Ensemble-based genomic prediction for maize flowering time reveals novel insights into trait genetic architecture and improves prediction for breeding applications

While many genomic prediction models have been evaluated for their potential to accelerate genetic gain for multiple traits, no individual genomic prediction model has outperformed others across all applications. This result aligns with the implications of the No Free Lunch Theorem, stating that the average performance of individual prediction models becomes equivalent across the state space of diverse prediction scenarios. While no individual prediction model outperforms all others, ensembles of multiple individual genomic prediction models can be applied to leverage their complementary strengths. The Diversity Prediction Theorem provides a framework for investigating the reduction in prediction error through the inclusion of diverse prediction models in the ensemble. We used the EasiGP (Ensemble AnalySis with Interpretable Genomic Prediction) software to investigate the performance of an ensemble approach, targeting flowering time traits measured in two maize nested association mapping datasets. For both datasets, the ensemble-based prediction approach achieved the highest prediction accuracy and lowest prediction error across traits. Multiple genomic regions containing key flowering time-related genes were included as features in the different genomic prediction models with diverse weights among the individual models, demonstrating different views of the trait genetic architecture. The Diversity Prediction Theorem framework suggests that the ensemble combination of such diverse views likely contributed to the improvement of prediction performance by the ensemble-based approach over the individual prediction models. Exploiting the expectations of the Diversity Prediction Theorem, ensemble-based prediction can be applied to overcome some limitations proposed by the No Free Lunch Theorem when applying individual genomic prediction models.