Identification Of Insect Pests Research Articles

Incidence, Level of Damage and Identification of Insect Pests of Fruits and Leaves of Ziziphus Tree Species in Ethiopia

Incidence, Level of Damage and Identification of Insect Pests of Fruits and Leaves of Ziziphus Tree Species in Ethiopia

Identification of Insect Pests in Stored Pulses within Tripoli, Libya

أجريت هذه الدراسة للبحث في أنواع الآفات الحشرية المتواجدة بخمسة أنواع من الحبوب البقولية وهي: الحمص، الفول، الفاصوليا البيضاء، البازلاء والعدس الأحمر. تم الحصول على عينات هذه البقوليات عشوائيا من أسواق محلية مختلفة بمدينة طرابلس كما يلي: سوق الجمعة، تاجوراء، عين زارة، طرابلس المركز، أبو سليم، حي الأندلس وجنزور. أظهرت النتائج أن 39.05 % من العينات كانت مصابة بنوع أو أكثر من الحشرات. من خلال النتائج المتحصل عليها كانت النسب المئوية للعينات المصابة كالتالي: الفول 52.38 %، البازلاء 42.86%، العدس الأحمر 38.11 %، الفاصوليا البيضاء 33.33% والحمص 28.57%. بينت النتائج أيضاً وجود ثماني أنواع من الآفات الحشرية في العينات المدروسة. وهي: سوسة اللوبيا Callosobruchus maculatus (F.)، خنفساء الفول الصينية Callosobruchus chinensis L.، خنفساء الفاصوليا Acanthoscelides obtectus (Say)، خنفساء الفول الصغيرة Bruchidius incarnatus Boheman، سوسة الحبوب Sitophilus granarius (L.)، ثاقبة الحبوب الصغرى Rhizopertha dominica (F.) ، خنفساء الدقيق الحمراء Tribolium castaneum (Herbst) و خنفساء الحبوب المنشارية Oryzaephilus surinamensis (L.). من خلال النتائج المتحصل عليها كانت أكثر أنواع الخنافس وجوداً هي سوسة اللوبيا C. maculatus بنسبة مئوية 18.10 %، خنفساء الفاصوليا A. obtectus 14.29 % وثاقبة الحبوب الصغرى R. dominica بنسبة مئوية بلغت 8.57 %.

Decision fusion-based system to detect two invasive stink bugs in orchards

Accurate and early detection of insect pests plays an important role in crop protection and pest management in agriculture, especially in orchards. This paper is focused on evaluating and improving the performance of insect detection algorithms by adopting an ensemble approach of artificial neural networks. A set of advanced object detection models including YOLOv8, Faster R-CNN, RetinaNet, SSD, and FCOS were selected, and the models were trained and evaluated on a common dataset representing digital images of different insect species pests. Two classes were considered represented by quite similar invasive stink bugs, Halyomorpha Halys and Nezara Viridula. These architectures were optimized to identify significant peculiarities and variations between reference insects, including size, shape, and color. Each model has been implemented and optimized to achieve the best possible performance before integrating into an ensemble system. By integrating the predictions of these models through a weighted ensemble mechanism that leverages the F1 Score of each model, a more performant global system was developed capable of detecting insect pests with improved performance over individual models. This significant improvement in insect detection highlights the potential of the proposed ensemble system in efficient and rapid insect pest identification, ultimately providing valuable opportunities for implementing crop monitoring technologies. The research highlights the importance of implementing and developing deep-learning technologies for solving specific challenges in agriculture and brings innovative ways of strategic pest management for sustainable agricultural practices.

