Search

Natural enemies suppress many aphid populations, and yet, population outbreaks sometimes occur. The reasons predation fails to suppress such outbreaks are not clearly understood. While manipulating predators to examine their role in soybean aphid population growth, a natural immigration of soybean aphids occurred that enabled us to compare the roles immigration and predation played in population growth. Using predator exclusion cages, we found that predation on the top of the plant accounted for 42.3 ± 11.4% (mean ± SE) reduction in aphid population growth rates. When 90-100% of the canopy was exposed, predation failed to reduce aphid population growth because winged immigrants colonized plants, with an observed 6-fold increase in alates compared to plants completely covered or exposing only the top nodes (approximately 10% of the total canopy). We conclude that reproduction by immigrants contributed to population growth rates sufficiently to compensate for predation. These results demonstrate that immigration can counteract high levels of predation and lead to aphid population growth rates that could result in outbreak population densities. [ABSTRACT FROM AUTHOR]

Since the invasion of the sorghum aphid Melanaphis sorghi (Theobald), farmers in the sorghum ( Sorghum bicolor L. Moench) production region in the Great Plains of the U.S. have faced significant crop damage and reduced yields. One widely used practice to aid in managing sorghum aphids is pest monitoring, which often results in field-level insecticide applications when an economic threshold is reached. However, relying on this traditional management practice includes the application of insecticides to non-infested plants. To reduce insecticide usage in sorghum, we proposed spraying individual plants when aphids are present or absent compared to traditional spraying based on a standard economic threshold using field replicate plots over two summer seasons. The experimental results of this study indicated fewer aphids in plots managed with an economic threshold, followed by randomly sprayed and plant-specific treatments compared with the untreated control treatment. Therefore, compared with traditional management, those treatments can be alternative strategies for managing aphids on sorghum within our field plot study.

Sorghum aphid, Melanaphis sorghi (Theobald) have become a major economic pest in sorghum causing 70% yield loss without timely insecticide applications. The overarching goal is to develop a monitoring system for sorghum aphids using remote sensing technologies to detect changes in plant-aphid density interactions, thereby reducing scouting time. We studied the effect of aphid density on sorghum spectral responses near the feeding site and on distal leaves from infestation and quantified potential systemic effects to determine if aphid feeding can be detected. A leaf spectrometer at 400-1000 nm range was used to measure reflectance changes by varying levels of sorghum aphid density on lower leaves and those distant to the caged infestation. Our study results demonstrate that sorghum aphid infestation can be determined by changes in reflected light, especially between the green-red range (550-650 nm), and sorghum plants respond systemically. This study serves as an essential first step in developing more effective pest monitoring systems for sorghum aphids, as leaf reflection sensors can be used to identify aphid feeding regardless of infestation location on the plant. Future research should address whether such reflectance signatures can be detected autonomously using small unmanned aircraft systems or sUAS equipped with comparable sensor technologies., (© 2024. The Author(s).)

Wheat ( Triticum aestivum ) is a major cereal crop planted in the Southern Great Plains. This crop faces diverse pests that can affect their development and reduce yield productivity. For example, aphids are a significant pest in wheat, and their management relies on pesticides, which affect the sustainability and biodiversity of natural predators that prey on aphids. Coccinellids, commonly named lady beetles, are the most abundant natural predators of wheat. These natural enemies contribute to the natural predation of aphids, which can reduce the use of excessive pesticides for aphid management. Usually, visual observations of these natural enemies are performed during pest sampling; however, it is time-consuming and requires manual labor, which can be expensive. An automation system or detection models based on machine learning approaches that can detect these insects is needed to reduce unnecessary pesticide applications and manual labor costs. However, developing an automation system or computer vision models that automatically detect these natural enemies requires imagery to train and validate this cutting-edge technology. To solve this research problem, we collected this dataset, which includes images and label annotations to help researchers and students develop this technology that can benefit wheat growers and science to understand the capabilities of automation in Entomology. We collected a dataset using mobile devices, which included a diverse range of coccinellids on wheat images. The dataset consists of 2,133 images with a standard size of 640 × 640 pixels, which can be used to train and develop detection models for machine learning purposes. In addition, the dataset includes annotated labels that can be used for training models within the YOLO family or others, which have been proven to detect small insects in crops. Our dataset will increase the understanding of machine learning capabilities in entomology, precision agriculture, education, and crop pest management decisions., (© 2024 The Author(s).)

