Weather Forecasting
topic on 3 shows · 7 statements across 4 episodes
7 statements about Weather Forecasting, every show
FourCastNet models trained on six-hour steps produce stable months-long forecasts
“To predict for the next six hours. And a little bit of multi-step fine tuning... Now we are showing for several months that it's able to do that.”
Battaglia: Early ML in weather improved downstream calibration, not base models
“So actually, the first advent of like, AI and machine learning in weather forecasting, or at least some of the earliest, was not, like, trying to overhaul the whole weather forecast process itself, but making, you know, using more and more, like, statistical m…”
DeepMind primarily uses traditional supervised learning for AI weather models
“What we use in our weather forecasting models, and a lot of folks out in the community are using it as, you know, as this field is advancing and this AI-based weather forecasting is developing, we're still mostly using fairly traditional machine learning, supe…”
DeepMind uses transformers to model spatial interactions in weather, not time
“We actually use transformers not to model the spatial, the interactions in weather over time, like the sequence of text, but in space.”
Battaglia: AI weather models leverage macroscopic spatial ranges unlike traditional simulations
“In a traditional model, the way it simulates that is it, in very fine detail, it kind of figures out, like, what's the pressure, and the temperature, and the wind, and the moisture, and what are those things? What's going to happen next is determined strictly …”
Mochida: ML Weather Models Cut Costs 99% and Increase Resolution 100x
“With machine learning, what you're able to do is reduce costs by 99% and increase resolution by a hundred times.”