Identification of Insect Pests on Soybean Leaves Based on SP-YOLO

Soybean insect pests can seriously affect soybean yield, so efficient and accurate detection of soybean insect pests is crucial for soybean production. However, pest detection in complex environments suffers from the problems of small pest targets, large inter-class feature similarity, and background interference with feature extraction. To address the above problems, this study proposes the detection algorithm SP-YOLO for soybean pests based on YOLOv8n. The model utilizes FasterNet to replace the backbone of YOLOv8n, which reduces redundant features and improves the model’s ability to extract effective features. Second, we propose the PConvGLU architecture, which enhances the capture and representation of image details while reducing computation and memory requirements. In addition, this study proposes a lightweight shared detection header, which enables the model parameter amount computation to be reduced and the model accuracy to be further improved by shared convolution and GroupNorm. The improved model achieves 80.8% precision, 66.4% recall, and 73% average precision, which is 6%, 5.4%, and 5.2%, respectively, compared to YOLOv8n. The FPS reaches 256.4, and the final model size is only 6.2 M, while the number of computational quantities of covariates is basically comparable to that of the original model. The detection capability of SP-YOLO is significantly enhanced compared to that of the existing methods, which provides a good solution for soybean pest detection. SP-YOLO provides an effective technical support for soybean pest detection.

Automated Identification of Insect Pests: A Deep Transfer Learning Approach Using ResNet

Automated Identification of Insect Pests: A Deep Transfer Learning Approach Using ResNet

Research on Insect Pest Identification in Rice Canopy Based on GA-Mask R-CNN

Aiming at difficult image acquisition and low recognition accuracy of two rice canopy pests, rice stem borer and rice leaf roller, we constructed a GA-Mask R-CNN (Generative Adversarial Based Mask Region Convolutional Neural Network) intelligent recognition model for rice stem borer and rice leaf roller, and we combined it with field monitoring equipment for them. Firstly, based on the biological habits of rice canopy pests, a variety of rice pest collection methods were used to obtain the images of rice stem borer and rice leaf roller pests. Based on different segmentation algorithms, the rice pest images were segmented to extract single pest samples. Secondly, the bug generator based on a generative adversarial network strategy improves the sensitivity of the classification network to the bug information, generates the pest information images in the real environment, and obtains the sample dataset for deep learning through multi-way augmentation. Then, through adding channel attention ECA module in Mask R-CNN and improving the connection of residual blocks in the backbone network ResNet101, the recognition accuracy of the model is improved. Finally, the GA-Mask R-CNN model was tested on a multi-source dataset with an average precision (AP) of 92.71%, recall (R) of 89.28% and a balanced score F1 of 90.96%. The average precision, recall, and balanced score F1 are improved by 7.07, 7.65, and 8.83%, respectively, compared to the original Mask R-CNN. The results show that the GA-Mask R-CNN model performance indexes are all better than the Mask R-CNN, the Faster R-CNN, the SSD, the YOLOv5, and other network models, which can provide technical support for remote intelligent monitoring of rice pests.

Determinants of Training Need of the Pineapple Growers for Boosting Production in Hilly Areas of Sreemangal Upazila Under Moulvibazar District

Training is a tool to increase production both vertically and horizontally through enhanced skills of the farmers. The focus of the study was to determine and describe the training need of the pineapple growers in a hilly area of Sylhet region and explores the relationship between the selected characteristics of growers and training need. Data were collected from randomly selected 75 pineapple growers out of 228 of three unions namely Sreemangal, Ashidron, and Sindhurkhan of Sreemangal upazila under Moulvibazar district using a pre-tested interview schedule from 1 September to 2 October 2020. Through Focus Group Discussion (FGD) with the growers, a total of 12 different aspects of pineapple cultivation were identified as inadequately skilled for modern pineapple cultivation. For quantification of training need, each respondent was asked to answer the extent of training need against each of those aspects. Results revealed that most of the pineapple growers (58.7%) had medium training need while 29.3% had high and only 12.0% had low training need. The top five training need aspects of pineapple cultivation were appropriate amount and time of fertilizer application, modern method of insect–pest identification and control, soil moisture conservation technique, and preventive measure of fruit sunburn. Correlation analysis indicated that age (-0.272*), educational (-0.526**), annual income (-0.269*), experience of pineapple cultivation (-0.455**), knowledge about pineapple cultivation (-0.807**), training received (-0.558**), and use of information source (-0.331**) were found negatively significant with their training need. Extension service providers should come forward to facilitate access of need-based information and skills to the pineapple growers or at least do their best alternative based on resource allocation for improvement of yield and production of pineapple in the hilly areas of Sylhet region.

