John N. Ferguson

The paper uses AI to phenotype leaf vein and stomatal traits in maize, finding independent genetic control between these traits.

This study identifies MYB59 as a gene linked to water-use variation in Arabidopsis thaliana, showing its association with temperature rather than precipitation.

C4TUNE predicts photosynthesis kinetic parameters from response curves, enabling efficient simulation and identification of limiting factors in maize genotypes.

This study identifies the polygenic architecture of photoprotection in sorghum through a high-throughput screen of natural genetic variation in non-photochemical quenching traits.

KineticGP improves prediction of leaf photosynthesis traits in maize by integrating genomic data with kinetic models of C4 photosynthesis.

The paper identifies photophysiological variation in wild barley linked to environmental origin through common garden experiments and GWAS.

This study evaluates ML models for predicting maize traits using hyperspectral data across three seasons, revealing trait-specific generalizability limits and offering a robust framework for breeding applications.

This paper improves genomic prediction accuracy by using synthetic traits derived from hyperspectral data, showing higher accuracy than single-trait models for leaf traits in sorghum.

The paper introduces an R package and Shiny app for calculating CSR ecological strategies using plant trait data, supporting multiple models and providing visualizations.

This study shows that reducing stomatal density in sorghum via synthetic EPF expression improves water use efficiency without compromising carbon fixation, but with trade-offs in reproductive development.

This study estimates deleterious mutation burden in sorghum and assesses its impact on agronomic traits, finding moderate genetic variance explanation but limited improvement in breeding accuracy due to linkage.