home.social

#climateai — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #climateai, aggregated by home.social.

  1. Climate-scale AI cannot be governed under vendor sovereignty. No single jurisdiction will accept another's audit log as authoritative.

    Polycentric architecture under a shared OAR canonical schema is the only structure that scales.

    Sovereign Futures, Vol VI.

    mickai.co.uk/articles/planetar

    #SovereignAI #ClimateAI #Polycentric

  2. 🌍 AI is transforming climate modelling!

    Catch us at #EGU26 presenting work on AI climate models, hybrid approaches & scaling

    ⚡️ Don’t miss: Beucler, Grundner, Ivanov, Camps-Valls + more!

    #AI4PEX #AI4Earth #ClimateAI

  3. AI maps deep-sea coral reefs from archived underwater footage: A new project uses AI to analyze thousands of hours of seafloor video, producing the first comprehensive maps of vulnerable marine ecosystems across the Atlantic basin. theconversation.com/how-ai-cou #AIagent #AI #GenAI #ClimateAI

  4. 🌍 AI is transforming climate research!

    Catch us at #EGU25 presenting cutting-edge work on applying #MachineLearning, hybrid models, and causal discovery in climate research.

    ⚡️ Don’t miss: Camps-Valls, Reid, Ouala, Beucler + more!

    #AI4Climate #ML4Science #EGU25 #ClimateAI

  5. 🌍 AI is transforming climate research!

    Catch us at #EGU25 presenting cutting-edge work on applying #MachineLearning, hybrid models, and causal discovery in climate research.

    ⚡️ Don’t miss: Camps-Valls, Reid, Ouala, Beucler + more!

    #AI4Climate #ML4Science #EGU25 #ClimateAI

  6. 🌍 AI is transforming climate research!

    Catch us at #EGU25 presenting cutting-edge work on applying #MachineLearning, hybrid models, and causal discovery in climate research.

    ⚡️ Don’t miss: Camps-Valls, Reid, Ouala, Beucler + more!

    #AI4Climate #ML4Science #EGU25 #ClimateAI

  7. I have been diving into the #ClimateAI literature recently and one thing I notice, that I think is interesting is how many of the publications are authored by scientists who are not at traditionally high powered climate institutes, or often indeed from countries we see a lot of climate modelling literature from. And their names are often not classically WEIRD either. Which suggests #ML / #AI methods in science are widening access. There is no need for a large hpc + a well developed model 1/2

  8. 🚨 Preprint Alert 🚨
    We see a lot of #ML in science applications. What can one do if the data generation process just computationally infeasible? Our paper shows a novel approach inspired by statistical physics, applied to a climate science problem. 🧵👇
    arxiv.org/abs/2302.03258

    #machinelearning #AI #climate #SciML #science #data #climateAI