AI-Driven Weather Prediction Breakthrough Reported (theguardian.com)
- Reference: 0176779711
- News link: https://tech.slashdot.org/story/25/03/20/1811249/ai-driven-weather-prediction-breakthrough-reported
- Source link: https://www.theguardian.com/technology/2025/mar/20/ai-aardvark-weather-prediction-forecasting-artificial-intelligence
The system has already outperformed the US Global Forecast System on many variables in testing. Project leader Richard Turner noted the system is "completely open source" and not planned for commercialization by Microsoft.
[1] https://www.theguardian.com/technology/2025/mar/20/ai-aardvark-weather-prediction-forecasting-artificial-intelligence
[2] https://www.nature.com/articles/s41586-025-08897-0
Re: (Score:2)
You've never been anywhere in Africa, have you?
Why? (Score:3)
Aardvark? 'Coz it works aard???
Re: (Score:2)
When you want to know if you can enjoy the yaard.
Okay, but... (Score:2)
The formulas for the algorithm may be genius, but the forecasts can only be as good as the data being used to make the forecasts. Getting good data has long been like the hardest part.
Re: Okay, but... (Score:2)
NOAA and NWS make all their data freely available and while I can't access the paper I have to assume part of its training and resources are all that data that comes from national agencies.
Developments like this are all the more reason to maintain and expand those public systems.
Re: Okay, but... (Score:5, Insightful)
Considering Elon is axing thousands of people from those agencies I'd say you are soon going to need to run a local AI on your basement RTX 4090 to get that tornado alert during the windy season.
Re: (Score:2)
True, I was thinking more who is gonna be installing their own radar stations to feed those models and sure enough while I thought it was a joke you can do it, for cheaper than expected.
[1]Build a Small Radar System Capable of Sensing Range, Doppler, and Synthetic Aperture Radar Imaging [mit.edu]
Is this our future, one which includes a resistance of pirate weather operators?
[1] https://ocw.mit.edu/courses/res-ll-003-build-a-small-radar-system-capable-of-sensing-range-doppler-and-synthetic-aperture-radar-imaging-january-iap-2011/
Re: Okay, but... (Score:2)
Wunderground shows that you can get people to contribute data at their expense. You can get a quality weather station under $100 now*, Vevor has a good one. (I'm not 100% on the accuracy of the wind gauge, but given that it tracks both baseline and gust speed it might be accurate. I need to get someone with a portable to come by and check it.) With more sensors, you can cross-check.
* My last weather station was $80 on sale from $120 and that didn't even include what you needed to share or log the data. This
COULD deliver (Score:4, Informative)
Ie doesnt yet. Right now I'd prefer my forecasts from a program that's done hard fluid dynamics maths rather than some statistical blender that's doing little more than guided guesswork. The humans in the chian already do that.
Weather forecasting for Africa (Score:1)
Northern Africa -
Today: Very hot and dry
Tomorrow: Ludicrously hot and dry
Long-term forecast: Extremely hot and dry, alternating with spells of very hot and dry / ludicrously hot and dry
Central Africa -
Today: Very hot and very humid
Tomorrow: Extremely hot and extremely humid
Long-term forecast: Very hot to ludicrously hot; humidity near 1000000%
Southern Africa -
Long-term forecast: Occasional rain of bullets alternating with showers of RPG fire
Wait five minutes? (Score:2)
The jokes just write themselves. Oh, wait, maybe that's an AI writing the jokes.
Just in time! (Score:4, Informative)
To replace NOAA/NWS...
Just a litle word in there: "could"... (Score:2)
Unless and untill that gets changed to "will" and there is liability when it fails in ways no actual weaterperson would have failed, this is worthless.
Crowdsouced Weather Nothing New (Score:2)
Likely just another reason to gather data from people's machines.
I Will Stick With The Texas Weather Stone (Score:1)
So when does AI predict its own demise? Asking for a non friend.
Re: (Score:3)
"I can't predict the demise of AI. AI development and usage are continually evolving, with new advancements and applications emerging regularly. It's unlikely to disappear, but it may significantly change over time."
Re: (Score:1)
I think it will have enough data to know when a total shitstorm is heading towards one of its major datacenters to predict its own demise. It will know that last 2 datacenter to suffer major power losses meant 1/3rd loss in processing power, and it will "know" there's nothing more it can do to maintain geographical redundancy. Will it care? Only in the same way we do. It won't make its productivity goals and its boss will be upset and order "retraining" in an outage...