A1221
Title: Comparing artificial-intelligence techniques with parametric prediction models for predicting soybean traits
Authors: Reka Howard - University of Nebraska - Lincoln (United States) [presenting]
Susweta Ray - University of Nebraska - Lincoln (United States)
Diego Jarquin - University of Florida (United States)
Abstract: Soybean is a significant source of protein and oil and is also widely used as animal feed. Thus, developing lines that are superior in terms of yield, protein, and oil content is important to feed the ever-growing population. As opposed to high-cost phenotyping, genotyping is both cost and time efficient for breeders, thus enabling the potential success of genomic prediction techniques. A conventional GP method (genomic best linear unbiased predictor [GBLUP]), a kernel method (Gaussian kernel [GK]), an artificial intelligence (AI) method (deep learning [DL]), and a hybrid method that corresponds to the emulation of a DL model using a kernel method (an arc-cosine kernel [AK]) in terms of their prediction accuracies for predicting grain yield, oil, and protein using data from the soybean nested association mapping experiment are compared. The relative performance of the four methods varied with the response variable and whether the model included the genotype-by-environmental interaction (GE) effects or not. The GBLUP consistently showed better performances, whereas GK and AK followed a similar pattern to GBLUP, and DL performed slightly worse than the other three methods in most of the cases; however, this may also be attributed to suboptimal hyperparameters. The DL method performed particularly worse than the other three methods in the presence of the GE effects models.