integration of various sensors and Internet of Things (IoT) devices has become prevalent in the agricultural sector. Within this context, the precise identification of pests and diseases using unmanned robotic systems assumes a crucial role in ensuring food security, advancing agricultural production, and maintaining food reserves. Nevertheless, existing recognition models encounter inherent limitations such as suboptimal accuracy and excessive computational efforts when dealing with similar pests and diseases in real agricultural scenarios. Consequently, this research introduces the lightweight cross-layer aggregation neural network (LCA-Net). To address the intricate challenge of fine-grained pest identification in agricultural environments, our approach initially enhances the high-performance large-scale network through lightweight adaptation, concurrently incorporating a channel space attention mechanism. This enhancement culminates in the development of a cross-layer feature aggregation (CFA) module, meticulously engineered for seamless mobile deployment while upholding performance integrity. Furthermore, we devised the Cut-Max module, which optimizes the accuracy of crop pest and disease recognition via maximum response region pruning. Thorough experimentation on comprehensive pests and disease datasets substantiated the exceptional fine-grained performance of LCA-Net, achieving an impressive accuracy rate of 83.8%. Additional ablation experiments validated the proposed approach, showcasing a harmonious balance between performance and model parameters, rendering it suitable for practical applications in smart agricultural supervision. [ABSTRACT FROM AUTHOR]

Simple Summary: Monitoring pests is a labor-intensive and time-consuming task for agricultural experts. This paper proposes a new approach to classifying and counting different categories of crop pests. Specifically, we propose a multi-category pest detection network (MCPD-net), which includes a multiscale feature pyramid network and a novel adaptive feature region proposal network. The multiscale feature pyramid network is used to fuse the multiscale pest information, which significantly improves detection accuracy. The adaptive feature region proposal network addresses the problem of not aligning when region proposal network (RPN) iterating, especially for small pest objects. Extensive experiments on the multi-category pests dataset 2021 (MPD2021) demonstrated that the proposed method provides significant improvements in terms of average precision (AP) and average recall (AR); it outperformed other deep learning-based models. Specialized pest control for agriculture is a high-priority agricultural issue. There are multiple categories of tiny pests, which pose significant challenges to monitoring. Previous work mainly relied on manual monitoring of pests, which was labor-intensive and time-consuming. Recently, deep-learning-based pest detection methods have achieved remarkable improvements and can be used for automatic pest monitoring. However, there are two main obstacles in the task of pest detection. (1) Small pests often go undetected because much information is lost during the network training process. (2) The highly similar physical appearances of some categories of pests make it difficult to distinguish the specific categories for networks. To alleviate the above problems, we proposed the multi-category pest detection network (MCPD-net), which includes a multiscale feature pyramid network (MFPN) and a novel adaptive feature region proposal network (AFRPN). MFPN can fuse the pest information in multiscale features, which significantly improves detection accuracy. AFRPN solves the problem of anchor and feature misalignment during RPN iterating, especially for small pest objects. In extensive experiments on the multi-category pests dataset 2021 (MPD2021), the proposed method achieved 67.3% mean average precision (mAP) and 89.3% average recall (AR), outperforming other deep learning-based models. [ABSTRACT FROM AUTHOR]

Facing the need of modern agriculture to accurately grasp the information of farmland diseases and pests, this paper proposes an intelligent plant protection system. The system is composed of a wireless lens, temperature and humidity sensor, intelligent information terminal, and probe rod to realize the collection of plant images and meteorological information. At the same time, a software based on the mobile terminal and the computer terminal was developed. The plant images and meteorological data are transmitted to the server through Wi-Fi transmission. Combined with the expert knowledge model, a solution is generated, and the user can identify the current diseases and pests and obtain solutions at any time. The system can remotely and automatically monitor and warn of mainstream diseases and pests of field crops such as rice and wheat and provide support for fine plant protection management. [ABSTRACT FROM AUTHOR]

