Sort by
Refine Your Search
-
will support genome-wide prediction of variant effects across pathogen populations represented in USDA-ARS culture collections. Simultaneously, protein language models and structural methods will
-
. During this training opportunity, you will have the opportunity to be involved in the development of a training model to predict PRRSV disease outcomes in field-collected samples from pigs infected with
-
influence drape behavior and identify the most predictive traits for evaluating fabric performance. Machine-learning tools may also be used to examine whether certain fiber traits associated with drape have
-
rainfall–runoff models, such as HEC-HMS and the National Water Model, to support more reliable flood frequency analysis and improve flash flood predictions in small watersheds. Under the guidance of a mentor
-
predictive modeling, to identify distinct phenotypes of diabetes and characterize factors associated with disease onset, progression, complications, and mortality. Gain experience analyzing administrative
-
trained on high-quality standards across diverse PFAS classes, and validating prediction accuracy and error rates. These tools will then be applied to real-world agricultural samples to detect previously
-
) to predict crop yields, nutrient uptake and losses; perform model calibration/validation as needed. In addition, you will have an opportunity to use well established crop/farm decision support tools
-
. These insights are important for predicting the ecological success of resistant populations and developing more sustainable, integrated weed management strategies. This project will also involve close
-
scientists to characterize movement patterns of stored-product insects across U.S. agroecosystems and to identify invasion pathways. This includes modeling environmental variables that predict population
-
prediction of agricultural application system performance. You may participate in laboratory, wind tunnel, field, and computational investigations designed to improve understanding of agricultural application