Huh, I was just watching a YouTube video that claimed the limited ability of China to predict weather in the Taiwan Strait is a factor in what makes it hard to invade.
DeepMind's WeatherNext model achieves breakthrough forecasting cyclones
121–130 of 143 posts
Re: DeepMind's WeatherNext model achieves breakthrough forecasting cyclones
#122Earlier quoted context omitted.
How does predicting a typhoon prevent billions in damage? It could save thousands of lives because people can be evacuated if you can predict a few hours or a day further ahead, or the path more accurately. You can save some damage by moving ships and vehicles. But you can't evacuate buildings or infrastructure.
It could save billions by raising confidence in predictions. Bad predictions have a “boy who cried wolf” aspect.
Why does it matter when potus draws the expected path with a sharpie anyway?
Re: DeepMind's WeatherNext model achieves breakthrough forecasting cyclones
#123Earlier quoted context omitted.
shareholders are pretty unhappy about demis. think about alphafold. huge investments from the company, tens of billions. at a critical time. and absolutely 0 revenue. it got demis a nobel though. as a shareholder you'd be unhappy too.
As a shareholder I am up 75% in a year. Alphafold gained experience makes them better suited to succeed with Isomorphic Labs than anyone else. Research on improved translation gave us the transformer. If you think AI will win but Google will continue failing, there so many better places to allocate your capital right now.
I guess so. Probably i was being greedy. But there is a feeling in investment community that google open sources too much
Re: DeepMind's WeatherNext model achieves breakthrough forecasting cyclones
#124Earlier quoted context omitted.
> You can board up a helluva lot more stuff in a week than in two days TFA says they might be able to predict one extra day ahead (three days instead of two). No prediction system will ever give you a week's notice on a typhoon.
Actually it doesn't even say that - they claim to have the same "accuracy" at 3 days that older methods have at 2 days. What does that actually get you? Were the older models so much less accurate at 3 days (compared to 2) that it prevented evacuation of key areas? Looking at the paper, it doesn't really seem like this can be answered yet because there's not enough data over a long enough time. Keep in mind, DeepMind…
I wish there was a way that your comment could be pinned.
The context is so important here and radically re-frames the impact of GDM's results. Folks need to understand that with modern forecasting tools, we anticipate tropical cyclones to develop 5-10 days before they ever threaten landfall. The "2-day" vs "3-day" improvement in forecast skill is better interpreted as a modest reduction in forecast uncertainty - the "cone" on the hurricane track map gets a little narrower.
It's not like there's a "literal extra day" of preparation time for folks who may be impacted by the storm. They get the same amount of time they always have. Nothing actually changes on-the-ground for really any consumer of hurricane forecast data anywhere in the world.
And that's not a sleight against GDM. It's just a simple statement of how good contemporary weather forecasting is, and how good it was before AI forecast models came onto the scene some 5 years ago.
Re: DeepMind's WeatherNext model achieves breakthrough forecasting cyclones
#125Earlier quoted context omitted.
I know this is uncharitable and I am wrong but I am having trouble coming up with concrete scenarios where you die with 2 days notice but survive with 3. I am nonethless a believer that more accurate forecasting has value.
Hurricane Maria went from Cat 2 to Cat 5 in less than 24 hours, and turned making a direct hit to Dominica in 2017.
It was also forecast by virtually every NWP system multiple days ahead of time that it would make this intensification.
Re: DeepMind's WeatherNext model achieves breakthrough forecasting cyclones
#126Earlier quoted context omitted.
Traditional physics based weather models also rely heavily on physical parameterization for sub grid scale processes (think clouds, microphysics of rain sleet snow, etc) so even the deterministic physics models are learned approximations from data.
traditional physics-based weather models also rely heavily on humans looking at the output and the evaluation of the output to discard wacky runs. Let's not pretend that existing physical models of the atmosphere stay on the rails all the time.
When you say runs that is an ensemble model forecast which is different than a deterministic model forecast. Any type of weather model sensitive to initial input state errors will have outlier model runs.
Re: DeepMind's WeatherNext model achieves breakthrough forecasting cyclones
#127Earlier quoted context omitted.
I'm interested in understanding wheater prediction models because accurate wind forecasts make a big difference to my personal life (sports). Is there a good overview to learn about the current models, which all just seem like cryptic acronyms to me? in apps like Windy etc. WRF, TRRM, IK-HRRR-3km, ECMWF-9km,... I understand by now that small grid cells are better for local prediction and that thermic winds are mostly…
Ask your favorite AI to give you a crash course, but to start the main models you need to know are the GFS and the ECMWF. In the US where available in high res, the HRRR is excellent, but doesn’t forecast very far out. The PWG/PWE 1km PredictWind models are also very good at picking up land based features and other more precise patterns. If you are in the US everything else is probably not super relevant.
Any advice will really depend on where you live and the dominant source of local error. These are all good options for the US and if the one main source of error is near surface winds around complex terrain then you can also look into WindNinja from the National Forrest Service.
Re: DeepMind's WeatherNext model achieves breakthrough forecasting cyclones
#128Re: DeepMind's WeatherNext model achieves breakthrough forecasting cyclones
#129call me a cynic, but in the age of government underinvestment in science, isn’t this how google could actually change the world?
Re: DeepMind's WeatherNext model achieves breakthrough forecasting cyclones
#130Predicting big weather events is not that hard even with 50 year old technology. What's hard is predicting details, like exactly where it will rain, what the slope of the beach is today (many people don't even know this changes drastically daily and why it is important), wave height, ocean depth today where people swim, water temperature, shorebreak, and knowing with certainty when rain becomes ice/sleet/snow and wha…
> what the slope of the beach is today (many people don't even know this changes drastically daily and why it is important So why is it important? As far as I know the slope changes AFTER the weather not before as a prediction mechanism but happy to learn
It changes constantly on a daily cycle and also on a larger seasonal cycle.
Slope defines the water depth and what kind of beach it is - long flat beach means shallow water, steep beach means deep water - it affects if you can you fish there, route lagoon systems and seasonal floodwater, do sports like surfing and skimboarding which are highly dependent on it to the point you can only do it some times of day only part of the year, and other things like whether or not it’s safe to be on that day for visitors.
In California, a beach can be flat and inches deep in the Spring at low tide, and be 20ft deep in Winter at high tide with a massive hill you can’t even stand on with basically a river running thru it. That same massive hill can turn into a literal cliff drop off 25ft to a flat beach below overnight. So you come back 24h later and it’s a massive cliff now. Come back 8 hours after that and it’s like a massive flat puddle revealing hundreds of yards of exposed land.
It’s not random either, it happens in cycles that you observe if you go there daily to fish or surf, but none of the weather or surf apps can ever predict it.
A great example is the amazing skimboarding conditions in Laguna Beach and Santa Cruz during the fall (October, November) there's nothing like it anywhere else in the world.
Another good example is surfing the winter swell in Santa Cruz, when a good majority of the beach disappears underwater for months. A wave you're surfing on Halloween is where someone will be laying out tanning in June.