Situation des poissons d’eau douce fumés vendus dans les marchés de la ville de Yaoundé (Région du Centre du Cameroun) et évaluation des méthodes de contrôle contre leurs insectes ravageurs au cours du stockage

The smoking, storage and conservation of smoked fish remain the most efficient means of ensuring the almost permanent availability of seasonal fishing products. However, stored smoked fish can be infested by insect pests. The aim of this study was to present the situation of smoked fishes sold in the city of Yaoundé and the methods used by the traders to control insect pests. For this purpose, a study was conducted from October to December 2022 in seven markets in Yaoundé where 65 traders were interviewed mainly on their activities, the origin of smoked fishes and the methods used to control insect pests. The inventory and the quantity of smoked fishes was made in different markets. The storage tools were inspected and the samples of infested smoked fish (commons names) (Catfish, Kanga, Carp, Tilapia, Eel fish, Redtail) and samples of apparently not infested fish (Catfish, Kanga, Carp) were bought from traders according to availability and brought back to laboratory. In the Laboratory, the identification of insect pests was done, the number of insect and the galleries of fish’s collection was counted. It emerges from this study that 80.37% traders are women; according to the age group, 41.44% of traders are between [41-50] years old. 53.67% of traders have a primary education level. Cardboard boxes are the most used tools in fish storage (100%). Six (6) freshwater smoked fish are sold and catfish are the most represented with 2,604 boxes of 50 kg. Dermestes maculatus De Geer 1774 (Coleoptera: Dermestidae) (221 larvae and 54 adults) and Necrobia rufipes De Geer 1775 (Coleoptera: Cleridae) (65 larvae and 37 adults) are the insects pests. Catfish is the smoked fish that revealed the largest number of galleries (86). The chemicals used by traders are Rambo (14.10%) and DD force (24.36%). Mayo-Danay provides 49.86% of smoked fish sold in Yaoundé markets. The ANOVA and Duncan tests have shown that significant differences are observed in the various storage tools and control methods used by traders in the various Yaoundé markets to protect smoked fish from insect pests (p<0.001).

Rapid detection of insect pest with CRISPR‐Cas13a‐Based Lateral Flow Strip: Using Locusta migratoria manilensis

AbstractThe Clustered Regularly Interspaced Short Palindromic Repeats‐associated (CRISPR‐Cas) system has been used as a powerful diagnostic tool because of its trans‐cleavage ability to accurately recognize and cleave specific nucleic acid targets. However, its application in insect pest detection has rarely been reported. The aim of the current study was to develop a new molecular identification method for insect based on CRISPR‐Cas13a system. In this study, we have developed a highly specific and sensitive detection system that combines polymerase chain reaction, CRISPR‐Cas13a system and lateral flow dipstick (PCR‐Cas13a‐LFD) to rapidly detect the presence of Locusta migratoria manilensis (Orthoptera: Acrididae) DNA and discriminate it from other species, by using material from different stages of development. A pair of specific primers and crRNA were designed based on the Gene DEAD‐box DDX10 mRNA sequence. For visual readout, a FAM‐RNA‐biotin reporter was used for detection. The CRISPR‐Cas13a‐based detection method utilizes the visual identification of L. migratoria manilensis at different developmental stages or with the use of incomplete samples. The test results could be distinguished within 2 h. The sensitivity of the PCR‐Cas13a‐LFD detection system reached 0.1 ng/μL, a 10‐fold increase compared with that of the PCR with electrophoresis. The LFD coupled with CRISPR‐Cas13a (Cas13a‐LFD) is promising for the portable, onsite and fast identification of insect pests. This study provides a reference for the development of a new method for insect identification.

Jenis-Jenis Hama Serangga Gaharu (Aquilaria mallacensis Lamk) di Desa Kuapan, Kecamatan Tambang, Kabupaten Kampar, Provinsi RIAU

The presence of insect pests has an important effect on the success of plant maintenance. The level of attack caused by insect pests can cause plants to die. The purpose of the study was to analyze agarwood plants that were attacked by insect pests and identify the types of insect pests that attack agarwood plants. The research method used is descriptive. The assessment of the level of damage to agarwood plants due to insect pests is calculated based on the criteria for damage caused by insect pests. Identification of insect pests is carried out directly in the field based on the activity of insects that damage agarwood plants. Based on the results of the identification of insect pests that damage agarwood plants, there are 5 types of insect pests, namely the type of White Flea (Pseudococcus sp.), Leaf Caterpillar (Heortia viitessoides), Pitama hermesalis, Coreidae and Locusta migratoria. The insect pest attack rate is 2.3% and is included in the low category. It is necessary to intensive monitoring can insect pest attacks. If the insect pests found, they should clean up the environment from pests

