This federal Project Grant award from the National Science Foundation's Office of International Science and Engineering (CFDA 47.079) provides $400,000 over 3 years to Cornell University to develop advanced imaging, machine learning, and multi-omic prediction methods for evaluating and improving yield and quality traits in three important horticultural crops: tomato, onion, and strawberry.
The project aims to create faster, more precise ways to measure traits like fruit count, size, and shape using both RGB and spectral imaging from handheld and autonomous devices. It will also investigate models incorporating genomic, transcriptomic, and hyperspectral data to predict complex horticultural traits. Additionally, the research team will combine 3D plant modeling and gene expression data to better understand and forecast growth in strawberry plants. This international collaboration also includes partners from India, Japan, and Australia to support the development of productive, high-quality crop varieties that benefit both growers and consumers.