** AWARDS ISSUED PRIOR TO JANUARY 20, 2025, WERE FUNDED UNDER PREVIOUS ADMINISTRATIONS AND MAY NOT REFLECT THE PRIORITIES AND POLICIES OF THE CURRENT ADMINISTRATION.** THIS PROJECT AIMS TO DEVELOP A SELECTION METHOD THAT SYNERGISTICALLY COMBINES HIGH-THROUGHPUT PHENOTYPING (HTP) AND GENOMIC SELECTION (GS) TO ACCELERATE YIELD IMPROVEMENT IN PUBLIC SMALL GRAINS BREEDING PROGRAMS WITH MODEST BUDGETS.OUR PROPOSED METHOD, 'PHENOMIC ASSISTED GENOMIC SELECTION' (PAGS), USES HTP TO IMPUTE YIELD PHENOTYPIC DATA ON A PROPORTION OF RESEARCH PLOTS. BOTH IMPUTED AND TRUE YIELD DATA ARE SUBSEQUENTLY USED FOR GS MODEL TRAINING. PAGS ENABLES BREEDERS TO GENERATE LARGE GS MODEL TRAINING DATASET SETS REQUIRED FOR SUCCESSFUL GS AMONG UNTESTED BREEDING CANDIDATES, UNLOCKING THE POTENTIAL OF GS TO SHORTEN BREEDING CYCLES AND ACCELERATE RATES OF GENETIC GAIN.TO DEVELOP PAGS, WE WILL GENERATE AND ANALYZE YIELD AND HTP DATA TO TEST THE LIMITS OF GRAIN YIELD IMPUTATION USING HTP DATA AND IDENTIFY THE BEST STATISTICAL OR MACHINE LEARNING MODEL FOR THIS PURPOSE. NEXT, WE WILL CONDUCT VALIDATION STUDIES TO EVALUATE THE EFFECT OF INCLUDING IMPUTED YIELD DATA ON GS ACCURACY UNDER DIFFERENT SCENARIOS. LASTLY, WE WILL USE STOCHASTIC SIMULATIONS TO EVALUATE THE COSTS AND BENEFITS OF PAGS TO ULTIMATELY EVALUATE ITS MERIT COMPARED TO ALTERNATIVE STRATEGIES.