When the heat hit Washington State’s apple orchards last year, farmers faced a dilemma. Artificial intelligence (AI) could offer a solution, by forecasting ideal harvest dates based on weather conditions. Joel Carter of Okanagan Specialty Fruits, with 1,250 acres of genetically engineered apple orchards, sees AI as a valuable tool. However, the accuracy of these models depends on the quality of historical data.

Other tools aim to count and analyse fruit on the tree or vine, predicting ripening times. For instance, cameras from Vivid Machines mounted on tractors can identify buds, flowers or fruit. Yet, these systems require bespoke data and can be expensive.

Strawberry growers, like Raymond Martin of FruitCast, offer forecasts for various fruits. In the UK, hot weather and drought have stressed many fruit plants, putting them into thermal dormancy and slowing production. FruitCast’s models account for weather and irrigation conditions, with 90% accuracy one week out.

Researchers are exploring new ways of analysing fruit, such as using millimetre waves, high-frequency radio waves, to detect ripeness. This technology could benefit both farmers and consumers, but its adoption remains complex. Growers need confidence in the technology’s effectiveness.

The journey towards a fully integrated forecasting ecosystem is ongoing. While some growers are keen to try new tech, many wonder if it’s worth the investment. As AI continues to evolve, it will be interesting to see how it reshapes the agricultural landscape.