Aphid infestations are one of the primary causes of extensive damage to wheat and sorghum fields and are one of the most common vectors for plant viruses, resulting in significant agricultural yield losses. To address this problem, farmers often employ the inefficient use of harmful chemical pesticides that have negative health and environmental impacts. As a result, a large amount of pesticide is wasted on areas without significant pest infestation. This brings to attention the urgent need for an intelligent autonomous system that can locate and spray sufficiently large infestations selectively within the complex crop canopies. We have developed a large multi-scale dataset for aphid cluster detection and segmentation, collected from actual sorghum fields and meticulously annotated to include clusters of aphids. Our dataset comprises a total of 54,742 image patches, showcasing a variety of viewpoints, diverse lighting conditions, and multiple scales, highlighting its effectiveness for real-world applications. In this study, we trained and evaluated four real-time semantic segmentation models and three object detection models specifically for aphid cluster segmentation and detection. Considering the balance between accuracy and efficiency, Fast-SCNN delivered the most effective segmentation results, achieving 80.46% mean precision, 81.21% mean recall, and 91.66 frames per second (FPS). For object detection, RT-DETR exhibited the best overall performance with a 61.63% mean average precision (mAP), 92.6% mean recall, and 72.55 on an NVIDIA V100 GPU. Our experiments further indicate that aphid cluster segmentation is more suitable for assessing aphid infestations than using detection models.

Aphid infestation poses a significant threat to crop production, rural communities, and global food security. While chemical pest control is crucial for maximizing yields, applying chemicals across entire fields is both environmentally unsustainable and costly. Hence, precise localization and management of aphids are essential for targeted pesticide application. The paper primarily focuses on using deep learning models for detecting aphid clusters. We propose a novel approach for estimating infection levels by detecting aphid clusters. To facilitate this research, we have captured a large-scale dataset from sorghum fields, manually selected 5447 images containing aphids, and annotated each individual aphid cluster within these images. To facilitate the use of machine learning models, we further process the images by cropping them into patches, resulting in a labeled dataset comprising 151,380 image patches. Then, we implemented and compared the performance of four state-of-the-art object detection models (VFNet, GFLV2, PAA, and ATSS) on the aphid dataset. Extensive experimental results show that all models yield stable similar performance in terms of average precision and recall. We then propose to merge close neighboring clusters and remove tiny clusters caused by cropping, and the performance is further boosted by around 17%. The study demonstrates the feasibility of automatically detecting and managing insects using machine learning models. The labeled dataset will be made openly available to the research community., (© 2023. Springer Nature Limited.)

Increased global production of sorghum has the potential to meet many of the demands of a growing human population. Developing automation technologies for field scouting is crucial for long-term and low-cost production. Since 2013, sugarcane aphid (SCA) Melanaphis sacchari (Zehntner) has become an important economic pest causing significant yield loss across the sorghum production region in the United States. Adequate management of SCA depends on costly field scouting to determine pest presence and economic threshold levels to spray insecticides. However, with the impact of insecticides on natural enemies, there is an urgent need to develop automated-detection technologies for their conservation. Natural enemies play a crucial role in the management of SCA populations. These insects, primary coccinellids, prey on SCA and help to reduce unnecessary insecticide applications. Although these insects help regulate SCA populations, the detection and classification of these insects is time-consuming and inefficient in lower value crops like sorghum during field scouting. Advanced deep learning software provides a means to perform laborious automatic agricultural tasks, including detection and classification of insects. However, deep learning models for coccinellids in sorghum have not been developed. Therefore, our objective was to develop and train machine learning models to detect coccinellids commonly found in sorghum and classify them according to their genera, species, and subfamily level. We trained a two-stage object detection model, specifically, Faster Region-based Convolutional Neural Network (Faster R-CNN) with the Feature Pyramid Network (FPN) and also one-stage detection models in the YOLO (You Only Look Once) family (YOLOv5 and YOLOv7) to detect and classify seven coccinellids commonly found in sorghum (i.e., Coccinella septempunctata, Coleomegilla maculata, Cycloneda sanguinea, Harmonia axyridis, Hippodamia convergens, Olla v-nigrum, Scymninae). We used images extracted from the iNaturalist project to perform training and evaluation of the Faster R-CNN-FPN and YOLOv5 and YOLOv7 models. iNaturalist is an imagery web server used to publish citizen's observations of images pertaining to living organisms. Experimental evaluation using standard object detection metrics, such as average precision (AP), AP@0.50, etc., has shown that the YOLOv7 model performs the best on the coccinellid images with an AP@0.50 as high as 97.3, and AP as high as 74.6. Our research contributes automated deep learning software to the area of integrated pest management, making it easier to detect natural enemies in sorghum., (© 2023. The Author(s).)

