Pretty much the only thing I think AI could be useful for - forecasting the weather based off tracking massive amounts of data. I look forward to seeing how this particular field of study is improved.

Bonus points, AI weather modeling, for once, saves energy relative to physics models. Pair it with some sort of light weight physical model to keep the hallucinations at bay, and you’ve got a good combo.

  • Buffalox@lemmy.world
    link
    fedilink
    English
    arrow-up
    21
    ·
    5 months ago

    what’s perhaps most striking about GenCast is that it requires significantly less computing power than traditional physics-based ensemble forecasts like ENS. According to Google, a single one of its TPU v5 tensor processing units can produce a 15-day GenCast forecast in eight minutes. By contrast, it can take a supercomputer with tens of thousands of processors hours to produce a physics-based forecast.

    If true this is extremely impressive, but this is their own evaluation, so it may be biased.

    • RvTV95XBeo@sh.itjust.worksOP
      link
      fedilink
      English
      arrow-up
      9
      ·
      5 months ago

      What they leave off is how much goes into training the model, but I imagine once they settle on a trained model it can carry on pretty efficiently for a long time, especially if they’re baking in things like atmospheric CO2 levels to help keep forecasts in line with global warming.

      • Buffalox@lemmy.world
        link
        fedilink
        English
        arrow-up
        6
        ·
        edit-2
        5 months ago

        Absolutely, but training is only once, being so efficient to make the actual forecast, you could have a forecast personally made for your own garden, which may be very different than a generic one covering hundreds of km². Then the about 90% accuracy will feel WAY more accurate.

        • RvTV95XBeo@sh.itjust.worksOP
          link
          fedilink
          English
          arrow-up
          5
          ·
          5 months ago

          I feel this personally, I live in the hills outside of a valley metro. All weather data is forecasted off of valley sensors, but shit gets weird when you suddenly climb 2000+ ft.

          The best weather services in my area are those that can factor in peoples household meters into their forecasting, but those services still aren’t perfect.

      • Zarxrax@lemmy.world
        link
        fedilink
        English
        arrow-up
        3
        ·
        5 months ago

        I’m sure the model would need to be continuously updated to take in more recent weather data.

        • RvTV95XBeo@sh.itjust.worksOP
          link
          fedilink
          English
          arrow-up
          2
          ·
          5 months ago

          There’s a difference between the real-ish-time weather data continuously fed in to output predictions, and the decades of weather data used to build the model. The continuous feed of data is more than likely part of what Google alleges is saving significant energy.

          Its the training on decades of information, and occasional updates to those trained models that take a significant amount of resources, but hopefully for relatively short bursts.

    • jacksilver@lemmy.world
      link
      fedilink
      English
      arrow-up
      2
      ·
      5 months ago

      It actually makes sense if you think about it from the perspective that ML is about generalizing trends/functions. Simulating the world is hard, generalizing the world based on past observations - easy (with some lossyness).

    • RvTV95XBeo@sh.itjust.worksOP
      link
      fedilink
      English
      arrow-up
      2
      arrow-down
      1
      ·
      5 months ago

      It’s not just about cutting costs, but also improving accuracy. Physical simulations factor in a dozen or so weather conditions to predict outcomes. Machine learning can track thousands of conditions, drawing connections not realized in physical models, leading to much more accurate statistical models.

      • chaosCruiser@futurology.today
        link
        fedilink
        English
        arrow-up
        1
        ·
        5 months ago

        Yeah, that’s pretty impressive. I wonder if you could apply the same philosophy in other areas too. Instead of training the model with data produced in a simulation, you could just feed it real world data instead. Like, if you gave a bunch of stress-strain data to a model, could you make better predictions about the behavior of physical structures, such as bridges and towers.