Graduate Student Li Meinhold Presents Transformer-Based Genomic Prediction in Wheat

Graduate student Li Meinhold presented his research on Transformer-based genomic prediction at the 2026 National Association of Plant Breeders (NAPB) Annual Meeting, held June 15–18 in College Station, Texas. Li developed a Transformer-based model integrating genotypic and environmental data to predict wheat grain yield, heading date, and plant height. Using two years of field data, the model outperformed conventional genomic prediction methods.

Li Meinhold Advances AI Tools for Wheat Breeding

At the Bay Area Plant Hub meeting hosted by University of California, Berkeley, Li Mainhold, a PhD student from the Small Grains Crop Breeding Program presented new research on using artificial intelligence to improve crop breeding.

Li Meinhold is developing a prediction model using WheatCAP data from public wheat breeding programs. The model combines genomic data—about 500,000 DNA markers from ~8,400 wheat lines—with 40 environmental variables such as weather and location. 

Stronger Wheat for Real-World Conditions

We are excited to start a new project funded by USDA-NIFA to develop better wheat varieties for the future. In this project, we are testing new plant height genes (PLATZ1 and AP2L2) to replace the older ones (Rht-B1b, Rht-D1b) used since the Green Revolution. We will evaluate whether these new genes can help wheat grow better under tough conditions like drought, deep planting, and low nitrogen. Our goal is to develop varieties that produce high yields while staying resilient in changing environments.

Collaboration Advancing Wheat Innovation at UC Davis

The UC Davis Wheat Breeding Program continues its strong tradition of innovation in wheat genetics and breeding. Our team is developing wheat varieties for California producers using an integrated “package” approach that combines disease resistance, yield performance, grain quality, and nutritional traits.