Rapid assessment of crop damage is essential for successful management of insect pest outbreaks. In this study, we investigated the use of an unmanned aircraft system (UAS) and image analyses to assess an outbreak of the beet armyworm, Spodoptera exigua (Hübner) (Lepidoptera: Noctuidae), that occurred in soybean fields in South Korea. A rotary-wing UAS was deployed to obtain a series of aerial images over 31 soybean blocks. The images were stitched together to generate composite imagery, followed by image analyses to quantify soybean defoliation. An economic analysis was conducted to compare the cost of the aerial survey with that of a conventional ground survey. The results showed that the aerial survey precisely estimated the defoliation compared to the ground survey, with an estimated defoliation of 78.3% and a range of 22.4–99.8% in the 31 blocks. Moreover, the aerial survey followed by image analyses was found to be more economical than the conventional ground survey when the number of target soybean blocks subject to the survey was more than 15 blocks. Our study clearly demonstrated the effectiveness of using an autonomous UAS and image analysis to conduct a low-cost aerial survey of soybean damage caused by S. exigua outbreaks, which can inform decision-making for S. exigua management.

Tree of heaven (Ailanthus altissima) is a highly invasive tree species in the USA and the preferred host of an invasive insect, the spotted lanternfly (Lycorma delicatula). Currently, pest managers rely solely on ground surveys for detecting both A. altissima and spotted lanternflies. This study aimed to develop efficient tools for A. altissima detection using drones equipped with optical sensors. Aerial surveys were conducted to determine the optimal season, sensor type, and flight altitudes for A. altissima detection. The results revealed that A. altissima can be detected during different seasons and at specific flight heights. Male inflorescences were identifiable using an RGB sensor in the spring at <40 m, seed clusters were identifiable in summer and fall at <25 m using an RGB sensor, and remnant seed clusters were identifiable in the winter at <20 m using RGB and thermal sensors. Combining all seasonal data allowed for the identification of both male and female A. altissima. This study suggests that employing drones with optical sensors can provide a near real-time and efficient method for A. altissima detection. Such a tool has the potential to aid in the development of effective strategies for monitoring spotted lanternflies and managing A. altissima.

Pollinators play vital roles to the environment, biodiversity conservation, food security and several dimensions of global sustainable development. Honey bee is an important pollinator globally but has been exposed to increasing threats from diseases, pesticides and biotic stresses. This review paper highlights the role of honey bees as pollinators, addresses threats which influence decline of honey bees and assess pesticidal risk toxicity on non-target organisms. Decline of honey bee population is caused by several factors including habitat fragmentation, pesticidal toxicity, colony collapse disorder and climate change. Pesticidal residue and toxicity has an adverse effect which results in honey bee population decline, disturb foraging and contamination of bee products. Residues of agricultural pesticides like pyrethroid and neonicotinoid pose a serious threat on honey bee health further reducing agricultural production and diversity. Pesticidal risk assessments are carried out to study effects of pesticides on pollinators with an aim to provide measures to safeguard their abundance, diversity and health. Sustainable agriculture, effective policy and proper management can decrease pollinators' risk by helping to diversify the agriculture for pollen and nectars with reduced usage of pesticides and proper management.

Lythrum salicaria (purple loosestrife) is an invasive species that displaces native wetland flora in the USA. The detection and manual release of biological control agents for L. salicaria is challenging because L. salicaria inhabits many inaccessible areas. This study was conducted to develop aerial systems for the detection of L. salicaria and the release of its natural enemy, Galerucella calmariensis (Coleoptera: Chrysomelidae). We determined the optimal sensors and flight height for the aerial detection of L. salicaria and designed an aerial deployment method for G. calmariensis. Drone-based aerial surveys were conducted at various flight heights utilizing RGB, multispectral, and thermal sensors. We also developed an insect container (i.e., bug ball) for the aerial deployment of G. calmariensis. Our findings indicated that L. salicaria flowers were detectable with an RGB sensor at flight heights ≤ 15 m above the canopy. The post-release mortality and feeding efficiency of G. calmariensis did not significantly differ from the control group (non-aerial release), indicating the feasibility of the targeted release of G. calmariensis. This innovative study establishes a critical foundation for the future development of sophisticated aerial systems designed for the automated detection of invasive plants and the precise release of biological control agents, significantly advancing ecological management and conservation efforts.

Invasive knotweeds are rhizomatous and herbaceous perennial plants that pose significant ecological threats due to their aggressive growth and ability to outcompete native plants. Although detecting and identifying knotweeds is crucial for effective management, current ground-based survey methods are labor-intensive and limited to cover large and hard-to-access areas. This study was conducted to determine the optimum flight height of drones for aerial detection of knotweeds at different phenological stages and to develop automated detection of knotweeds on aerial images using the state-of-the-art Swin Transformer. The results of this study found that, at the vegetative stage, Japanese knotweed and giant knotweed were detectable at ≤35 m and ≤25 m, respectively, above the canopy using an RGB sensor. The flowers of the knotweeds were detectable at ≤20 m. Thermal and multispectral sensors were not able to detect any knotweed species. Swin Transformer achieved higher precision, recall, and accuracy in knotweed detection on aerial images acquired with drones and RGB sensors than conventional convolutional neural networks (CNNs). This study demonstrated the use of drones, sensors, and deep learning in revolutionizing invasive knotweed detection.

The Mexican bean beetle, Epilachna varivestis Mulsant (Coleoptera: Coccinellidae), is a key pest of beans, and early detection of bean damage is crucial for the timely management of E. varivestis. This study was conducted to assess the feasibility of using drones and optical sensors to quantify the damage to field beans caused by E. varivestis. A total of 14 bean plots with various levels of defoliation were surveyed aerially with drones equipped with red-blue-green (RGB), multispectral, and thermal sensors at 2 to 20 m above the canopy of bean plots. Ground-validation sampling included harvesting entire bean plots and photographing individual leaves. Image analyses were used to quantify the amount of defoliation by E. varivestis feeding on both aerial images and ground-validation photos. Linear regression analysis was used to determine the relationship of bean defoliation by E. varivestis measured on aerial images with that found by the ground validation. The results of this study showed a significant positive relationship between bean damages assessed by ground validation and those by using RGB images and a significant negative relationship between the actual amount of bean defoliation and Normalized Difference Vegetation Index values. Thermal signatures associated with bean defoliation were not detected. Spatial analyses using geostatistics revealed the spatial dependency of bean defoliation by E. varivestis. These results suggest the potential use of RGB and multispectral sensors at flight altitudes of 2 to 6 m above the canopy for early detection and site-specific management of E. varivestis, thereby enhancing management efficiency.