Hugues de Verdal

This paper proposes using singular value decomposition in near infrared spectroscopy pre-processing for phenomic prediction, showing it performs as well as classical chemometrics methods with less parameter optimization.

This study evaluates phenomic prediction in sorghum breeding, showing it can compete with genomic prediction and is less affected by population structure, though trait-dependent and requiring further optimization.

This paper evaluates phenomic prediction (PP) accuracy in rice breeding, finding that multi-environment data improve PP performance, making it comparable to genomic prediction (GP) when all genotypes have NIRS measurements.