Pest infestation causes significant crop damage during crop production, which reduces the crop yield in terms of quality and quantity. Accurate, precise, and timely information on pest infestation is a crucial aspect of integrated pest management practices. The current manual scouting methods are time-consuming and laborious, particularly for large fields. Therefore, a fleet of scouting vehicles is proposed to monitor and collect crop information at the sub-canopy level. These vehicles would traverse large fields and collect real-time information on pest type, concentration, and infestation level. In addition to this, the developed vehicle platform would assist in collecting information on soil moisture, nutrient deficiency, and disease severity during crop growth stages. This study established a proof-of-concept of a crop scouting vehicle that can navigate through the row crops. A reconfigurable ground vehicle (RGV) was designed and fabricated. The developed prototype was tested in the laboratory and an actual field environment. Moreover, the concept of corn row detection was established by utilizing an array of low-cost ultrasonic sensors. The RGV was successful in navigating through the corn field. The RGV's reconfigurable characteristic provides the ability to move anywhere in the field without damaging the crops. This research shows the promise of using reconfigurable robots for row crop navigation for crop scouting and monitoring which could be modular and scalable, and can be mass-produced in quick time. A fleet of these RGVs would empower the farmers to make meaningful and timely decisions for their cropping system.

Stink bugs represent an increasing risk to soybean production in the Midwest region of the United States. The current sampling protocol for stink bugs in this region is tailored for population density estimation and thus is more relevant to research purposes. A practical decision-making framework with more efficient sampling effort for management of herbivorous stink bugs is needed. Therefore, a binomial sequential sampling plan was developed for herbivorous stink bugs in the Midwest region. A total of 146 soybean fields were sampled across 11 states using sweep nets in 2016, 2017, and 2018. The binomial sequential sampling plans were developed using combinations of five tally thresholds at two proportion infested action thresholds to identify those that provided the best sampling outcomes. Final assessment of the operating characteristic curves for each plan indicated that a tally threshold of 3 stink bugs per 25 sweeps, and proportion infested action thresholds of 0.75 and 0.95 corresponding to the action thresholds of 5 and 10 stink bugs per 25 sweeps, provided the optimal balance between highest probability of correct decisions (≥ 99%) and lowest probability of incorrect decisions (≤ 1%). In addition, the average sample size for both plans (18 and 12 sets of 25 sweeps, respectively) was lower than that for the other proposed plans. The binomial sequential sampling plan can reduce the number of sample units required to achieve a management decision, which is important because it can potentially reduce risk/cost of management for stink bugs in soybean in this region., (© The Author(s) 2021. Published by Oxford University Press on behalf of Entomological Society of America. All rights reserved. For permissions, please e-mail: journals.permissions@oup.com.)

Pollinators are undergoing a global decline. Although vital to pollinator conservation and ecological research, species-level identification is expensive, time consuming, and requires specialized taxonomic training. However, deep learning and computer vision are providing ways to open this methodological bottleneck through automated identification from images. Focusing on bumble bees, we compare four convolutional neural network classification models to evaluate prediction speed, accuracy, and the potential of this technology for automated bee identification. We gathered over 89,000 images of bumble bees, representing 36 species in North America, to train the ResNet, Wide ResNet, InceptionV3, and MnasNet models. Among these models, InceptionV3 presented a good balance of accuracy (91.6%) and average speed (3.34 ms). Species-level error rates were generally smaller for species represented by more training images. However, error rates also depended on the level of morphological variability among individuals within a species and similarity to other species. Continued development of this technology for automatic species identification and monitoring has the potential to be transformative for the fields of ecology and conservation. To this end, we present BeeMachine, a web application that allows anyone to use our classification model to identify bumble bees in their own images.

