Uncle Sam to blow millions on getting fusion power finally working – with the help of AI
- Reference: 1598248987
- News link: https://www.theregister.co.uk/2020/08/24/in_brief_ai/
- Source link:
“These awards will enable fusion researchers to take advantage of recent rapid advances in artificial intelligence and machine learning,” [1]said Chris Fall, Director of DOE’s Office of Science. “AI and ML will help us to accelerate progress in fusion and keep American scientists at the forefront of fusion research.”
Fusion reactors release copious amounts of heat that, in turn, produces steam to generate electricity. Modern designs like the tokomak use a magnetic field to confine the hot plasma, but they aren’t used on industrial scales because it requires an incredible amount of energy to kickstart nuclear fusion reactions in the first place.
Still, they’re an attractive idea since the process is safer than nuclear plants and doesn’t emit pesky greenhouse gases that lead to climate change. But fusion seems to be one of those technologies that is always a decade away.
The DOE hopes that machine learning algorithms can make fusion energy more efficient. For example, AI systems could automate some control systems and help scientists analyze data to reveal the best way to operate fusion reactors.
AI portraits of Roman emperors from ancient busts
A designer has used an online tool to create photorealistic depictions of Roman emperors from historical sources.
Daniel Voshart has modeled 54 emperors so far, including Augustus, Nero and Marcus Aurelius using various software. Artbreeder uses a generative adversarial network to create the fake, digital images.
Voshart would feed the software depictions of the ancient leaders alongside color representations that he had edited in Photoshop. The outputs of Artbreeder would be fine-tuned in Photoshop and fed back into the system in a loop, until the results were good enough.
“I would do work in Photoshop, load it into ArtBreeder, tweak it, bring it back into Photoshop, then rework it,” he [2]told The Verge. “That resulted in the best photorealistic quality, and avoided falling down the path into the uncanny valley.” Sometimes he even took inspiration from real photographs of people too.
An Assistant Professor of Classics at USC has informed me that he might be the doppelgänger depiction of Numerian. [3]pic.twitter.com/0Qh66pTPpB — Dan Voshart 𓀡 𓀒 𓀓 𓀢 (@dvoshart) [4]July 29, 2020
You can see more images [5]here .
Who’s the fastest Formula One driver? Let’s ask AWS
Amazon’s machine learning algorithms have determined that the best Formula One driver since 1983 is Ayrton Senna.
AWS collaborated with F1 to analyze lap times, and took into account things like age of the driver, the number of crashes and even weather conditions to [6]rank top 20 drivers. Michael Schumacher comes in second, and Lewis Hamilton third.
“With machine learning, there are a number of opportunities to apply the technology to answer complex problems, and in this case, we hope to help settle age-old disputes with fans by using data to inform decisions,” said Priya Ponnapalli, a principal scientist and senior manager at Amazon’s ML Solutions Lab.
Amazon’s results just didn’t sit right with everyone, however. So much so that F1’s managing director Ross Brawn issued a statement supporting the algorithm to reporters. “There’s been one or two surprises but when you delve into it, there’s a certain amount of sense,” Reuters [7]reported . ®
Get our [8]Tech Resources
[1] https://www.energy.gov/articles/department-energy-provide-21-million-artificial-intelligence-and-machine-learning-research
[2] https://www.theverge.com/2020/8/21/21395115/roman-emperors-photorealistic-portraits-ai-artbreeder-dan-voshart
[3] https://t.co/0Qh66pTPpB
[4] https://twitter.com/dvoshart/status/1288619015947067392?ref_src=twsrc%5Etfw
[5] https://medium.com/@voshart/photoreal-roman-emperor-project-236be7f06c8f
[6] https://www.formula1.com/en/latest/article.hamilton-schumacher-senna-machine-learning-reveals-the-fastest-f1-driver-of.3DwwPLW4glCmlunjciH1Cz.html
[7] https://www.reuters.com/article/us-motor-f1-fastest-idUSKCN25F2NV
[8] https://whitepapers.theregister.com/
Re: But how long will it take to get there?
I reckon that we would have abandoned nuclear fusion research decades ago, if it wasn't for the giant fusion ball in the sky that keeps telling everyone that this technology does work. All science has to do is miniaturise it a little bit. Apparently miniaturizing what the sun does is not as simple as shrinking transistors.
Re: But how long will it take to get there?
"Let me guess - with these advances, experts predict we'll have fusion power for the masses in 20 years?"
Thirty years is the "traditional" value. It has held good for all of my life, which started a long time ago.
[1]"Nuclear fusion energy is 30 years away...and always will be."
[1] https://spectrum.ieee.org/energy/nuclear/5-big-ideas-for-making-fusion-power-a-reality
Fusion reactor safe?!!!!
Saying a fusion reactor would be safe ... doesn't make it safe.
See https://thebulletin.org/2017/04/fusion-reactors-not-what-theyre-cracked-up-to-be/
The saving grace for fusion reactors is that they are unlikely to ever exist, happily obviating all safety concerns.
IMO, the main reason governments fund fusion research (with paltry budgets) is to keep their nuclear genii busy and satisfied at home. This to forestall them being lured to go work in Pakistan or Russia on their nuclear projects, ones that are actually practical and nothing to do with cutting carbon.
A secondary reason is to keep punters and the Readers Digest set lulled into a sense of security about the future. Like my uncle who smoked all his life, saying "By the time I get cancer, they'll have found a cure for it" .
Re: Fusion reactor safe?!!!!
That article is one hell of a wet blanket on my fusion enthusiasm. If what he says is true, we're better off with [1]thorium reactors .
[1] https://en.wikipedia.org/wiki/Thorium-based_nuclear_power
Re: Fusion reactor safe?!!!!
The article doesn's say "safe". It says "safer than nuclear [fission] plants". That's a simplification, of course, but it's a very reasonable assertion. A fusion plant cannot melt down, and the link you posted does not dispute that. It is not "safe" in an absolute sense, which is also true of pretty much every large-scale power generation method.
Arrrrrrghhh soundbites!
Each of these tiny snippets is worthy of a proper article in its own right. Is El Reg running out of willing contributors?
“These awards will enable fusion researchers to take advantage of recent rapid advances in artificial intelligence and machine learning,”
If only they'd put Blockchain in too then the problem would have been solved already...
Surely you mean...
Blockchain reaction?
F1
I've not looked in huge detail at the F1 analysis, but I think it's based on qualifying 'raw' speed, the main comparison being against teammates. I have my doubts about the accuracy and usefulness of the outcome.
Not all teammates are equal, but even if this is taken into account there will still be large areas of bias. Not all teams treat their drivers equally, not all cars are produced or specified equally (in the same team), some teams technical development direction will be specifically to suit their number 1 driver, and some drivers (those experienced and talented enough) will sacrifice their qualifying setup for better race pace. The list goes on I'm sure. It's as much a talking point generator than a meaningful analysis.
And even after all that, raw qualifying speed is only one part of being the best 'complete package' F1 driver. I've watched it for a long time, and I would put Hamilton right at the top of this list. It's a privilege to witness the levels of performance he has reached.
But how long will it take to get there?
Let me guess - with these advances, experts predict we'll have fusion power for the masses in 20 years?