All Times ET
Virtual
Optimizing Time-Window When Integrating Weather Information in Genomic Prediction (305344)
*Vamsi Manthena, University of Nebraska, LincolnKeywords: Genomic prediction, plant breeding, high-dimensionality, optimization
One of the main goals of plant breeders is to develop improved cultivars in a sustainable way. To aid their objective, they collect multiple data types such as weather information, high-throughput images, and information on secondary traits that are associated with the trait of interest (e.g.: grain yield). The collected data can help breeders select material for advancements, and a common technique to use for that is genomic selection. However, in the face of changing climate conditions, it is important to consider the genotype-by-environmental interaction that can significantly impact the performance of the prediction models. Thus, there is a need to develop methods able to effectively combine weather information with genotype data and better predict the performance of varieties. In this work, we propose a method to optimize the time-window in the growing season from which weather variables are included and integrate the weather and genomic data to predict primary traits.