A novel approach for insect-pest identification using multipath convolutional neural network

A novel approach for insect-pest identification using multipath convolutional neural network

Fine-grained image classification of microscopic insect pest species: Western Flower thrips and Plague thrips

Accurate identification of insect pests is essential in crop management as they are one of the primary causes of yield losses. However, differences between insect species demand different pest control strategies. Hence, research on new technology for fine-grained classification of insect pests is potentially important. Morphologically similar microscopic pest species classification has received little attention in the literature, and is targeted by this study as a means to address the need for agricultural pest management. We propose a novel computational method for deep learning-based, fine-grained classification of microscopic insects using the Vision Transform (ViT) architecture. This architecture employs an attention mechanism motivated by domain knowledge. The proposed approach consists of two main modules, a Data Preprocessing Module to segment relevant insect features and split the insect into body segments to inform identification, and a Domain Knowledge-Driven Stacked Model based on ViT to generate the prediction from each body segment and to fuse predictions for each segment into an accurate species-level classification. We tested the approach using an image dataset of two economically devastating thrip species – Western Flower thrips (Frankliniella occidentalis) and Plague thrips (Thrips imaginis). These insects are small (∼1mm), exhibit minute inter-species differences, and require different pest control strategies. We compared our model with the original ViT model, RestNet101, and RestNet50. Experimental results achieve an F1-score of 0.978, a 3.27% improvement over the baselines. This is important in the horticultural context given the yield losses that these pest insects are known to cause if their populations remain incorrectly quantified.

Custom CornerNet: a drone-based improved deep learning technique for large-scale multiclass pest localization and classification

Insect pests are among the most critical factors affecting crops and result in a severe reduction in food yield. At the same time, early and accurate identification of insect pests can assist farmers in taking timely preventative steps to reduce financial losses and improve food quality. However, the manual inspection process is a daunting and time-consuming task due to visual similarity between various insect species. Moreover, sometimes it is difficult to find an experienced professional for the consultation. To deal with the problems of manual inspection, we have presented an automated framework for the identification and categorization of insect pests using deep learning. We proposed a lightweight drone-based approach, namely a custom CornerNet approach with DenseNet-100 as a base network. The introduced framework comprises three phases. The region of interest is initially acquired by developing sample annotations later used for model training. A custom CornerNet is proposed in the next phase by employing the DenseNet-100 for deep keypoints computation. The one-stage detector CornerNet identifies and categorizes several insect pests in the final step. The DenseNet network improves the capacity of feature representation by connecting the feature maps from all of its preceding layers and assists the CornerNet model in detecting insect pests as paired vital points. We assessed the performance of the proposed model on the standard IP102 benchmark dataset for pest recognition which is challenging in terms of pest size, color, orientation, category, chrominance, and lighting variations. Both qualitative and quantitative experimental results showed the effectiveness of our approach for identifying target insects in the field with improved accuracy and recall rates.

Knowledge and Practices of Vegetables Insect Pest Managements in Banganga Municipality of Kapilvastu District

A study was carried out in Banganga Municipality of Kapilvastu district to know the farmer's knowledge, practices, and management method used in insect pests of vegetables. The survey involved 160 randomly selected farmers who were interviewed using semi-structured questionnaires and also evaluated based on direct field observation. The data were analyzed using SPSS and Microsoft-Excel. Tomato, potato, chili, cauliflower, cabbage, garlic, and onion were major vegetables grown by the farmers during the winter season and cucumber, bottle gourd, bitter gourd, sponge gourd, tomato, chili, brinjal during the summer season. Aphids, cabbage butterfly, pumpkin beetle, tomato leaf miner, cutworm, and tomato fruit borer were the major pests in vegetable field. Knowledge of vegetable farmers regarding insect pest identification was also observed i.e., 86% of respondents identified insect pest by the help of Junior Technical Assistance and agro-vets, and 10% of respondents identified insects by their own knowledge. About 60% of respondents were found using chemical pesticides such as; chlorpyrifos, cypermethrin, imidacloprid, alphamethrin etc. to control pests, 4% of respondents were using botanical plant extract i.e., jholmal, neem extract, cow urine and 24% were using cultural methods such as crop rotation, mulching, tillage operation. Only a few farmers' groups were found to know about IPM, biological pest management practices, and conservation of natural enemies.

