{
  "id": 11052185,
  "title": "The AI telling farmers when to harvest",
  "url": "https://urgent.news/2026/09/30/the-ai-telling-farmers-when-to-harvest",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-30T23:02:21.000Z",
  "source": {
    "name": "BBC Business",
    "slug": "bbc-business",
    "url": "https://www.bbc.co.uk/news/articles/cgk53dkmyxko?at_medium=RSS&at_campaign=rss"
  },
  "original_language": "en",
  "account": "As the apple harvest began in Washington State last year, the fruit was ready for picking, but the scorching weather proved challenging. Joel Carter of Okanagan Specialty Fruits explained that temperatures reached a sweltering 38C, making outdoor work unsafe. He emphasized the usefulness of artificial intelligence (AI) models that forecast the ideal harvest dates, considering factors like weather. These models are particularly beneficial in determining the duration required to pick the fruit. Carter's company owns over 1,250 acres of apple orchards in Washington, where the apples are grown for slicing and sold to hotels and schools. Though the apples are genetically engineered to resist browning after being cut, planning a harvest remains complex. Emerging tools that count and analyze fruit on trees or vines, and predict ripening, are being developed to aid growers. Okanagan Specialty Fruits is testing cameras from Vivid Machines, mounted on tractors to capture images of apple trees as they pass. These cameras identify various components like buds, flowers, and fruit in the footage. However, the accuracy of forecasts heavily relies on the quality of historical data fed into the system. Carter noted that AI cannot predict specific yield averages for particular apple varieties without tailored data. For other fruits like berries, the harvest window is often much shorter. Raymond Martin, co-founder and COO of FruitCast, a UK-based company providing harvest forecasts to growers, mentioned that FruitCast offers predictions for strawberries, raspberries, blackberries, blueberries, and tomatoes. The firm utilizes drone footage, smartphone measurements, or cameras on farm vehicles to gather data on ripening fruit. Martin emphasized that the system provides more comprehensive insights than seasoned farmers could obtain on their own. FruitCast's forecasts have a high accuracy rate, with errors not exceeding 20% one week out and 17% three weeks ahead. However, the development of AI technology for forecasting fruit ripeness is still in progress, and the industry has not yet reached a fully integrated forecasting ecosystem.",
  "summary": "Will farmers want AI tools to help judge when to pick fruit, or is their own intuition enough?",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 2,
    "also_reported_by": [
      {
        "outlet": "BBC Science",
        "title": "The AI telling farmers when to harvest",
        "url": "https://urgent.news/2026/09/30/the-ai-telling-farmers-when-to-harvest-11052591",
        "published": "2026-09-30T23:02:21.000Z"
      }
    ]
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}