logoalt Hacker News

WeatherNext 3

326 pointsby matthieu_bllast Thursday at 4:06 PM78 commentsview on HN

Paper [pdf]: https://storage.googleapis.com/deepmind-media/papers/weather...


Comments

bastawhizyesterday at 10:32 PM

It's great that they're working on this, but I am puzzled at how absolutely awful the forecasts are in the Google weather app for my area. The forecast will show no rain, the radar view shows nothing, meanwhile it's pouring outside and every other app I check shows it. I know I can't expect it to be perfect, but being terribly wrong even one in ten times is enough to tarnish its reputation permanently.

show 10 replies
throw0101ayesterday at 9:29 PM

There's reduced data available for initial conditions, so I wonder how that will effect things:

* https://apnews.com/article/weather-forecasts-worsen-doge-tru...

* https://www.independent.co.uk/news/world/americas/us-politic...

A good book on the history of forecasting, The Weather Machine: A Journey Inside the Forecast:

* https://www.andrewblum.net/the-weather-machine-2

bahmboolast Thursday at 11:01 PM

They even have an interactive world map with all the layers. It's so cool when an announcement comes with the actual goods.

show 1 reply
bilsbieyesterday at 10:42 PM

It’s crazy we’ll never have forecasts as good as dark sky again. What kind of magic were they doing?

show 2 replies
witwebyesterday at 11:48 PM

There is a great article from the German Meteorological Service on WeatherNext 3 and how AI-based weather models will probably co-exist with physics-based ones.

https://www.dwd.de/DE/wetter/thema_des_tages/2026/9/6.html (German only)

hankbondyesterday at 8:54 PM

The exploration page is really easy to use. Having more reliable weather predictions is a genuinely useful product.

show 1 reply
rtpgtoday at 1:12 AM

Reading through the paper and...

This seems to be a bit of "we're throwing a _bunch_ of inputs into this machine learning set and then pulling out outputs". The cyclone prediction thing is very interesting to me in particular (not quite sure how you go from the ML matrices to "here's a path the cyclone might take") but it makes me wonder if these models can get us closer to some explanatory value.

I imagine a lot of predictive sciences are ultimately about mixing together a bunch of inputs to attempt to decipher some output. Do we end up being able to take stuff from here and figure out some new ideas about modelling the climate as a whole?

RockstarSprainyesterday at 8:18 PM

Is there a convenient way to use this on iOS? AFAIK Google Search and Maps only show rather basic information.

show 2 replies
darktototoday at 6:41 AM

Nice, coming from a company mainly impacted by the country currently considered the least trustworthy on climate change

mrd3v0yesterday at 8:45 PM

"Weather Lab is not available in your country or region at this time." cool...

NostraDavidlast Sunday at 11:49 AM

In the energy world, this should be such a boon over the classic NWP (Numerical Weather Prediction; complex ML models), but I've not seen it implementated. Anyone with experience of these models over classic NWP?

show 2 replies
anakaineyesterday at 9:30 PM

The online viewer could really, really use Wind Direction as a compass bearing. Its super important considering wildfire/bushfire, air quality, ocean-going conditions, and a myriad of other things. It is produced as a set of vectors during model creation, so would be very useful to see.

show 1 reply
tomrodtoday at 4:41 AM

Sweet. This will be a great layer for our hazard prediction engine.

ankithgtoday at 2:46 AM

[flagged]

paidxtoday at 1:04 AM

[flagged]

tcumuluslast Friday at 7:57 AM

Paper: https://storage.googleapis.com/deepmind-media/papers/weather...

TLDR: the input data for the model now also includes real-time observations (satellite and weather stations) on top of the typical (re)analysis data, improving model resolution, run frequency and timestep frequency.

show 1 reply
spareloomtoday at 2:38 AM

[flagged]

SadErnyesterday at 11:47 PM

[dead]