Data-driven decentralized breeding increases prediction accuracy in a challenging crop production environment

de Sousa et al. present a data-driven decentralized crop breeding approach called 3D-breeding that is geared toward improving yields for smallholder farmers. 3D-breeding is applied to a case study of durum wheat in Ethiopia, which demonstrates higher prediction accuracies for grain yield than the existing model. Crop breeding must embrace the broad diversity of smallholder agricultural systems to ensure food security to the hundreds of millions of people living in challenging production environments. This need can be addressed by combining genomics, farmers' knowledge, and environmental analysis into a data-driven decentralized approach (3D-breeding). We tested this idea as a proof-of-concept by comparing a durum wheat (Triticum durum Desf.) decentralized trial distributed as incomplete blocks in 1,165 farmer-managed fields across the Ethiopian highlands with a benchmark representing genomic prediction applied to conventional breeding. We found that 3D-breeding could double the prediction accuracy of the benchmark. 3D-breeding could identify genotypes with enhanced local adaptation providing superior productive performance across seasons. We propose this decentralized approach to leverage the diversity in farmer fields and complement conventional plant breeding to enhance local adaptation in challenging crop production environments.

Automated summary

The study introduces a data-driven decentralized crop breeding approach called 3D-breeding, which aims to improve yields for smallholder farmers and demonstrates higher prediction accuracies for grain yield in a durum wheat case study in Ethiopia. 3D-breeding doubles the prediction accuracy of the benchmark, identifying genotypes with enhanced local adaptation for superior productive performance across seasons. This decentralized approach leverages the diversity in farmer fields to enhance local adaptation in challenging crop production environments.