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

GraphCast: AI model for weather forecasting

deepmind.google

Post reply on HN
Print view View original

191–200 of 310 posts

Re: GraphCast: AI model for weather forecasting

#191

Post by isaacfrond »

I find this quite surprising actually.

You'd think predicting the weather is mostly a matter of fast computation. The physical rules are well understood, so to get a better estimate use a finer mesh in your finite element computation and use a smaller time scale in estimating your differential equations.

Neural networks are notoriously bad at exact approximation. I mean you can never beat a calculator when the issue is doing calculations.

So apparently the AI found some shortcut for doing the actual computational work. That is also surprising as weather is a chaotic system. Shortcuts should not exist.

Long story short, I don't get what's going on here.

Re: GraphCast: AI model for weather forecasting

#193

Post by tomaskafka »

brahbrah wrote: post #186
tomaskafka wrote: post #182

Earlier quoted context omitted.

I confirm, open-meteo is awesome and has a great API (and API playground!). And is the only source I know to offer 2 weeks of hourly forecasts (I understand at that point they are more likely to just show a general trend, but it still looks spectacular). It's a pleasure being able to use it in https://weathergraph.app

> And is the only source I know to offer 2 weeks of hourly forecasts Enjoy the data directly from the source producing them. American weather agency: https://www.nco.ncep.noaa.gov/pmb/products/gfs/ European weather agency: https://www.ecmwf.int/en/forecasts/datasets/open-data The data’s not necessarily east to work with, but it’s all there, and you get all the forecast ensembles (potential forecasted weather paths) t…

Thank you, I didn't know! I'd love to, but I'd need another 24 hours in a day to also process the data - I'm glad I can build on a work of others and use the friendly APIs :).

Re: GraphCast: AI model for weather forecasting

#197

Post by mg »

It's interesting, that Google keeps publishing AI research papers. Is there a business rationale behind it?

OpenAI has become one of the fastest growing companies of all time. And much of it is based on Google's "Attention is all you need" and other papers.

Since Microsoft added the Dall-E 3 image creator to Bing, Bing saw a huge inflow of new users. Dall-E is also a technology rooted in Google papers.

I wonder how Google thinks about this internally.

Re: GraphCast: AI model for weather forecasting

#198

Post by uoaei »

isaacfrond wrote: post #191

I find this quite surprising actually. You'd think predicting the weather is mostly a matter of fast computation. The physical rules are well understood, so to get a better estimate use a finer mesh in your finite element computation and use a smaller time scale in estimating your differential equations. Neural networks are notoriously bad at exact approximation. I mean you can never beat a calculator when the issue…

> The physical rules are well understood

Nope. They're constantly updating these models with really finnicky things like cloud nucleation rates that differ depending on which tree species's pollen is in the air. They've gotten a lot better (~2 day to ~7 day hi-res forecasts) but they're still wrong a lot of the time. The reason is the chaos as you say, however, chaos is deterministic, so, that a deterministic method can approximate a deterministic system is really not the surprising part.

You don't get what's going on here because your baseline understanding is a lot worse than you think it is.

What they're doing is skipping literal numerical simulation in favor of graph- (attention-) based approaches. Typical weather models simulate pretty fine resolution and return hourly forecasts. Google's new approach is learning an approximate Markov model at 6 hours resolution directly so they don't need to run on massive supercomputers.

Re: GraphCast: AI model for weather forecasting

#199

Post by matsemann »

How's the distribution of the errors? For instance I don't care if it's better on average by 1 Celsius each day for normal weather, if it once every month is off by 10 Celsius when there is a drastic weather event, for instance.

I'm all for better weather data, it's quite critical up in the mountains, so that's why my question about how reliable it is in life&death situations.

Re: GraphCast: AI model for weather forecasting

#200

Post by karaterobot »

isaacfrond wrote: post #191

I find this quite surprising actually. You'd think predicting the weather is mostly a matter of fast computation. The physical rules are well understood, so to get a better estimate use a finer mesh in your finite element computation and use a smaller time scale in estimating your differential equations. Neural networks are notoriously bad at exact approximation. I mean you can never beat a calculator when the issue…

I used to think so too, but evidently weather forecasting is a much harder problem than it seems from the outside. I was talking to a physicist who told me who had first wanted to get into weather modeling, but that it was too hard. I think his quote was something like: "those guys are hard. core."
Post reply on HN