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

Two new AI-based weather-forecasting systems challenging the status quo

phys.org

Post reply on HN
Print view View original

31–39 of 39 posts

Re: Two new AI-based weather-forecasting systems challenging the status quo

#31

Post by pixl97 »

zerodensity wrote: post #21
NoahECampbell wrote: post #16

Earlier quoted context omitted.

No we aren't actually. We are still well within historical data, since we use that still to calculate future weather patterns, and there hasn't been anything unprecedented that would trip up a model like this either.

So global warming is just a hoax? Or what are you saying?

No, what they are saying is events are not so far out of bounds that the models fall apart. Either there have been no black swans spotted yet, or in conjunction with other numerical models the outliers are correctly predicted.

Re: Two new AI-based weather-forecasting systems challenging the status quo

#33

Post by counters »

supdudesupdude wrote: post #14
opdahl wrote: post #4

I’m actually surprised to hear that the standard approaches used for weather forecasts do not use AI. One would think this would be one of the first areas that would adopt AI given the data available. Also that these new AI systems are performing at the same level of the old non-AI approaches I feel is a real testament to the developers of those systems. This is not something we see in many other cases.

I'm actually not surprised that people think 'AI' can fix everything including weather prediction. I've heard about AI machine learning forecasts for 10+ years now, waiting for one of them to be actually used in industry... This aint a retail product recommendation. If the AI makes a bad choice it will cost millions/billions of dollars and we could lose many MANY lives.

> I've heard about AI machine learning forecasts for 10+ years now, waiting for one of them to be actually used in industry...

The problem is that they offer little to no advantage over the highly optimized ML-based forecast post-processing systems widely in use in the industry. You see an awful lot of hype from start-ups proclaiming their AI forecasts are "the most accurate ever"... when in reality they barely improve at all over the status quo that can be achieved with rather simple statistical modeling.

Re: Two new AI-based weather-forecasting systems challenging the status quo

#34

Post by hulitu »

mydriasis wrote: post #2

> In the first effort, the team behind Pangu-Weather, trained their system on 39 years of weather data and then asked it to make predictions based on current weather patterns. They found that it was as accurate at doing so as existing systems, and did its work in just a fraction of the time. That's awesome -- years of analysis paying off in a very cool and interesting way. It says that this particular model doesn't p…

I'm sure this is already used in the weather stations selled on Amazon. /s

Re: Two new AI-based weather-forecasting systems challenging the status quo

#35

Post by troupo »

zerodensity wrote: post #21
NoahECampbell wrote: post #16

Earlier quoted context omitted.

No we aren't actually. We are still well within historical data, since we use that still to calculate future weather patterns, and there hasn't been anything unprecedented that would trip up a model like this either.

So global warming is just a hoax? Or what are you saying?

No. What they are saying is that:

- weather is not climate

- we are not in a situation where weather models don't work

Re: Two new AI-based weather-forecasting systems challenging the status quo

#36

Post by nmstoker »

jcalx wrote: post #27

Old (from 2011) but Dark Sky had a blog post on how local, short-term weather prediction works: https://web.archive.org/web/20200122042359/https://blog.dark... Incidentally, this post, along with the rest of the Dark Sky blog, was deleted after they were acquired by Apple.

Was telling people about how good DarkSky was over the weekend! It's a shame the blog got pulled. They didn't do such a thorough job though as the Vimeo videos are still there (was able to view them via the web archive link you posted... You need to login as they're unrated)

Re: Two new AI-based weather-forecasting systems challenging the status quo

#37

Post by sorokod »

counters wrote: post #28
sorokod wrote: post #18

Earlier quoted context omitted.

Must say that "as accurate at doing so as existing systems" is quite mysterious. Not as accurate as systems from previous decades, not more accurate then the existing systems. What is so special about the now?

It's specifically referring to these forecast models having accuracy about on par with the state-of-the-science global numerical weather forecast models. "Accuracy" here specifically means esoteric metrics like the "500mb anomaly correlation coefficient" (basically a summary statistic that tells you how well the 3D atmosphere fields predicted by the model match what we observe later on). This entire class of global n…

Thanks for the explanation but my question was not about the cost but about the accuracy. Or is it the case that because of the reduced cost there is an opportunity to improve accuracy because more scenarios can be executed?

Re: Two new AI-based weather-forecasting systems challenging the status quo

#38

Post by counters »

sorokod wrote: post #37
counters wrote: post #28

Earlier quoted context omitted.

It's specifically referring to these forecast models having accuracy about on par with the state-of-the-science global numerical weather forecast models. "Accuracy" here specifically means esoteric metrics like the "500mb anomaly correlation coefficient" (basically a summary statistic that tells you how well the 3D atmosphere fields predicted by the model match what we observe later on). This entire class of global n…

Thanks for the explanation but my question was not about the cost but about the accuracy. Or is it the case that because of the reduced cost there is an opportunity to improve accuracy because more scenarios can be executed?

The problem in this world of AI/weather is that "accuracy" is an extremely fuzzy concept. The leading pack of AI-NWP models (NVIDIA's FourCastNet, DeepMind's Graphcast, Huawei PanguWeather), when compared on an apples-to-apples basis with the leading pack of traditional NWP systems (NOAA GFS and ECMWF HRES) have similar accuracy metrics. But here, "accuracy" is an esoteric term that is far removed from how an end user would perceive how "good" any of these given models are at predicting tomorrow's afternoon high temperature at their house.

In the world of meteorology, the way you build an "accurate" (e.g. "user-perceived accuracy") forecast is to consume the entire previous class of forecasts and apply statistics/ML to post-process them. The greater your ability to probe uncertain in the forecasts from these models - e.g. by running larger ensembles or tailoring the ones you run to try to quantify the uncertainty more explicitly - the better your opportunity to improve those 'accuracy" metrics. So yes - the opportunity here is running larger sets of tailored forecast simulations as a way to statistically optimize forecast accuracy.

Re: Two new AI-based weather-forecasting systems challenging the status quo

#39

Post by tnecniv »

PaulHoule wrote: post #10
troupo wrote: post #5

Earlier quoted context omitted.

> I’m actually surprised to hear that the standard approaches used for weather forecasts do not use AI. Why would they use AI where weather models exist, and work? What exactly would AI bring into space?

A lot of people are using neural network models to model fields in variable resolution, solve PDEs and such. I know a bit about astrophysical modeling and you sure can't afford to model every part of a star in the same amount of detail. You can pick some special coordinate system or make the grid vary in size or you can use a neural network to model some f(x,y,z) and the network can allocate its own resources to put…

PINNs are neat but by my understanding they’re conceptually not too different from traditional numerical solution methods. The solution to your PDE is some complicated function that is not available in closed-form, so you require a numerical approximation of that function. Traditional methods use various kinds of grid discretization systems (possibly with interpolation schemes). PINNs replace the grid with a parametric continuous function. I’m not sure how PINNs handle discontinuities like shocks though.
Post reply on HN