Rapid Identification of Western Flower Thrips, Frankliniella occidentalis (Thysanoptera: Thripidae) in Shade Houses in Western Cape of South Africa

The western flower thrips (WFT), Frankliniella occidentalis (Pergande) (Thripidae: Thysanoptera), is one of the most economically important pests in shade houses. However, their identification is usually difficult, with them being easily confused with other thrips species. Accurate, rapid and reliable identification of insect pests is a crucial first step in implementing an efficacious management program. In this study the identity of F. occidentalis was verified, using molecular methods using the mtCOI gene sequences. Molecular analysis of thrips specimens collected from chrysanthemums and blueberries in the Western Cape Province, South Africa revealed the presence of Frankliniella. occidentalis and four other thrips species. Two of the five the specimens were F. occidentalis and one of the specimens was identified as Gynaikothrips ficorum. The remaining specimens were identified only to a generic level as Pseudophilothrips sp and to an ordinal level as Thrips sp. Failure to identify the two specimens to specific levels might have resulted from lack of sequences of identified thrips species in the molecular data bases. Considering the speed, specificity as well as sensitivity of the method, mtCOI sequences can be used as a swift and efficient method for western flower thrips identification and detection of new thrips pest invasion.

Multi-Scale Convolution-Capsule Network for Crop Insect Pest Recognition

Accurate crop insect pest identification in fields is useful to control pests and beneficial to agricultural yield and quality. However, it is a difficult and challenging problem due to the crop insect pests being small with various sizes, postures, shapes, and disorganized backgrounds. Multi-scale convolution-capsule network (MSCCN) is constructed for crop insect pest identification. It consists of a multi-scale convolution module, capsule network (CapsNet) module, and SoftMax classification module. Multi-scale convolution is used to extract the multi-scale discriminative features, CapsNet is employed to encode the hierarchical structure of the size-variant insect pests in the crop images, and Softmax is adopted for insect pest identification. MSCCN combines the advantages of convolutional neural network (CNN), CapsNet, and multi-scale CNN, and can learn multi-scale robust features from pest images of different shapes and sizes for pest recognition and identify various morphed pests. Experimental results on the crop pest image dataset show that this method has a good recognition rate of 91.4%.

​​Identification of Insect Pests of Maize (Zea mays L.) in Girar Jarso and Hidebu Abote Districts, North Shewa Zone, Oromia, Central Ethiopia

Background: Maize is the most important staple food crops in sub-Saharan Africa, including Ethiopia, predominantly produced and consumed directly by the smallholder farmers. Insect pests are the serious pests causing yield loss of maize in field at different growth stages. Methods: The field survey was carried out during 2019-2020 crop growing season. Purposive sampling technique was used for selecting the districts based on the potential producers of maize and a random sampling technique was used to select the kebeles and the stakeholders. Result: The major identified insect pests of maize in the two districts were grass hopper (Hieroglyphus nigrorepletus), maize leaf hopper (Cicadulin ambila), maize pod borers (Helicoverpa armigera, Etiella), maize stem borers (Chilopartellus Swinhoe), Hairy caterpillar (Amsacta albistriga Walker), Black cut worm (Agrotis ipsilon Hufnagal), Maize leaf Aphid (Rhopalosiphum maidis Fitch), Army worm (Mythimna separata Walker), Fall armyworm (Spodoptera frugiperda), Pink stem borer (Sesamiain ferens Walker), Corn Earworm (Helicoverpa zea Boddias), Chafer beetle (Chiloloba acuta Wiedmann), Shoot bug (Peregrinus maidis Ashamed), White grub (Holotrichia consanguinea) and shoot fly (Atherigona soccata).

