Slashdot Mirror
Google's DeepMind Can Predict Wind Patterns a Day In Advance (engadget.com)
technology_dude writes: Google's DeepMind can predict wind patterns one day in advance. "Beginning last year, [Google and DeepMind] fed weather forecasts and existing turbine data into DeepMind's machine learning platform, which churned out wind power predictions 36 hours ahead of actual power generation," Engadget reports. "Google could then make supply commitments to power grids a full day before delivery." According to the report, this makes the energy generated by its wind turbines more valuable (by roughly 20%). Is this a blow to Big Blue who purchased The Weather Channel's Weather.com to showcase Watson, or is it news just because it's Google?
A butterfly flapping it's wings in Brazil?
How can they predict the clima... oh you can predict the weather now? Ok.
to predict some things.
So what? I can do that.
My predictions rarely turn out to be correct, but that's besides the point.
Actually we don't call it prediction, we call it prognosis.
And there are plenty of companies like https://www.windfinder.com/ who do this since decades.
Cost free eBook I read (by iBook/Kobo/Amazon/ObookO/Gutenberg etc.): "The Green Odyssey" by Philip Jose Farmer.
NOAA, The National Weather Service does ACCURATE wind forecasts days out and less accurate ones even further out than that.
Window Finder does it as well.
Even my local TV stations do it using NWS and a computer based forecasting system(not Accuweather shit).
Imagine you are Walmart. (Insert snark here) You have one of the best distribution networks ever developed at your disposal. Your biggest problem is running out while there are still customers with money to part with when inclimate weather strikes. Knowing when and where to ship needful supplies is a huge deal because of the shipping lag. You don't have to price gouge in order to make bank, just have the stuff on hand to sell. So... if you could by reliable info from a tech company like Google, there is a price you would be willing to pay... and it's not a small number.
I predict that tomorrow the winds at Goggle's offices in Playa del Rey will be light to moderate from the West. Let's see if I'm right!!!
Weather forecasting is a hard mathematical problem with thousands of variables which needs to be calculated to be precise.
The question is: does DeepMind AI/algorithm calculate the weather or it is just guessing it? If it's doing the latter then this guesswork is going to be pretty random and equally worthless, and I see no way it's gonna reach the precision of the known mathematical weather models. It might guess well in the short term (relatively few initial parameters), but in the long term I don't see it working well.
One year is a short timeline to declare success. This is a positive development but it will be instructive to see how this works over a multiyear period.
...or did I miss something special about this?
I totally need one of these in my living-room. Any advanced warning of when my old man dog farts is worth its weight in gold!
I ate chili for dinner ... I can predict tomorrow's wind patterns too!
IBM sells your location data from different apps to many people including hedge funds. This is just another way to monetize your data; it's not to predict the weather.
This means that if a calm day is predicted for tomorrow, you would know to put off running the oven and the dryer for another day.
Best go direct to the source for your answers:
Using a neural network trained on widely available weather forecasts and historical turbine data, we configured the DeepMind system to predict wind power output 36 hours ahead of actual generation.
So no, it doesn't do weather forecasts itself, but it is based on those.
Why would anyone engrave "Elbereth"?
Ah, ok, so I actually read the article (no I'm not new here). And it even says it right there in the summary, but somehow it didn't register. They are predicting wind power generation, not the wind itself!
Definitely not as impressive as my first reading. They are even using existing weather forecast data, so nothing particularly innovative here. I think there is a lot of potential to do something really cool in this area with DeepMind, though. There is a ton of historical and real-time data available.
I can't predict them correctly, but I can predict them.
This is Google we talking about. So there's an obvious big question, now that this service has proven useful: when will they discontinue it?
We have been doing this for years and this is nothing new. This is news because it has Googles name in it and the AI buzz word.
Simply astonishing what people will write up as an article and it makes as "news"
A little lesson in scientific literacy:
Algorithms, like Google's, that trawl through historical data & make predictions based on that work fine, as long as everything continues as before & nothing changes. It's a complex equivalent of continuing a straight line on a graph & calling it a prediction. It's completely useless & can even be destructive if you use it in combination with exerting influence on the system itself because biased or wrong predictions (which is always the case) create positive feedback loops that are self-reinforcing. A prime example of this abuse of data is so called predictive policing, which suffers from a negative form of the "Matthew Effect."
In contrast, a theoretical model makes predictions based on the properties, forces, & constraints on a system, be it complex (probabilities) or simple (rules). Even if conditions change, anomalies appear, etc., the model is more likely to remain reasonably predictive.
BTW, looking for patterns, regularities, etc. in data without testable hypotheses or research questions is a form of scientific malpractice called p-hacking.
Conclusions: AI is only predictive as long as nothing changes. Models or more reliable & flexible. We shouldn't stop thinking about how the world works & give it all over to mindless algorithms.
Debate is a form of harassment. Do not question my truth.
What's the accuracy of Google's prediction vs just assuming it will be the same as yesterday or the average of the last 4 days?
Hate to see such shallow linked articles on /.
One statement from Google and a bunch of links to unrelated articles on wind generation and weather.
Link to something with more than 3 asserted facts and 2 quotes from persons.
The optimal site for a wind farm?
Predictable consistent wind. Ridge lines, ocean reaches, etc. where topography and atmosphere create onshore / offshore winds, or mountain ranges channel effects.
There is a concise, succinct summary at Technology Review's “The Download” page (link below):
Ref: https://www.technologyreview.c...
Error: NSE - No Signature Error