{
  "id": 1509900,
  "title": "AI learns to spot tomato diseases using nearly 9,000 field images",
  "url": "https://urgent.news/2026/08/17/ai-learns-to-spot-tomato-diseases-using-nearly-9-000-field-images",
  "topic": "ai",
  "section": "AI",
  "published": "2026-08-17T16:00:07.000Z",
  "source": {
    "name": "Phys.org",
    "slug": "phys-org",
    "url": "https://phys.org/news/2026-08-ai-tomato-diseases-field-images.html"
  },
  "original_language": "en",
  "account": "A new AI-driven technology, developed by researchers from Charles Darwin University and the University of Peradeniya, has the potential to revolutionize tomato disease detection. The SLIF-Tomato dataset, which contains over 8,900 high-quality images of tomato leaves, is the first in-field dataset to include detailed class labels and bounding box annotations. These images were collected under various real-world conditions to ensure the model could learn to identify diseases accurately in diverse environments. The dataset contains eight classes, ranging from healthy leaves to seven different diseases, including bacterial spot, early blight, mosaic, powdery mildew, septoria, wilt, and late blight. The key to the AI model's success lies in its ability to prioritize disease-relevant features over background clutter, enabling it to achieve an accuracy rate of over 99% in disease detection. This breakthrough technology has the potential to significantly reduce crop losses, minimize the use of harmful chemicals, and promote sustainable farming practices. By enabling rapid and accurate disease identification using lightweight models, the AI system can run efficiently on resource-constrained devices such as mobile phones, making it accessible to farmers in remote areas. The researchers aim to expand the dataset to include a broader range of crops and diseases, ultimately contributing to the development of affordable and sustainable agricultural solutions.",
  "summary": "A breakthrough in AI-driven crop disease detection is set to reduce harvest losses and chemical-related health risks, thanks to a first-of-its-kind tomato leaf dataset comprising almost 9,000 images.",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "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."
}