Table 2 Sample sizes output from the APY algorithm. Sample sizes and respective percentages (%) were obtained and calculated for each dataset (HEL and USP), kernel (GET and GWT), and optimized training set scenario (OTS 1, OTS 2, and OTS 3). GET: genotype × environment × trait; GWT: genotype × environmental covariates × trait. Percentages were obtained based on dataset size

From: Enviromic-based kernels may optimize resource allocation with multi-trait multi-environment genomic prediction for tropical Maize