Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Google says AI weather model masters 15-day forecast

phys.org

Post reply on HN
Print view View original

141–150 of 216 posts

Re: Google says AI weather model masters 15-day forecast

#141

Post by pharrington »

Ankaios wrote: post #128

Turns out the Google AI's 15-day forecasts are for the weather in Mountain View. Which I can forecast 15 days out, too.

Nope. An excerpt from https://www.nature.com/articles/s41586-024-08252-9:

>Figure 2 shows some of the forecast samples of GenCast for Typhoon Hagibis, shortly before it made landfall in Japan on 12 October 2019. Figure 2b–e,g,h–k,m shows that GenCast forecasts are sharp and have spherical harmonic power spectra that closely match the ERA5 ground truth at both 1- and 15-day lead times

Re: Google says AI weather model masters 15-day forecast

#142

Post by genewitch »

rtsil wrote: post #11
bad_haircut72 wrote: post #5

Obviously this team knows way more about this donain than me but I have to ask, wouldnt this only be able to predict weather which is in line with past weather patterns/indicators? I can imagine a weather analyst might be able to see "between the data" and recognise when some anomaly might be brewing, but an AI model would not

I know nothing about weather, but aren't changes happening gradually instead of overnight? There's no major anomaly that appears all of a sudden. In which case we can assume the every new change will be incorporated in the AI model's training.

As mentioned the bomb cyclone in PNW this year, but also the hurricane that started in the Pacific, whittled down to a trop depression in the gulf (crossing all that land inbetween!) and then spun up into a gnarly hurricane that made a beeline for florida (iirc?). I distinctly remember a lack of worry about that storm system until it started spinning and collecting more stuff a few days after it had left land in central america. None of the models that i know of correctly predicted that it would re-spin, and even the latest updated models with planes flying in the storm still couldn't nail the eyepath - it was essentially off by two whole cities up until it actually made landfall, and then they were a lot more accurate about the land track.

i'd never heard of a storm doing that, but i am not really that in to weather, so it's possible it's in the training data somewhere?

Re: Google says AI weather model masters 15-day forecast

#143

Post by superfrank »

choeger wrote: post #59

Is that a prediction in the form of "There's a 30% chance of light rain that day." or "Temperature will reach 22,5°C at 14:00."?

If they're using the same strategy they were a year or two ago when I first started hearing about Google AI making progress in this space then I think it's closer to the second thing.

IIRC, they had a model that was built to predict weather 15 minutes into the future and were just recursively running that to get days worth of predictions. If that's still the case then I would assume they have predictions for every 15 minutes. Back when I first read about that they were saying the accuracy started to drop off around the 7-10 day mark though, so not sure if they improved on that or changed their strategy though.

Re: Google says AI weather model masters 15-day forecast

#144

Post by shmageggy »

boringg wrote: post #117
atonse wrote: post #7

This is great from a practical standpoint (being able to predict weather), but does it actually improve our understanding of the weather, or WHY those predictions are better? That is my issue with some of these AI advances. With these, we won't have actually gotten better at understanding the weather patterns, since it's all just a bunch of weights which nobody really understands.

This whole article smells like marketing and a way to monetize their weather model. I hope its leaps and bounds beyond current capability but I have very strong doubts about its efficacy in the real world.

Looks like it will be free and open

> We’ll be releasing our model’s code, weights, and forecasts, to support the wider weather forecasting community.

https://deepmind.google/discover/blog/gencast-predicts-weath...

Re: Google says AI weather model masters 15-day forecast

#145

Post by thephyber »

space_oddity wrote: post #136
genewitch wrote: post #133

Earlier quoted context omitted.

haha, one of the few times my gut reaction to something on HN was dead on. "The easiest job in the world is the weatherperson in San Diego... And now, Ryan, what's the weather going to be like today?' 'uh, nice. back to you!'"