The detection and accurate positioning of agricultural pests and diseases can significantly improve the effectiveness of disease and pest control and reduce the cost of prevention and control, which has become an urgent need for crop production. Aiming at the low precision of maize leaf pest and disease detection, a new model of maize leaf pest and disease detection using attention mechanism and multi-scale features was proposed. Our model combines a convolutional block attention module (CBAM) with the ResNet50 backbone network to suppress complex background interference and enhance feature expression in specific regions of the maize leaf images. We also design a multi-scale feature fusion module that aggregates local and global information at different scales, improving the detection performance for objects of varying sizes. This module reduces the number of parameters and enhances efficiency by using a lightweight module and replacing the deconvolutional layer. Experimental results on a natural environment dataset demonstrate that our proposed model achieves an average detection accuracy of 85.13%, which is 9.59% higher than the original CenterNet model. The model has 24.296 M parameters and a detection speed of 23.69 f/s. Compared with other popular models such as SSD-VGG, YOLOv5, Faster-RCNN, and Efficientdet-D0, our proposed model demonstrates superior performance in the fast and accurate detection of maize leaf pests and diseases. This model has practical applications in the identification and treatment of maize pests and diseases in the field, and it can provide technical support for precision pesticide application. The trained model can be deployed to a web client for user convenience. [ABSTRACT FROM AUTHOR]

Weeds cause more crop yield loss and increase farmers' production costs more than any other agricultural pest worldwide. Natural extracts can be an important alternative to synthetic herbicides, or they can be one of the resources from which to discover new pesticide leads. The phytotoxic potential of smoke water was evaluated regarding germination and initial growth, prospecting for its possible herbicidal activity in weeds. Herbicidal activity was evaluated through germination, initial growth, and seedling vigor index bioassays in the laboratory and emergency with initial development bioassays in a greenhouse with smoke water solutions at 2.5, 5, 10 and 20% v/v. Experiments with two treatments were analyzed using T-tests for the parametric data and the Mann–Whitney test for the non-parametric data (p < 0.05). Experiments with three treatments or more were analyzed with a one-way ANOVA test followed by a Tukey test for the parametric data and a Kruskal–Wallis test followed by a Dunn test for the non-parametric data (p < 0.05). Linear regression was used to analyze data from the time–injury curve. The greatest effect on germination suppression (98%) was achieved when the Amaranthus viridis seeds were germinated in the laboratory with a 10% smoke water solution. Germination of Raphanus raphanistrum and Digitaria insularis was reduced by 93 and 75%, respectively, at this concentration. In greenhouse experiments, emergence of A. viridis was inhibited 81% by 20% smoke water. In laboratory initial growth experiments, 5% smoke water had the greatest inhibitory effect (94%) on A. viridis. R. raphanistrum initial growth reduction was 82%, Urochloa decumbens was 80%, D. insularis was 77% and Emilia fosbergii was 70% in the same conditions. In greenhouse development experiments, 70% of the A. viridis plants were killed by 5% smoke water treatment. These plants had 88% injury after treatment with 5% smoke water. Therefore, these findings suggest that smoke water solutions have potential as an herbicide, inhibiting the germination and initial growth of monocotyledonous and eudicotyledonous weeds. However, field tests are needed to confirm the potential of smoke water as an herbicide. [ABSTRACT FROM AUTHOR]

Most butterfly larvae are agricultural pests and forest pests, but butterflies have important ornamental value and the ability to sense and respond to changes in the ecological environment. There are many types of butterflies, and the research on classification of butterfly species is of great significance in practical work such as environmental protection and control of agricultural and forest pests. Butterfly classification is a fine-grained image classification problem that is more difficult than generic image classification. Common butterfly photos are mostly specimen photos (indoor photos) and ecological photos (outdoor photos/natural images). At present, research on butterfly classification is more based on specimen photos. Compared with specimen photos, classification based on ecological photos is relatively difficult. This paper mainly takes ecological photos as the research object, and presents a new classification network that combines the dilated residual network, squeeze-and-excitation (SE) module, and spatial attention (SA) module. The SA module can make better use of the long-range dependencies in the images, while the SE module takes advantage of global information to enhance useful information features and suppress less useful features. The results show that the integrated model achieves higher recall, precision, accuracy, and f1-score than the state-of-the-art methods on the introduced butterfly dataset. [ABSTRACT FROM AUTHOR]

