Posted on 01/19/2024 1:05:22 PM PST by Red Badger
Using AI and cloud computing, Microsoft was able to identify promising new battery materials for the Department of Energy (DoE) — in a fraction of the time it would usually take.
The challenge: Batteries are an essential part of the clean energy future. We need them to power electric vehicles and to store energy from solar and wind.
Currently, lithium-ion batteries are our best option for both of these uses, but they aren’t ideal. Because lithium is relatively scarce, it’s also expensive, and the metal is often unethically mined using child labor and environmentally destructive processes.
Identifying better battery materials is a time-consuming process, though.
“It’s always trial and error,” Vijay Murugesan, head of the Material Sciences Group at the DoE’s Pacific Northwest National Laboratory (PNNL), told Fast Company.
“Something comes up in my dreams or the shower, and then I come in and spend two years testing whether it works or not, and then you go back and do that cycle again for a decade,” he continued. “The success rate is not that great, to be honest.”
What’s new? To speed up that process, PNNL teamed up with Microsoft.
Using a combination of AI models and cloud computing, the tech giant simulated potential chemical combinations for batteries, starting from a list of 32.6 million materials. Within just 80 hours, it had identified 18 promising candidates for new battery materials.
“Something that could have taken years, we did in two weeks,” Jason Zander, an executive VP at Microsoft, told Reuters.
Looking ahead: PNNL scientists have already synthesized one of the candidate battery materials for testing — if it performs well, it could enable production of batteries containing 70% less lithium.
They also expect Microsoft’s technology to lead to the discovery of far more than just new battery materials.
“That’s the part we’re most excited about … We just picked one problem,” said Zander. “There are thousands of problems to go solve, and it’s applicable to all of them.”
VIDEO AT LINK....................
This isn’t a commercial for AI. I is a programing tool for gettin g rid of fossel fuels. Batteries cannot produce power, they only store. so trying to get enough solor and wind turbines to do what they need is going to be impossible as it already has proven inadequate.
Wind turbines need an unchanging and uninterrupted flow of air to work effectively, which means there must be no obstructions nearby. Researchers have suggested that for residential wind turbines 150 meters away from nearby obstructions is enough. In the case of wind farm spacing, turbines need to be at least 7 rotor diameters away from each other. A wind turbine is most effective when it operates in a steady, smooth, unchanging and uninterrupted flow of air. That never happens in the real world, but when planning where to install a wind turbine the locations has to be as close as possible to the ideal.
It is estimated by Forbes it would take 1.26 million turbines to power the US at a minimum. They would have to be located in the midwest as that’s where more of the workable wind is on the plains. So which states are they going to eliminate of people?
wy69
“Mathematics for Machine Learning”
“Probabilisc Machine Learning”
“Machine Learning for Imbalanced Data”
“Machine Learning Engineering”
“Support Vector Machines”
A few books I’ve studied since I ‘retired” from a career in Software Engineering. Got to keep going, got to keep the ‘imbalanced’ mind sharp. Regards.
Not specifically about AI, but "Click here to kill everyone" by Bruce Schneier will make you think a bit.
“12,000 watts per gallon.”
We know that the author of the above failed 9th grade science!
I’d rather they work on a Mr. Fusion instead.
In a world of wires and circuits so neat,
Let’s explore AI, a technological feat!
Pros of AI, let’s start with the pluses:
1. Efficiency supreme, no human excuses!
2. Learning and adapting, it’s clever and wise,
Solving complex problems right before our eyes.
3. Speedy computations, it’s quick as a breeze,
Crunching big data with utmost ease.
4. Repetitive tasks? AI takes the load,
Humans can focus on things that explode!
5. Medical diagnoses, it’s remarkably keen,
Detecting diseases we’ve never foreseen.
But now, let’s flip the coin and see,
The cons of AI, as it might not always be glee:
1. Job displacement, a workforce concern,
AI could replace jobs, that’s something to discern.
2. Privacy invasion, it’s a hot debate,
Personal data security, don’t underestimate!
3. Bias and discrimination, it can perpetuate,
If not trained right, it might discriminate.
4. Dependence and addiction, a real conundrum,
Relying on AI for everything, we might become numb.
5. Unpredictability, sometimes it may glitch,
We can’t always predict how AI will pitch.
So, in the world of AI, it’s vital to see,
Both pros and cons in this technology spree.
With careful development and ethical care,
We can navigate AI’s challenges and fare!
It's just a program written by someone.
This is DEFCON One for the environmentalists and socialists (but I repeat myself): 18 promising new energy technologies to shut down before they open the door to a growing and prosperous future for a free society.
Wondeful! Now China can corner the market on those materials!
What about the ability to charge those batteries? Any AI consulted on how to increase the production of electricity to do the charging of the storages?
Very un-amazing.
There are LOTS of possible battery solutions out there.
Finding one that doesn’t catch fire, explode or needs a special env to work is the hard part.
Yeah, and some of it would burn through metal like xenomorph blood. Others would be dangerously volatile or flammable. And, of course, belching poisonous fumes if struck in traffic and ruptured.
Too bad the world will end before that. How many years left? 7.62?
I wonder if some long-unsolved mathematics theorems could be solved by AI.
This is the chart I used to make my comparison.
Gasoline has about 13,000 MJ/kg in energy and lithium ion batteries about 0.46-0.72 MJ/kg.
The figure I used was just the top of my head
https://en.wikipedia.org/wiki/Energy_density_Extended_Reference_Table
“You don’t scare me. Work on it.”
Sorry. 13MJ/kg
For all the hype, this is literally the first time I have heard about something potentially useful produced by AI.
It seems like doing legal work would be quite straight forward, but I cannot recall seeing anything like that, except for passing the LSAT exam or state Bar exams.
Pharmacology seems like an obvious AI gold mine, but I do not recall hearing about any new treatments or re-purposed drugs.
HUMANS will need to test the AI’s theories out. AI did not discover anything. It produced some suggestions, not knowing anything about the subject.
Here’s a thought: If AI is so “smart”, can it generate bitcoins? That would be the end of crypto currencies.
Disclaimer: Opinions posted on Free Republic are those of the individual posters and do not necessarily represent the opinion of Free Republic or its management. All materials posted herein are protected by copyright law and the exemption for fair use of copyrighted works.