Choosing the right moment to harvest can be a make-or-break decision for farmers. When the first day of the apple harvest rolled around in Washington State last year, the fruit was ripe and the pickers were ready – but the weather had other ideas. Joel Carter at Okanagan Specialty Fruits recalls, "It was like 38C… it's not safe for people to work in that heat. We had to stop at 10 o'clock in the morning."
He emphasizes the need for artificial intelligence (AI) models that forecast ideal harvest dates, taking into account the weather. "You need to know more than just when your fruit is going to be ripe. How long do you have to pick it? That's where these models are really helpful."
The Role of Technology in Harvesting
Carter's company manages over 1,250 acres of apple orchards in Washington, focusing on fruit for sliced apple portions, often sold to hotels and schools. The firm is investing in technology to maximize productivity, even genetically engineering apples to prevent browning once cut.
Planning a harvest is tricky, especially as prices for fruit, particularly high-value berries like strawberries and blueberries, can fluctuate wildly. Getting the harvest date wrong can lead to unnecessary costs, such as booking seasonal workers when they are not needed, and missing out on significant profits.
Okanagan Specialty Fruits is currently experimenting with cameras from Vivid Machines, a Canadian firm. These cameras are mounted on tractors, capturing imagery of the apple trees as the tractor moves by. AI then identifies buds, flowers, or fruit in the footage. Carter states, "Right now, Vivid is telling us crop estimates and harvest dates," noting the system's ability to detect tiny flower buds that are hard to see with the naked eye.
However, Carter adds that the accuracy of forecasts depends heavily on the quality of historical data fed into the system. "This isn't something where an AI can scrape the internet and figure out what's the average [yield] for Granny Smith. It's going to be bespoke to your farm."