San Diego weather forecasting is the meteorological equivalent of being on cruise control

> 80% of the time, the WeatherMan is right every time!

Re: Google says AI weather model masters 15-day forecast

#146

Post by Terr_ »

Ankaios wrote: post #128

Turns out the Google AI's 15-day forecasts are for the weather in Mountain View. Which I can forecast 15 days out, too.

There's a little cautionary story I like to tell about predictions and probabilities

There is a man living near a volcano. He has put up a sign outside his house for travelers, proudly declaring: "Will not erupt today. Accuracy: 100%."

One night, after thirty years of this, the volcano erupts for a few hours at night, oozing magma on its opposite side.

The next morning, the man is grateful that his house is fine, but feels a pang of sadness as he replaces the famous sign with a new one: "Will not erupt today. Accuracy rate: 99.99%."

Re: Google says AI weather model masters 15-day forecast

#147

Post by gniv »

atonse wrote: post #7

This is great from a practical standpoint (being able to predict weather), but does it actually improve our understanding of the weather, or WHY those predictions are better? That is my issue with some of these AI advances. With these, we won't have actually gotten better at understanding the weather patterns, since it's all just a bunch of weights which nobody really understands.

I'm not sure there's a good WHY. To me both weather and AI are similarly complex and inscrutable, so they seem right for each other.

Re: Google says AI weather model masters 15-day forecast

#148

Post by labster »

counters wrote: post #118
labster wrote: post #89

Earlier quoted context omitted.

Weather and climate models have their own physics, which at the very least means that the solution is physical for the universe that particular model inhabits. The boundary conditions are parameterized, and those can be tweaked as climate and land use changes. AI models don’t have any of that, but they are actually more akin to human forecasters, gaining forecast skill from pattern recognition. I think there’s a plac…

> Weather and climate models have their own physics, which at the very least means that the solution is physical for the universe that particular model inhabits. The boundary conditions are parameterized, and those can be tweaked as climate and land use changes. That really isn't true these days. The dynamical cores and physics packages in numerical weather prediction models and general circulation models have more-o…

> That really isn't true these days. The dynamical cores and physics packages in numerical weather prediction models and general circulation models have more-or-less converged over the past two decades.

Ah, well, I did stop studying GCMs about 20 years ago so perhaps I should shut up and let other people post. I appreciate the detail in your explanation here, and I wouldn’t mind a link to papers explaining the current state of the art.

Re: Google says AI weather model masters 15-day forecast

#149

Post by mjburgess »

counters wrote: post #124
mjburgess wrote: post #6

Earlier quoted context omitted.

Yup. There's fundamentally no way to automatically verify predictive accuracy, the assumptions in ML papers about such accuracy is (the almost always false presumption) that there are no distributional shifts in the data generating process. Here, since weather certainly changes its fundamental patterns over time, there is no way of reliably predicting out-sample performance. It's highly likely that in 1-2 years time…

> Here, since weather certainly changes its fundamental patterns over time, there is no way of reliably predicting out-sample performance. This seems overly pessimistic. The weather doesn't change its fundamental patterns over time; those are governed by the fluid dynamics of the atmosphere, and are largely forced (to first order) by things like the amount of solar radiation received by the sun and the the configurat…

The causal mechanics are the same. ML works on very specific distributions of measurements of those patterns.

ML models are models of measures, not of the causal process which generates those measures. In this sense they arent 'models' at all, in the traditional scientific sense of the term.

Re: Google says AI weather model masters 15-day forecast

#150

Post by toxik »

Dylan16807 wrote: post #98
seizethecheese wrote: post #90

Earlier quoted context omitted.

A hard science Nobel is very different from the peace prize, obviously.

> obviously It's not obvious to me. Care to elaborate? The only one that strikes me as "obviously" different is the Nobel prize that isn't really a Nobel prize, the one for economics.

The peace prize isn’t awarded by the Nobel committee either.
Post reply on HN