Characterization of Farmer’s knowledge and management practices of papaya mealybug Paracoccus magnatus (Hemiptera: Pseudococcidae) in Tanzania

Papaya mealybug (PMB) is a serious insect pest for papaya production in Sub-Saharan Africa, limiting production potential in farming communities. We did a household survey to evaluate the Characteristics of farmers' knowledge, challenges, and current (PMB) control practices in four papaya growing regions of Tanzania namely, Tanga, Dodoma, Pwani, and Katavi involving 100 papaya farmers. The study found that 96% of farmers reported PMB, as a major challenge in papaya production. Very few (0.8%) of the farmers were knowledgeable on insect pest identification. Chemical pesticides were the only option for PMB control, and 43.0% of farmers were able to access and apply. We also found that 36.4% of the farmers were aware of the adverse effects of chemical pesticides. Furthermore, the study observed that 0.3% of farmers use botanical pesticides. Additionally, the study observed that 44.1% of farmers use control measures against PMB, the remaining 55.9% did not practice any control measure, thus leading to low papaya yields observed in the study regions. Our findings provide insights to farmers into the use of plant-based pesticides, mainly plant essential oils, and its benefits that may promote farmers' attitudes towards increasing papaya yield and reducing chemical pesticide use to avoid pest resistance.

Smarter Pest Identification Technology (SPIDTECH): a Mobile Application for Digital Identification and Remote Monitoring of Insect Pests and Diseases of Major Crops in the Philippines

Correct identification and proper monitoring are vital components of integrated pest and disease management. The Android application – Smarter Pest Identification Technology (SPIDTECH) – was developed for the digital identification and remote monitoring of insect pests and diseases of rice, corn, coffee, cacao, banana, coconut, sugarcane, tomato, and soybean in the Philippines. SPIDTECH has three main features: the digital identification of insect pests and diseases using a smartphone camera; the digital library that contains images, identification signs, life stages, management practices, and other pertinent information about a pest or disease; and the remote monitoring that enables real-time mapping of reports through user-contributed images and GPS points. The application can identify 71 insects and 63 diseases, while the library features a collection of 104 insects and 89 diseases available in English and Filipino. The identification uses a pretrained MobileNetV2, a convolutional neural network design by Google for mobile devices. The models were retrained using the pest and disease image dataset collected specifically for this study and logging 55.7–73.3% accuracy. If connected to the internet, devices send image data from the field that are validated and used for model retraining. SPIDTECH recorded more than 7,400 device downloads from March 2019–July 2021 and received 4.8 out of 5 user review ratings. Based on the user-provided registration data in the same period, it has more than 5,600 registered users from 81 provinces with an average user acquisition rate of 266 new users per month. With the current features deployed, the application received more than 8,000 identification requests for different crops. The application has gathered a significant number of users necessary to evaluate the feasibility of the application in assisting in pest and disease identification and remote monitoring for the major crops in the Philippines.

Fine-Grained Pests Recognition Based on Truncated Probability Fusion Network via Internet of Things in Forestry and Agricultural Scenes

Accurate identification of insect pests is the key to improve crop yield and ensure quality and safety. However, under the influence of environmental conditions, the same kind of pests show obvious differences in intraclass representation, while the different kinds of pests show slight similarities. The traditional methods have been difficult to deal with fine-grained identification of pests, and their practical deployment is low. In order to solve this problem, this paper uses a variety of equipment terminals in the agricultural Internet of Things to obtain a large number of pest images and proposes a fine-grained identification model of pests based on probability fusion network FPNT. This model designs a fine-grained feature extractor based on an optimized CSPNet backbone network, mining different levels of local feature expression that can distinguish subtle differences. After the integration of the NetVLAD aggregation layer, the gated probability fusion layer gives full play to the advantages of information complementarity and confidence coupling of multi-model fusion. The comparison test shows that the PFNT model has an average recognition accuracy of 93.18% for all kinds of pests, and its performance is better than other deep-learning methods, with the average processing time drop to 61 ms, which can meet the needs of fine-grained image recognition of pests in the Internet of Things in agricultural and forestry practice, and provide technical application reference for intelligent early warning and prevention of pests.