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

DeepMind's WeatherNext model achieves breakthrough forecasting cyclones

deepmind.google

Post reply on HN
Print view View original

111–120 of 122 posts

Re: DeepMind's WeatherNext model achieves breakthrough forecasting cyclones

#111

Post by jeffbee »

micro2588 wrote: post #106
SirHumphrey wrote: post #99

Earlier quoted context omitted.

There is just A LOT of data available- usually an order of magnitude more than in any other related problem. And general weather forecasts are not that hard - we have semi useful forecasts for more than 50 years. It’s when you want to do something special: long range, nowcasting of convective storm, other extreme weather etc. that is hard. And even then it’s as much a problem of input data accuracy than the models th…

Traditional physics based weather models also rely heavily on physical parameterization for sub grid scale processes (think clouds, microphysics of rain sleet snow, etc) so even the deterministic physics models are learned approximations from data.

traditional physics-based weather models also rely heavily on humans looking at the output and the evaluation of the output to discard wacky runs. Let's not pretend that existing physical models of the atmosphere stay on the rails all the time.

Re: DeepMind's WeatherNext model achieves breakthrough forecasting cyclones

#112

Post by seizethecheese »

esperent wrote: post #52
trescenzi wrote: post #17

Earlier quoted context omitted.

Ironically typhoon forecasting, at this moment, is more valuable. These predictions are matters of life, death, and billions of dollars in damage.

How does predicting a typhoon prevent billions in damage? It could save thousands of lives because people can be evacuated if you can predict a few hours or a day further ahead, or the path more accurately. You can save some damage by moving ships and vehicles. But you can't evacuate buildings or infrastructure.

It could save billions by raising confidence in predictions. Bad predictions have a “boy who cried wolf” aspect.

Re: DeepMind's WeatherNext model achieves breakthrough forecasting cyclones

#113

Post by Zacharias030 »

sunshinesnacks wrote: post #104
micro2588 wrote: post #103

Earlier quoted context omitted.

ECMWF has an experimental AIFS direct observational prediction model (AIFS-DOP) that has become competitive with their physics based IFS model on certain metrics just in the past year. https://arxiv.org/html/2606.19093v1

Ah, yes, that’s one of them! Not to be confused with AIFS and AIFS Ensemble that are competitive with IFS, but start with the same DA as IFS.

I'm interested in understanding wheater prediction models because accurate wind forecasts make a big difference to my personal life (sports).

Is there a good overview to learn about the current models, which all just seem like cryptic acronyms to me? in apps like Windy etc. WRF, TRRM, IK-HRRR-3km, ECMWF-9km,...

I understand by now that small grid cells are better for local prediction and that thermic winds are mostly missing from them all.

Re: DeepMind's WeatherNext model achieves breakthrough forecasting cyclones

#114

Post by Zacharias030 »

pbronez wrote: post #42
tcumulus wrote: post #32

Everything in AI seems to be focused on LLMs lately. But in my opinion, powerful problem-specific models like this are even more interesting. The SOTA AI models used in weather forecasting are already outperforming the classic NWP models while being orders of magnitude more efficient (inference). Most are based on multi scale (hierarchical) Graph Neural Networks, an architecture which is not often talked about. The o…

Insightful paper, thanks for sharing. Two things stand out to me. First, it reinforces that you want methods that get better with more data. It emphasizes that the current approach cannot improve based on historic data - that’s the opportunity that ML based approaches exploit. Second, it highlights that mature legacy solutions are tough competitors. They benefit from extensive tuning and real world feedback. Even whe…

[flagged]

Re: DeepMind's WeatherNext model achieves breakthrough forecasting cyclones

#115

Post by c0_0p_ »

Onavo wrote: post #95
polairscience wrote: post #39

Earlier quoted context omitted.

You say this as if you don't need he MWP models to train the AI models? The accuracy of the AI Prediction depends entirely on the quality of the training dataset...

A more interesting question is...does differential equations based models like mamba/state space models perform better on this sort of physics problem than pure transformer LLMs?

Is it? I can't imagine why a language model would do well on this sort of problem at all.

Re: DeepMind's WeatherNext model achieves breakthrough forecasting cyclones

#116

Post by phi0 »

PunchTornado wrote: post #100
vickychijwani wrote: post #89

Earlier quoted context omitted.

Are you being sarcastic? Even if “Google is struggling so badly” (which it really is not - the narrative will flip again at some point), these efforts will have a lasting impact on the world. Not everything good is about bringing in revenue.

shareholders are pretty unhappy about demis. think about alphafold. huge investments from the company, tens of billions. at a critical time. and absolutely 0 revenue. it got demis a nobel though. as a shareholder you'd be unhappy too.

As a shareholder I am up 75% in a year. Alphafold gained experience makes them better suited to succeed with Isomorphic Labs than anyone else. Research on improved translation gave us the transformer.

If you think AI will win but Google will continue failing, there so many better places to allocate your capital right now.

Re: DeepMind's WeatherNext model achieves breakthrough forecasting cyclones

#117

Post by drusenko »

Zacharias030 wrote: post #113
sunshinesnacks wrote: post #104

Earlier quoted context omitted.

Ah, yes, that’s one of them! Not to be confused with AIFS and AIFS Ensemble that are competitive with IFS, but start with the same DA as IFS.

I'm interested in understanding wheater prediction models because accurate wind forecasts make a big difference to my personal life (sports). Is there a good overview to learn about the current models, which all just seem like cryptic acronyms to me? in apps like Windy etc. WRF, TRRM, IK-HRRR-3km, ECMWF-9km,... I understand by now that small grid cells are better for local prediction and that thermic winds are mostly…

Ask your favorite AI to give you a crash course, but to start the main models you need to know are the GFS and the ECMWF. In the US where available in high res, the HRRR is excellent, but doesn’t forecast very far out. The PWG/PWE 1km PredictWind models are also very good at picking up land based features and other more precise patterns. If you are in the US everything else is probably not super relevant.

Re: DeepMind's WeatherNext model achieves breakthrough forecasting cyclones

#118

Post by blitzar »

trescenzi wrote: post #17
fcanesin wrote: post #10

Maybe was this that was the last drop for Sundar. Demis: "I have a new amazing breakthrough" Sundar: "Great! We really need a answer to Sol and Fable" Demis: "They are completely owned in typhoon forecasting"

Ironically typhoon forecasting, at this moment, is more valuable. These predictions are matters of life, death, and billions of dollars in damage.

You want to know whats cooler than a billion dollars in damage, a trillion dollars in valuation.

Re: DeepMind's WeatherNext model achieves breakthrough forecasting cyclones

#119

Post by E-Reverance »

dgellow wrote: post #21

This is really cool, please more of this from the AI folks! That’s way more impactful and interesting than another coding agent

I get what you generally mean but it’s worth emphasizing that a coding agent probably helped with setting this up

Re: DeepMind's WeatherNext model achieves breakthrough forecasting cyclones

#120

Post by counters »

tcumulus wrote: post #32

Everything in AI seems to be focused on LLMs lately. But in my opinion, powerful problem-specific models like this are even more interesting. The SOTA AI models used in weather forecasting are already outperforming the classic NWP models while being orders of magnitude more efficient (inference). Most are based on multi scale (hierarchical) Graph Neural Networks, an architecture which is not often talked about. The o…

For what it's worth, that paper is a spiritual successor to Keisler (2022) which was the first published work that took this approach: https://arxiv.org/abs/2202.07575
Post reply on HN