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

91–100 of 216 posts

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

#91

Post by labster »

IshKebab wrote: post #28
hotstickyballs wrote: post #26

Earlier quoted context omitted.

What does a causal weather model even mean?

He meant one that is physically based and interpretable, rather than a black box based on pattern matching. But I'll take the accurate black box any day, at least for weather forecasting. Climate modelling is a totally different thing.

Accurate black box is fine until it blows a forecast and people die, and you want to fix it for the next time.

Take the situation with Hurricane Otis — what do you do if an AI doesn’t detect cyclogenesis 24-48 hours beforehand? Are we sure tuning the model to detect this event will improve forecast skill in general, or will it make it worse?

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

#92

Post by exprofmaddy »

kolinko wrote: post #62
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.

Define "our understanding". With complex / chaotic systems there sometimes are no higher level laws that govern them - all we have is just modeling and prediction.

A better name for "laws" is "models."

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

#93

Post by mnau »

diego_sandoval wrote: post #76
n4r9 wrote: post #57

Earlier quoted context omitted.

I would guess that everyday they're comparing the current weather against the forecast from 15 days ago. Not a lot of data points to be sure, but perhaps enough to have confidence of very high accuracy.

I don't think that's necessary. You can do a backtest for any point in the past, as long as you only use the data that was available until 15 days before the day being predicted.

So do they say. I am reminded of Google Flu Trends [0]. They likely also did similar "verification" and it didn't work.

> The initial Google paper stated that the Google Flu Trends predictions were 97% accurate comparing with CDC data.[4] However subsequent reports asserted that Google Flu Trends' predictions have been very inaccurate, especially in two high-profile cases. Google Flu Trends failed to predict the 2009 spring pandemic[12] and over the interval 2011–2013 it consistently overestimated relative flu incidence,

[0] https://en.wikipedia.org/wiki/Google_Flu_Trends

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

#94

Post by Retric »

atonse wrote: post #31
CabSauce wrote: post #8

Earlier quoted context omitted.

But that's the point of a weather forecast. We don't do them for the science. (I'm not arguing against weather research.)

I would think we also use these models to run simulations. So maybe the AI models can be used to run simulations with different kinds of inputs to see if doing X in one place (like planting a lot of trees in one area) will have an outsized impact rather than doing Y in another place.

AI models rarely have that kind of predictive power because they are noticing patterns not running simulations.

The model may care about trees because mountains above a specific height don’t have trees on them. The old, measures stop being useful once you start optimizing for them, AI edition.

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

#95

Post by chris_va »

encoderer wrote: post #86

I recently read that the 10 day forecast now is as accurate as the 5 day forecast from 30 years ago when I was a kid. This surprised me. I grew up in Ohio and now I live in the Bay Area and the forecast here seems to be accurate only 2-3 days out. It would be so helpful to have an accurate 10 day forecast.

If you want a graph: https://www.researchgate.net/publication/319645683/figure/fi...

... there is probably a newer one, it continues to improve. Keep in mind that individual locations are always hit or miss compared to the average skill.

EDIT: Some better graphs at https://charts.ecmwf.int/?facets=%7B%22Type%22%3A%5B%22Verif...

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

#96

Post by nradov »

labster wrote: post #91
IshKebab wrote: post #28

Earlier quoted context omitted.

He meant one that is physically based and interpretable, rather than a black box based on pattern matching. But I'll take the accurate black box any day, at least for weather forecasting. Climate modelling is a totally different thing.

Accurate black box is fine until it blows a forecast and people die, and you want to fix it for the next time. Take the situation with Hurricane Otis — what do you do if an AI doesn’t detect cyclogenesis 24-48 hours beforehand? Are we sure tuning the model to detect this event will improve forecast skill in general, or will it make it worse?

Weather forecasting models will gradually improve over time but it's unreasonable to expect perfect accuracy. That is mathematically impossible in a chaotic system. Some people will always die in extreme weather events.

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

#97

Post by Dylan16807 »

raincole wrote: post #66
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.

A fisherman was relaxing on a sunny beach, enjoying the day with his fishing line in the water. A businessman, stressed from work, walked by and criticized him for not working harder. "If you worked more, you'd catch more fish," the businessman said. "And what would my reward be?" asked the fisherman with a smile. "You could earn money, buy bigger nets, and catch even more fish!" the businessman replied. "And then wh…

Okay.

I mean, yeah, if you want 90% of your relaxation time for the rest of your life to be while you're fishing, that's fine.

For the businessman to assume otherwise is not outlandish. The idea of an entire fleet is overblown, but having "fuck you money" is a pretty nice goal.

-

Also I don't see how this applies to meteorologists? Which part is the "working more" aspect?

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

#98

Post by Dylan16807 »

seizethecheese wrote: post #90
soperj wrote: post #78

Earlier quoted context omitted.

[flagged]

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.

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

#99

Post by Dylan16807 »

computerex wrote: post #87
soperj wrote: post #78

Earlier quoted context omitted.

[flagged]

How is that even remotely relevant? Besides, work on Alphafold produced a Nobel prize in Chemistry.

The implication is that "producing a Nobel prize" is not reliably all that impressive.

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

#100

Post by deskamess »

dumbfounder wrote: post #40

"More accurate forecasts of risks of extreme weather can help officials safeguard more lives, avert damage, and save money," DeepMind said. Did the DeepMind AI say this?

Doing its own PR's as well. This model is now marketing itself.
Post reply on HN