Sugarcane aphid Melanaphis sacchari Zehntner is a significant economic pest of grain sorghum in the United States. Effective monitoring and early detection are cornerstones for managing invasive pests. The recently developed binomial sequential sampling plan estimates sugarcane aphid economic thresholds (ETs) based on classification whether a 2-leaf sample unit has ≤ or ≥ 50 M. sacchari. In this study, we evaluated eight 2-leaf sampling units for potential use in the sequential sampling plan. From 2016 through 2017, whole plant counts of M. sacchari were recorded non-destructively in situ on sorghum plants from 140 fields located in five states. Plant canopies were stratified into three categories. Two leaves from each stratum were used to compare linear relationships between M. sacchari numbers per two-leaf sample unit and total M. sacchari density per plant. Analysis revealed that two randomly selected leaves from the middle stratum accounted more variation for estimating M. sacchari density when compared to two leaves from the other strata. Comparison of eight two-leaf sampling units within plant growth stages were variable in quantifying variation of M. sacchari densities. When growth stages were combined, the standard uppermost + lowermost leaf sample unit and a unit consisting of two randomly selected leaves from the middle stratum revealed little difference in their enumeration of variation in M. sacchari density. Because other sample units were either less predictive and/or more variable in estimating M. sacchari density, we suggest that the (L1+U1) sample unit remain the preferred method for appraising M. sacchari ETs., (© The Author(s) 2020. Published by Oxford University Press on behalf of Entomological Society of America. All rights reserved. For permissions, please e-mail: journals.permissions@oup.com.)

The sugarcane aphid (Melanaphis sacchari Zehntner) is a significant economic pest of grain sorghum (Sorghum bicolor (L.) Moench) in the Southern United States. Current nominal and research-based economic thresholds are based on estimates of mean aphids per leaf. Because enumerating aphids per leaf is potentially time consuming, binomial sequential sampling plans for M. sacchari were developed that allow users to quickly classify the economic status of field populations and determine when an economic threshold has been exceeded. During 2016 and 2017, counts of M. sacchari were recorded from 281 sampling events in 140 sorghum fields located in six states (Oklahoma, Kansas, Texas, Arkansas, Louisiana, Mississippi) . Regression analysis was used to describe the relationships between the mean M. sacchari density per two-leaf sample and proportion of plants infested with one or more aphids. Tally thresholds of T50 and T100 aphids per two-leaf sample were selected based on goodness of fit and practicality. Stop lines for both tally thresholds were developed for selected economic thresholds using Wald's sequential probability ratio test. Model validations using an additional 48 fields demonstrated that reliable classification decisions could be made with an average of 11 samples regardless of location. This sampling system, when adopted, can allow users to easily and rapidly determine when M. sacchari infestations need to be treated., (© The Author(s) 2020. Published by Oxford University Press on behalf of Entomological Society of America. All rights reserved. For permissions, please e-mail: journals.permissions@oup.com.)

Stink bugs are an emerging threat to soybean (Fabales: Fabaceae) in the North Central Region of the United States. Consequently, region-specific scouting recommendations for stink bugs are needed. The aim of this study was to characterize the spatial pattern and to develop sampling plans to estimate stink bug population density in soybean fields. In 2016 and 2017, 125 fields distributed across nine states were sampled using sweep nets. Regression analyses were used to determine the effects of stink bug species [Chinavia hilaris (Say) (Hemiptera: Pentatomidae) and Euschistus spp. (Hemiptera: Pentatomidae)], life stages (nymphs and adults), and field locations (edge and interior) on spatial pattern as represented by variance-mean relationships. Results showed that stink bugs were aggregated. Sequential sampling plans were developed for each combination of species, life stage, and location and for all the data combined. Results for required sample size showed that an average of 40-42 sample units (sets of 25 sweeps) would be necessary to achieve a precision of 0.25 for stink bug densities commonly encountered across the region. However, based on the observed geographic gradient of stink bug densities, more practical sample sizes (5-10 sample units) may be sufficient in states in the southeastern part of the region, whereas impractical sample sizes (>100 sample units) may be required in the northwestern part of the region. Our findings provide research-based sampling recommendations for estimating densities of these emerging pests in soybean., (© The Author(s) 2019. Published by Oxford University Press on behalf of Entomological Society of America. All rights reserved. For permissions, please e-mail: journals.permissions@oup.com.)

