Robustly enhancing crop genomic prediction accuracy through ensemble learning and iterative optimization

With climate change and global population growth, accelerating the breeding of superior crop varieties is essential for food security. Genomic prediction, which uses genome-wide genetic markers to predict crop traits, plays an important role in intelligent crop breeding. However, existing methods often lack stable and accurate performance across crops and traits. Here, we propose GEG2P, a genetic algorithm-based ensemble learning method for genotype-to-phenotype prediction, integrates 20 base learners, dynamically selects their combinations through an iterative optimization strategy, and optimizes their weights using the genetic algorithm. Compared with the best-performing single base learners, GEG2P improves prediction accuracy by 4.02% on average across maize, wheat, rice, chickpea, and soybean. We use SHAP to quantify the contribution of SNPs to phenotype prediction and find that SNPs with large effects captured by different base learners are functionally complementary. This study provides a robust and accurate genomic prediction method for crop breeding. Existing genomic prediction methods often lack stability and accuracy across crops and traits. Here, the authors report a genetic algorithm-based ensemble learning method for genotype-to-phenotype prediction (GEG2P) by integrating 20 base learners and show its application in improving trait prediction accuracy in multiple crops.