The AI telling farmers when to harvest
Will farmers want AI tools to help judge when to pick fruit, or is their own intuition enough?
In Washington State, apple harvest in 2021 began as planned with ripe fruit and eager pickers, but extreme heat forced the stoppage at 10 a.m. Joel Carter at Okanagan Specialty Fruits highlighted the usefulness of AI models that forecast ideal harvest dates considering weather conditions. These models factor in not just when fruit becomes ripe, but also how long it takes to pick it.
Okanagan Specialty Fruits has over 1,250 acres of apple orchards in Washington, growing fruit for sliced apple portions sold to hotels and schools. The company invests in technology to maximize productivity, even though apples are genetically engineered to resist browning when cut. However, planning a harvest is complex. New tools counting and analyzing fruit on trees or vines, and predicting ripening, are emerging.
This is crucial as fruit prices can fluctuate significantly. Okanagan Specialty Fruits is testing Vivid Machines cameras mounted on tractors to capture images of apple trees. The AI identifies fruit in the footage, providing crop estimates and harvest dates. The accuracy of these forecasts depends on the quality of historical data fed into the system.
Raymond Martin, co-founder and chief operating officer of UK company FruitCast, offers harvest forecasts to growers for strawberries, raspberries, blueberries, and tomatoes. FruitCast's system analyzes footage from drones, smartphones, or mounted cameras on farm vehicles. This year, hot weather and drought in the UK stressed fruit plants, slowing production.
FruitCast's forecasts have been accurate within 10% one week out and 17% three weeks out. However, experienced farmers often know when their fruit will be ripe, but FruitCast can provide insights across larger farms with varied growing areas. Researchers are exploring millimetre wave technology to detect fruit ripeness, potentially aiding forecasts.
Despite interest from some growers, many remain cautious about investing in new technology, emphasizing the need for confidence in its effectiveness.
Written by urgent.news from BBC Science's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
This story
This is one outlet's version. Read the fullest account.
- The AI telling farmers when to harvest bbc.co.uk