Stink bugs (Hemiptera: Pentatomidae) are an increasing threat to soybean (Fabales: Fabaceae) production in the North Central Region of the United States, which accounts for 80% of the country's total soybean production. Characterization of the stink bug community is essential for development of management programs for these pests. However, the composition of the stink bug community in the region is not well defined. This study aimed to address this gap with a 2-yr, 9-state survey. Specifically, we characterized the relative abundance, richness, and diversity of taxa in this community, and assessed phenological differences in abundance of herbivorous and predatory stink bugs. Overall, the stink bug community was dominated by Euschistus spp. (Hemiptera: Pentatomidae) and Chinavia hilaris (Say) (Hemiptera: Pentatomidae). Euschistus variolarius (Palisot de Beauvois) (Hemiptera: Pentatomidae), C. hilaris and Halyomorpha halys (Stål) (Hemiptera: Pentatomidae) were more abundant in the northwestern, southeastern and eastern parts, respectively, of the North Central Region of the United States. Economically significant infestations of herbivorous species occurred in fields in southern parts of the region. Species richness differed across states, while diversity was the same across the region. Herbivorous and predatory species were more abundant during later soybean growth stages. Our results represent the first regional characterization of the stink bug community in soybean fields and will be fundamental for the development of state- and region-specific management programs for these pests in the North Central Region of the United States., (© The Author(s) 2019. Published by Oxford University Press on behalf of Entomological Society of America. All rights reserved. For permissions, please e-mail: journals.permissions@oup.com.)

Background: A 2-year, multi-state study was conducted to assess the benefits of using soybean seed treated with the neonicotinoid thiamethoxam to manage soybean aphid in the upper Midwestern USA and compare this approach with an integrated pest management (IPM) approach that included monitoring soybean aphids and treating with foliar-applied insecticide only when the economic threshold was reached. Concentrations of thiamethoxam in soybean foliage were also quantified throughout the growing season to estimate the pest management window afforded by insecticidal seed treatments., Results: Both the IPM treatment and thiamethoxam-treated seed resulted in significant reductions in cumulative aphid days when soybean aphid populations reached threshold levels. However, only the IPM treatment resulted in significant yield increases. Analysis of soybean foliage from thiamethoxam-treated seeds indicated that tissue concentrations of thiamethoxam were statistically similar to plants grown from untreated seeds beginning at the V2 growth stage, indicating that the period of pest suppression for soybean aphid is likely to be relatively short., Conclusion: These data demonstrate that an IPM approach, combining scouting and foliar-applied insecticide where necessary, remains the best option for treatment of soybean aphids, both in terms of protecting the yield potential of the crop and of break-even probability for producers. Furthermore, we found that thiamethoxam concentrations in foliage are unlikely to effectively manage soybean aphids for most of the pests' activity period across the region. © 2017 Society of Chemical Industry., (© 2017 Society of Chemical Industry.)

The soybean aphid, Aphis glycines Matsumura (Hemiptera: Aphididae), is an economically important pest of soybean, Glycine max (L.) Merrill, in the United States. Phenological information of A. glycines is limited; specifically, little is known about factors guiding migrating aphids and potential impacts of long distance flights on local population dynamics. Increasing our understanding of A. glycines population dynamics may improve predictions of A. glycines outbreaks and improve management efforts. In 2005 a suction trap network was established in seven Midwest states to monitor the occurrence of alates. By 2006, this network expanded to 10 states and consisted of 42 traps. The goal of the STN was to monitor movement of A. glycines from their overwintering host Rhamnus spp. to soybean in spring, movement among soybean fields during summer, and emigration from soybean to Rhamnus in fall. The objective of this study was to infer movement patterns of A. glycines on a regional scale based on trap captures, and determine the suitability of certain statistical methods for future analyses. Overall, alates were not commonly collected in suction traps until June. The most alates were collected during a 3-wk period in the summer (late July to mid-August), followed by the fall, with a peak capture period during the last 2 wk of September. Alate captures were positively correlated with latitude, a pattern consistent with the distribution of Rhamnus in the United States, suggesting that more southern regions are infested by immigrants from the north.