Hugo Gangloff

This paper evaluates deep learning's ability to predict genetic values in crossbred populations by capturing heterosis, finding it improves performance when heterosis is present.

The paper reports on a competition to predict maize yield using genetic and environmental data, showing that diverse modeling approaches can achieve good results.

This paper introduces a hybrid DLGBLUP model that integrates deep learning with GBLUP to improve prediction accuracy by capturing nonlinear genetic relationships between traits.