Advanced Tools for Apple Growers: Optimizing Crop Load

To maximize an orchard’s profits, one of the most important measures an apple grower can take is controlling the crop load—the number of apples that a tree produces. Allowing more fruits per tree increases yield but results in smaller apples with lower market value. By restricting the crop load, the grower can harvest larger apples; however, reducing the yield too much offsets the economic advantages of bringing larger fruits to market. Achieving the perfect balance has large economic benefits. Unfortunately, current methods for controlling crop load—such as manual pruning and chemical thinning to reduce the number of blossoms on a tree—are imprecise and extremely expensive.

Terence L. Robinson, School of Integrative Plant Science, Horticulture, is leading a multi-institutional team, including experts in plant science, economics, and engineering, to develop computer-assisted, easy-to-use methods for optimizing crop load. This research will allow apple growers to accurately calculate a target fruit number for each tree and then quickly count flower buds and fruitlets using machine vision and geo-referenced maps. Growers could use these data to guide the severity of pruning and thinning over the course of the growing season. This project will also advance research to develop automated vehicles that can adjust crop load using robotics and computer vision.

Project partners include Moog, Inc., Washington State University, Penn State University, University of Massachusetts, North Carolina State University, Virginia Tech University, and the Washington Tree Fruit Research Commission.

NIFA Award Number: 2020-51181-32197

Cornell Researchers

Funding Received

$4.8 Million spanning 4 years

Sponsored by