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

WeatherNext 2: Our most advanced weather forecasting model

blog.google

Post reply on HN
Print view View original

101–110 of 140 posts

Re: WeatherNext 2: Our most advanced weather forecasting model

#101

Post by tylervigen »

jasonmarks_ wrote: post #92
bigtones wrote: post #62

Googles weather prediction engine is already very good, and the new hurricane model was breathtakingly good this season when tested against actual hurricane paths. Meanwhile, the US Government Global Forecasting System continues to get worse. https://arstechnica.com/science/2025/11/googles-new-weather-...

> Global Forecasting System continues to get worse What do you mean?

It's the subtitle of the article they linked to.

But to expand: the US flagship forecast model just had its worst year predicting hurricanes since 2005. The trend of errors over the last few years hasn't been great.

Re: WeatherNext 2: Our most advanced weather forecasting model

#102

Post by jasonmarks_ »

tylervigen wrote: post #101
jasonmarks_ wrote: post #92

Earlier quoted context omitted.

> Global Forecasting System continues to get worse What do you mean?

It's the subtitle of the article they linked to. But to expand: the US flagship forecast model just had its worst year predicting hurricanes since 2005. The trend of errors over the last few years hasn't been great.

More objectively it reads as if none of the models performed well outside of 24 hours with a significant uptick in inaccuracy after 72 hours.

Re: WeatherNext 2: Our most advanced weather forecasting model

#105

Post by counters »

kachapopopow wrote: post #104
nipperkinfeet wrote: post #103

Hopefully this will help! I've found that all weather apps and websites have been completely inaccurate this year.

1) this is for 1 hour~ prediction 2) it's for CRPS not for normal people

These models don't predict CRPS - it's just the loss that they're optimized against. They still produce a normal weather forecast with gridded variables.

Re: WeatherNext 2: Our most advanced weather forecasting model

#106

Post by kachapopopow »

counters wrote: post #105
kachapopopow wrote: post #104

Earlier quoted context omitted.

1) this is for 1 hour~ prediction 2) it's for CRPS not for normal people

These models don't predict CRPS - it's just the loss that they're optimized against. They still produce a normal weather forecast with gridded variables.

huh, I guess I shouldn't believe every HN commenter that sounds like they know what they're talking about

Re: WeatherNext 2: Our most advanced weather forecasting model

#107

Post by generativenoise »

schiffern wrote: post #94
tekkk wrote: post #82

Earlier quoted context omitted.

Never thought of that. Probably a bit too generous given that it could be just as well waste of time and resources, nevermind the bias of the voodoo doctor. Most of it was just weirdly provided therapy I suppose to relieve stress. But it is funny that humans put a great lot of weight on social contracts and being given explicit orders, maybe even publicly, must help pursuing action instead of rumination. Especially i…

"Evolution doesn't optimize for correctness, it optimizes for minimum error cost." It's a subtle but important distinction.

That is such a good line. Another important note is the time horizon of that error function is often quite short.

Re: WeatherNext 2: Our most advanced weather forecasting model

#108

Post by nerdponx »

bilsbie wrote: post #38

Where can I use this? I’ve been trying to find hyperlocal forecasts like darksky used to be.

Windy is my favorite weather app. The forecast is usually very good and I can switch underlying models to see how much they disagree (an indication that the weather might be erratic). Plus the wind vector animation is mesmerizing and it's fun to look at all the satellite overlays and webcam feeds.

Re: WeatherNext 2: Our most advanced weather forecasting model

#109

Post by Quarrel »

cogman10 wrote: post #80
lampiaio wrote: post #54

Reminds me of a funny WWII story: Kenneth Arrow and his statisticians found that their long-range forecasts were no better than numbers pulled out of a hat. The forecasters agreed and asked their superiors to be relieved of this duty. The reply was: "The Commanding General is well aware that the forecasts are no good. However he needs them for planning purposes."

I think it was a stats class where I learned this, but as it turns out bad weather is less common than good weather. To be a fairly accurate weather person, you merely need to say "there will be no precipitation" and you'll be right like 90% of the time anywhere on earth. What makes that funny is that historically, weather forecasters have been less than 90% accurate. Now, I will say that today's weather models are p…

I heard it (again, I think it was a stats class) as:

Forecasting that what is happening today, will happen tomorrow, was an almost insurmountable baseline for early forecasters.

A bit like trying to come up with psych drugs that can beat a placebo. Although, placebos are particularly effective for psych treatments.

Re: WeatherNext 2: Our most advanced weather forecasting model

#110

Post by iFred »

mmooss wrote: post #86

On what geometric surfaces do weather models run? Spheriods? Spheres? Projections on planes? Geoids?? Weather is three-dimensional and I would guess that the difference between sphere and (appropriate) spheroid could impact predictions. It seems possible that, at least for local and hyperlocal forecasts, geoids would be worthwhile. But as you go from plane -> sphere -> spheroid -> geoid, computing resources must incr…

The German “ICON” model uses a spheroid shape that escapes me right now, but each grid cell is effectively a triangle. Most others are gridded squares.
Post reply on HN