{
  "id": 16949100,
  "title": "A new physics-informed AI tool aims to predict wildfire spread in real time and assist wildfire response",
  "url": "https://urgent.news/2026/10/28/a-new-physics-informed-ai-tool-aims-to-predict-wildfire-spread-in",
  "topic": "world",
  "section": "World",
  "published": "2026-10-28T20:00:10.000Z",
  "source": {
    "name": "Phys.org",
    "slug": "phys-org",
    "url": "https://phys.org/news/2026-10-physics-ai-tool-aims-wildfire.html"
  },
  "original_language": "en",
  "account": "A new AI system, developed by the NYU Fire Research Group, aims to predict the spread of wildfires in real-time, providing incident commanders with timely and explainable forecasts as conditions change. The digital twin of an active wildfire continuously updates its forecast using data from satellites, weather feeds, terrain, fuel, wildland-urban interface, structures, critical infrastructure, vegetation maps, drones, ground sensors, and crews in the field. The platform displays a U.S. map where users can select a fire location, set the area to forecast, and choose a time horizon up to 12 hours, which the AI then uses to predict the fire's perimeter spread. An AI-enabled plain-language interface allows users to ask questions and receive containment strategies, evacuation plans, and training scenarios, all citing fire department procedures and published research. The system works by combining a physics-informed fire-spread model with an AI layer, solving fundamental equations of fire propagation, combustion, heat transfer, fuel type and properties, wind, slope, weather, and known fire-transition thresholds in real-time, rather than relying solely on historical data. Tests on three active wildfires showed high spatial overlap scores, with the model accurately predicting not just the area, but also the irregular shape of the wildfire's boundary, which is crucial for incident commanders to deploy crews and make evacuation decisions. The researchers are testing the prototype with fire departments and federal agencies before any potential deployment.",
  "summary": "A new AI system that NYU Fire Research Group describes as a digital twin of an active wildfire has, in early testing, shown the ability to forecast how a fire will spread in near real time.",
  "key_points": [
    "NYU Fire Research Group develops AI tool for real-time wildfire prediction",
    "System uses physics-informed fire-spread model and AI layer for accurate forecasts",
    "Tests show high spatial overlap, aiding incident commanders in deployment decisions"
  ],
  "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."
}