Non-insecticidal control strategies using entomopathogens, nematodes, and endophytes provide sustainable and safer alternatives for managing crop pests. This study investigated the potential of different fungal endophytes, specifically Beauveria bassiana strains, in colonizing cotton plants and their efficacy against tarnished plant bug, Lygus lineolaris. The effect of endophytes on plant growth parameters and cotton yield were measured during different plant growth stages. The entomopathogenicity of these fungi was studied in diet cup bioassays using L. lineolaris adults. The behavior of adult males and females toward endophytic cotton squares was analyzed using olfactometer assays. The experiments showed that the fungal endophytes colonized the plant structures of cotton plants, which resulted in an increase in the number of cotton squares, plant height, and weight compared to control plants. B. bassiana strains/isolates such as GHA, NI-8, and JG-1 caused significant mortality in Lygus adults compared to controls. Also, male and female Lygus adults exhibited repellence behavior towards endophytic cotton squares containing JG-1 isolate of B. bassiana and to other B. bassiana strains such as NI-8, GHA, and SPE-120. No differences were observed in the survival and development of L. lineolaris second-instar nymphs on endophytic cotton, and no yield differences were observed in the field experiments. [ABSTRACT FROM AUTHOR]

Pleurotus ostreatus, an edible mushroom widely consumed worldwide, generates a by-product known as spent mushroom substrate (SMS). This material has demonstrated biological activity against agricultural crop pathogens. In this study, we evaluated the nematocidal effectiveness of hydroalcoholic extracts (T5, T2, AT5, and AT2) derived from SMS of P. ostreatus against (J2) of the phytonematode Nacobbus aberrans and assessed their potential toxicity towards the non-target nematode Panagrellus redivivus. Among these extracts, AT5 exhibited the highest efficacy against N. aberrans and was the least toxic against P. redivivus. Liquid–liquid partitioning yielded the AQU fraction, which showed significant nematocidal activity against J2 (75.69% ± 8.99 mortality), comparable to chitosan. The GC-MS analysis revealed the presence of several compounds, including palmitic acid, linoleic acid, and 2,4-Di-tert-butylphenol. These findings are consistent with studies confirming the antagonistic effectiveness of these compounds against phytonematodes. Additionally, all extracts exhibited toxicity against P. redivivus, with T2 being the most toxic. Our findings demonstrate that while the AT5 extract displays antagonistic effectiveness against both N. aberrans and P. redivivus, it was the least toxic among the extracts tested. Thus, SMS of P. ostreatus holds potential as a source of nematocidal compounds, which could offer significant benefits for agricultural pest control. [ABSTRACT FROM AUTHOR]

Cuelure, an effective lure specifically targeting Tephritid fruit flies, has been widely adopted and applied in the monitoring and control of these pests, providing significant support for agricultural pest management. However, its uncontrollable release speed and duration usually lead to a lot of waste, diminishing its effectiveness and increasing the cost of pest control. In order to solve these problems, we focused on Zeugodacus cucurbitae Coquillett and developed a temperature-sensitive nano-controlled release agent for cuelure. The release rate of this agent can be adjusted by adjusting the ambient temperature. The results show that the temperature-sensitive cuelure nano-controlled release agent demonstrates remarkable temperature-responsive controlled release characteristics. It still exhibits exceptional stability even after being subjected to high-temperature treatment at 60 °C for a week, and the trapping efficiency of this attractant remains between 73% and 75%. This study not only holds immense practical value in monitoring, warning, and managing of fruit fly pests, but it also lays a novel theoretical foundation for the development of insect attractants. [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]