AI-ENGAGE: Harnessing AI for Precision Genomic Selection Models in Wheat

About This Grant

Wheat is the world’s most traded crop and plays a central role in feeding the world, providing nearly 20% of all calories consumed by humans and serving as the primary source of plant-based protein for billions. Securing a stable wheat supply is essential, especially as extreme weather events like drought continually threaten food security and economic stability. This project harnesses artificial intelligence to transform wheat breeding, enabling faster development of drought-tolerant varieties. By advancing these innovations, this research directly contributes to securing food supplies, benefiting farmers to adapt to environmental challenges. This project addresses the challenge of improving wheat breeding by overcoming limitations in traditional methods, which struggle with the complex interactions between wheat genetics and diverse field environments, especially when analyzing the vast datasets now available from genome sequencing, weather stations, and high-throughput phenotyping technologies such as drone imaging. The project leverages feature-embedded neural networks to overcome these limitations, integrating genetic markers, environmental factors, and plant growth measurements to predict wheat performance. A core set of 400 wheat lines are being genotyped and evaluated over three years in two locations, under both normal and drought conditions. Environmental data is collected in parallel to create environmental indices and response parameters. The trained neural networks incorporate sequence variants and environmental indices in their first layer, embedding features representing quantitative trait loci identified via genome wide association studies in a second layer. The resulting tools will be made available as open-source software, enabling scientists worldwide to apply these innovations in their own breeding programs. In addition, the project includes training initiatives designed to equip the next generation of agricultural scientists with the skills needed to develop improved wheat varieties using cutting-edge technologies. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.