Geostatistical analysis of the attractive distance of two different sizes of yellow sticky traps for greenhouse whitefly, Trialeurodes vaporariorum (Westwood) (Homoptera: Aleyrodidae), in cherry tomato greenhouses

The Leaf Color and Trichome Density Influence the Whitefly Infestation in Different Cassava Cultivars

The whitefly species Bemisia tuberculata and Aleurotrixus aepim (Hemiptera: Aleyrodidae) are considered important cassava (Manihot esculenta) pests. Leaf color and other morphological characteristics can influence the pest's interactions with the host plants. Thus, this study aimed to identify the relationship between whitefly occurrence and trichome density and leaf color in different cassava cultivars. The study was conducted in the field during the 2014/2015 and 2016/2017 crop seasons. The whitefly occurrence was surveyed in the cultivars, IAPAR 19, IPR Upira, IPR União, IAC 576-70, IAC 14, IAC 90, Catarina Branca, Santa Helena and Baianinha. The whitefly nymph quantification was correlated with non-glandular trichome density, luminosity (L*) and chroma (a* and b*) of the cassava leaves. IAPAR 19 and IAC 14 were less infested by whitefly nymphs when contrasted with IPR União, IPR Upira and Baianinha, which were the most infested. The lowest B. tuberculata infestations were correlated with lesser trichome density, highest light reflection and highest chroma in the sprout and the plant's superior third portion leaves. Low A. aepim infestation in both crop seasons made it impossible to verify its correlation with the studied cassava plant characteristics. The cultivars IAPAR 19 and IAC 14 could contribute towards B. tuberculata management in regions with a history of whitefly infestation.

Deep learning-based system development for black pine bast scale detection

The prevention of the loss of agricultural resources caused by pests is an important issue. Advances are being made in technologies, but current farm management methods and equipment have not yet met the level required for precise pest control, and most rely on manual management by professional workers. Hence, a pest detection system based on deep learning was developed for the automatic pest density measurement. In the proposed system, an image capture device for pheromone traps was developed to solve nonuniform shooting distance and the reflection of the outer vinyl of the trap while capturing the images. Since the black pine bast scale pest is small, pheromone traps are captured as several subimages and they are used for training the deep learning model. Finally, they are integrated by an image stitching algorithm to form an entire trap image. These processes are managed with the developed smartphone application. The deep learning model detects the pests in the image. The experimental results indicate that the model achieves an F1 score of 0.90 and mAP of 94.7% and suggest that a deep learning model based on object detection can be used for quick and automatic detection of pests attracted to pheromone traps.

Within-field spatial distribution of stink bug (Hemiptera: Pentatomidae)-induced boll injury in commercial cotton fields of the southeastern United States

Spatial distribution of boll injury caused by stink bugs to developing cotton (Gossypium hirsutum L.) bolls was studied in five commercial fields (≍22 ha each) in 2011 and 2012 to understand variability in boll injury dynamics within fields. Cotton bolls and stink bugs were sampled weekly from a georeferenced grid of sampling points (one sample per 0.40 ha) in each field, but no samples were taken within 30 m of field edges. The inverse distance weighted interpolation, variogram analysis, and Moran's I were used to describe spatial variability of boll damage within the fields. Boll injury was found to be spatially associated at distances ranging from ≍75 to 275 m with an average distance ≍150 m. An exponential variogram model was selected as the best fitting model to describe the spatial association in four of the five fields. Moran's I indicated that spatial association was significant in three of the five fields. The spread of boll injury from stink bugs was gradual in most fields and always exceeded the treatment threshold during the fourth or fifth week of bloom. Capture of stink bugs using a sweep net was inefficient, strongly suggesting that quantifying boll injury is a better sampling method and predictor of stink bug activity when sampling all but the edges of the field. These data suggest that scouts need to sample boll injury from sample locations separated by at least 150 m to assure independence in the central part of large fields. Second, future researchers who plan to use parametric statistical methods could use a 150-m grid, as opposed to a denser grid that would require greater time and effort.