Michaela Jung

This study evaluates genomic and phenomic prediction methods for apple breeding, showing that expanding training sets improves predictive ability but leave-one-family-out validation reduces it, while phenomic data are less effective.

This study applies statistical and deep learning models to multi-environmental genomic prediction in apple, showing improved predictive ability for certain traits.

This study examines the genetic architecture and genomic prediction accuracy of 30 apple quantitative traits across six European locations, identifying novel associations and demonstrating the impact of genotype by environment interactions.