Fusarium head blight (FHB) is a disease of small grains caused by the fungus Fusarium graminearum. In this study, we explored the use of hyperspectral imaging (HSI) to evaluate the damage caused by FHB in wheat kernels. We evaluated the use of HSI for disease classification and correlated the damage with the mycotoxin deoxynivalenol (DON) content. Computational analyses were carried out to determine which machine learning methods had the best accuracy to classify different levels of damage in wheat kernel samples. The classes of samples were based on the DON content obtained from Gas Chromatography–Mass Spectrometry (GC-MS). We found that G-Boost, an ensemble method, showed the best performance with 97% accuracy in classifying wheat kernels into different severity levels. Mask R-CNN, an instance segmentation method, was used to segment the wheat kernels from HSI data. The regions of interest (ROIs) obtained from Mask R-CNN achieved a high mAP of 0.97. The results from Mask R-CNN, when combined with the classification method, were able to correlate HSI data with the DON concentration in small grains with an R² of 0.75. Our results show the potential of HSI to quantify DON in wheat kernels in commercial settings such as elevators or mills.

Peanut (Arachis hypogaea L.) is an important food crop for the U.S. and the world. The Virginia-Carolina (VC) region (Virginia, North Carolina, and South Carolina) is an important peanut-growing region of the U.S and is affected by numerous biotic and abiotic stresses. Identification of stress-resistant germplasm, along with improved phenotyping methods, are important steps toward developing improved cultivars. Our objective in 2017 and 2018 was to assess the U.S. mini-core collection for desirable traits, a valuable source for resistant germplasm under limited water conditions. Accessions were evaluated using traditional and high-throughput phenotyping (HTP) techniques, and the suitability of HTP methods as indirect selection tools was assessed. Traditional phenotyping methods included stand count, plant height, lateral branch growth, normalized difference vegetation index (NDVI), canopy temperature depression (CTD), leaf wilting, fungal and viral disease, thrips rating, post-digging in-shell sprouting, and pod yield. The HTP method included 48 aerial vegetation indices (VIs), which were derived using red, blue, green, and near-infrared reflectance; color space indices were collected using an octocopter drone at the same time, with traditional phenotyping. Both phenotypings were done 10 times between 4 and 16 weeks after planting. Accessions had yields comparable to high yielding checks. Correlation coefficients up to 0.8 were identified for several Vis, with yield indicating their suitability for indirect phenotyping. Broad-sense heritability (H²) was further calculated to assess the suitability of particular VIs to enable genetic gains. VIs could be used successfully as surrogates for the physiological and agronomic trait selection in peanuts. Further, this study indicates that UAV-based sensors have potential for measuring physiologic and agronomic characteristics measured for peanut breeding, variable rate input application, real time decision making, and precision agriculture applications.

Large-seeded virginia market type peanut (Arachis hypogaea L.) cultivars are common in Virginia and North Carolina, but cost more to plant than runner market type peanut cultivars when the goal is to establish the same plant population. Decreasing seeding density could help growers to reduce production costs, as long as thinner stands do not negatively impact yield and economic return. Selecting the optimum digging time is a decision that could significantly influence growers' production and economics. Field experiments were conducted in Virginia and North Carolina at four site-year environments in 2016 and 2017 to examine the influence of seeding density (109, 143, 180, and 200 thousand seeds/ha) and digging date (130, 140, and 150 days after planting [DAP]) on virginia type peanut cultivar (Bailey, Sullivan, Wynne) performance. Regardless of cultivar and digging date, the greatest pod yield (5930 kg/ha) was achieved from the 200 thousand seeds/ha density, but the 143 thousand seeds/ha density had the highest economic return ($2990/ha). At three of the four site-years, the 140 DAP digging date, i.e. 1400 to 1600 C growing degree days (GDD), produced the greatest pod yield (5470 kg/ha) and had the highest economic return ($2750/ha). While individual site-years should be monitored for digging date, growers should be prepared to dig the currently available cultivars from 1400 to no more than 1600 C accumulated GDD.

Cyberbiosecurity and workforce development in agriculture and the life sciences (ALS) is a growing area of need in the curriculum in higher education. Students that pursue majors related to ALS often do not include training in cyber-related concepts or expose the ‘hidden curriculum’ of seeking internships and jobs. Exposing students through workforce development training and hands-on engagement with industry professionals can provide learning opportunities to bridge the two and is an area of growth and demand as the workforce evolves. The objectives of this work were 1) to learn key concepts in cybersecurity, including data security, visualization, and analysis, to name a few, through class activities and engagement with professional partners and 2) to understand what knowledge students gained from participating in the course could transfer over for when they enter the workforce. Three themes emerged from the study where students, through direct engagement with industry partners, gained more insight about the industry applicable to their studies; they established work environment expectations for entering internships and official job placements and established ways in which the workforce development training informed their future careers.