{
  "id": 6329354,
  "title": "Physics-based AI unlocks first global predictions of carbon cycling in ocean sediments",
  "url": "https://urgent.news/2026/09/08/physics-based-ai-unlocks-first-global-predictions-of-carbon-cycling",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-08T20:40:03.000Z",
  "source": {
    "name": "Phys.org",
    "slug": "phys-org",
    "url": "https://phys.org/news/2026-09-physics-based-ai-global-carbon.html"
  },
  "original_language": "en",
  "account": "Researchers at The University of Manchester have devised a novel physics-based artificial intelligence method that enables global-scale predictions of how dissolved organic carbon moves between marine sediments and seawater. This breakthrough, led by Dr. Peyman Babakhani and Dr. Majid Sedighi, overturns previous limitations on quantifying this vital component of the planet's carbon cycle. Traditional complex models were either too computationally intensive or unstable for planetary-scale application. The team trained AI \"emulators\" to replicate the behavior of existing mechanistic models, allowing them to accurately predict dissolved organic carbon behavior at a scale previously unattainable. Key findings reveal that nearly 11% of seafloor particulate organic carbon returns to the ocean as dissolved carbon, while 24% binds to minerals. Importantly, roughly half of the organic carbon in the upper meter of sediments originates from dissolved carbon that has bonded to minerals. The study confirms that simpler neural network architectures yielded the most accurate predictions, providing empirical support for the principle of parsimony. This AI-driven framework offers a fast, scalable, and precise means to represent sediment carbon processes, paving the way for integrating sedimentary carbon dynamics into global climate models and evaluating potential ocean-based climate change mitigation strategies.",
  "summary": "Researchers at The University of Manchester have developed a new physics-based artificial intelligence approach that, for the first time, enables accurate global-scale predictions of how dissolved organic carbon moves between seawater and marine sediments, a crucial but previously unquantifiable component of the planet's carbon cycle.",
  "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."
}