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

GraphCast: AI model for weather forecasting

deepmind.google

Post reply on HN
Print view View original

261–270 of 310 posts

Re: GraphCast: AI model for weather forecasting

#261

Post by ellisv »

TSiege wrote: post #259
eppp wrote: post #256

Earlier quoted context omitted.

It still is. I farm outside of my day job and trying to schedule time to do things like cut hay is sort of a crapshoot. Hay needs a 3-4 day window to dry, rake and roll. This year I got rained on at least twice on days where the NWS showed clear and sunny for 3 days on the spot forecast. 20% or 50% chance of rain is almost useless knowledge. We went for weeks with a 20% chance and it never rained. We still got everyt…

Well it's actually not a 20% or 50% chance of rain. It's that it will definitely rain but only for 20-50% of the projected area forecasted

This is exactly wrong.

> The "Probability of Precipitation" (PoP) simply describes the probability that the forecast grid/point in question will receive at least 0.01" of rain.

[1] https://www.weather.gov/ffc/pop

It is worth noting the estimate is an areal average.

Re: GraphCast: AI model for weather forecasting

#262

Post by mike-cardwell »

tomesco wrote: post #253
patall wrote: post #250

Earlier quoted context omitted.

Isn't that highly subjective to where you live? Because I moved to Scandinavia and the forecast here is so incredibly bad, compared to central europe.

Yes, driven by local data collection. More tightly packed ground stations and the availability of atmospheric measurement at various altitudes will improve accuracy.

Also, the weather is just a lot more predictable in some areas than others.

Re: GraphCast: AI model for weather forecasting

#263

Post by londons_explore »

mike-cardwell wrote: post #262
tomesco wrote: post #253

Earlier quoted context omitted.

Yes, driven by local data collection. More tightly packed ground stations and the availability of atmospheric measurement at various altitudes will improve accuracy.

Also, the weather is just a lot more predictable in some areas than others.

I think it's mostly this. If you look at a weather radar map, sometimes you see a speckled pattern of rain where there is heavy rain in places, and 100 yards away there is no rain at all. No way you can predict that multiple days out.

Re: GraphCast: AI model for weather forecasting

#264

Post by obscurette »

mike-cardwell wrote: post #262
tomesco wrote: post #253

Earlier quoted context omitted.

Yes, driven by local data collection. More tightly packed ground stations and the availability of atmospheric measurement at various altitudes will improve accuracy.

Also, the weather is just a lot more predictable in some areas than others.

This. Just some days ago I had a conversation with meteorologist who said exactly this - the weather has never been easy to predict in northen Europe and it has become even less predictable with climate change and global warming.

Re: GraphCast: AI model for weather forecasting

#265

Post by Kye »

mike-cardwell wrote: post #262
tomesco wrote: post #253

Earlier quoted context omitted.

Yes, driven by local data collection. More tightly packed ground stations and the availability of atmospheric measurement at various altitudes will improve accuracy.

Also, the weather is just a lot more predictable in some areas than others.

I feel this living in the path of moisture coming from the Gulf of Mexico. My phone has gotten good at letting me know when the rain will start and stop to within a few minutes, but whatever data source Apple uses still struggles with near-term prediction (day+) in the summer when there are random popup storms all the time.

Re: GraphCast: AI model for weather forecasting

#266

Post by londons_explore »

isaacfrond wrote: post #191

I find this quite surprising actually. You'd think predicting the weather is mostly a matter of fast computation. The physical rules are well understood, so to get a better estimate use a finer mesh in your finite element computation and use a smaller time scale in estimating your differential equations. Neural networks are notoriously bad at exact approximation. I mean you can never beat a calculator when the issue…

Shortcuts 100% exist.

Imagine another physical problem. Simulating a sand grain and how it bounces off other sand grains or lodges against them. If you wanted to simulate a sand mountain, you could use a massive amount of compute and predict the location and behaviour of every single grain.

Or, you could take a bunch of well-known shortcuts and just know that sand sits in a heap at the angle-of-repose. That angle decides how steep the mountain will be. any steeper and it will tumble till it's at that angle.

Suddenly, the computation is dramatically reduced, and you get pretty much the same result.

Re: GraphCast: AI model for weather forecasting

#267

Post by crazygringo »

DaiPlusPlus wrote: post #210
ArnoVW wrote: post #202

Earlier quoted context omitted.

It’s difficult to retain top talent if you do not allow them to publish.

How does Apple do it, if anyone knows? Apple is so loathe to keep their potential product plans hidden that AAPL employees aren’t even allowed to have GitHub accounts without mgr approval… but they have to be employing serious researchers, but they’ll never get to publish on volition.

Does Apple do it?

They don't seem to be on the forefront of the AI train at all. They haven't been building AI products the way Google and Microsoft have been. Siri has been stuck for a long time.

When I think of Apple, I think of a lot of things, but AI is not on that list.

Re: GraphCast: AI model for weather forecasting

#268

Post by aaarrm »

meteo-jeff wrote: post #20

In case someone is looking for historical weather data for ML training and prediction, I created an open-source weather API which continuously archives weather data. Using past and forecast data from multiple numerical weather models can be combined using ML to achieve better forecast skill than any individual model. Because each model is physically bound, the resulting ML model should be stable. See: https://open-me…

This is awesome. I was trying to do a weather project a while ago, but couldn't find an API to suit my needs for the life of me. It looks like yours still doesn't have exactly everything I'd want but it still has plenty. Mainly UV index is something I've been trying to find wide historical data for, but it seems like it just might not be out there. I do see you have solar radiation, so I wonder if I could calculate it using that data. But I believe UV index also takes into account things like local air pollution and ozone forecast as well.

Re: GraphCast: AI model for weather forecasting

#269

Post by empath-nirvana »

isaacfrond wrote: post #191

I find this quite surprising actually. You'd think predicting the weather is mostly a matter of fast computation. The physical rules are well understood, so to get a better estimate use a finer mesh in your finite element computation and use a smaller time scale in estimating your differential equations. Neural networks are notoriously bad at exact approximation. I mean you can never beat a calculator when the issue…

> Neural networks are notoriously bad at exact approximation.

Neural networks can compute pretty much anything. There's no reason, given the same inputs and with enough trainining data that it shouldn't be able to discover the same physical laws that were hard-coded previously.

Re: GraphCast: AI model for weather forecasting

#270

Post by T-A »

isaacfrond wrote: post #191

I find this quite surprising actually. You'd think predicting the weather is mostly a matter of fast computation. The physical rules are well understood, so to get a better estimate use a finer mesh in your finite element computation and use a smaller time scale in estimating your differential equations. Neural networks are notoriously bad at exact approximation. I mean you can never beat a calculator when the issue…

https://www.science.org/content/article/models-galaxies-atom...

https://towardsdatascience.com/physics-informed-neural-netwo...

https://maziarraissi.github.io/PINNs/

https://arxiv.org/abs/2001.08055

https://arxiv.org/abs/2009.11990

Post reply on HN