The Wild New Materials of the Future Will Be Discovered With AI
My GAWD! An honest journalist. Well I guess there had to be one somewhere, there are so many of them. The law of large numbers predicts it. But I digress.
This is actually a pretty interesting article. He says..
The way I think about materials science is that it’s about stuff. That’s also how I think about parts of engineering and manufacturing. It’s about putting stuff together. The quality of your finished product relies on the quality and abilities of the stuff used to make it.
Excellent point. One of the early problems with airplanes was the 'stuff' they originally tried to make them out of had a poor strength to weight ratio. The 'stuff' was mostly wood which was too weak to handle large loads and then along came steel, alumuminium and composites. Building airplanes wasn't so hard anymore. It's even easier now. People even build them in their home workshops.
He did that with ordinary materials bought from the lumber yard and/or ordered on line with ordinary hand tools. Imagine what he (or his children) will be able to do with next generation materials.
Speaking of unorthodox flying machines. Don't look at this. Just. Don't.
I suppose it COULD be CGI...maybe. But this?
Moving on.
Among the new materials listed in the article are:
Superconductors :“We have a list of all superconductors that we know of, but we still don’t have a good way of figuring out if something is going to be a superconductor. I applied machine learning to the process to help find ways to develop such a framework,” he explains.
A superconductor that operates at room temperature would be a game changer. Technology and subsequently our world would be revolutionized.
Stanev sees big potential for machine learning in other areas too, such as the development of thermoelectric materials, which absorb heat and turn it into electricity.
Embrace the power of AND. High effeciency Thermoelectrics AND room temp. superconducters. Mind Boggling.
furthermore
Another unsolved challenge? How to turn new, theoretical materials science insights into actual materials and solutions—especially on an industrial scale.
Graphene comes to mind. Carbon is a wonder material. It has many allatropes among which is graphene. If (when) Graphene could be produced in industrial quantities everything I said about Thermoelectrics and SuperConductors to the next level. Oh..did I mention that Graphene is the best electrical conductor known, better than silver. It's also a hundred times stronger than steel...and stuff...
But back to the article in which the author quotes scientists who speak of 'machine learning'. That means computers.
with the advent of Quantum Computing there is no end in sight as to how powerful computers may become.
With the advance in materials technology there is no end in sight as to how cheap they may become.
One of the material scientists said.
“You can have a machine learning toolbox built into your experimental setup. It looks at the results coming out of the experiment and can algorithmically decide what experiment to do next and from these deduce the general outcome of a series of experiments. In a way, you may only need to run 10 or 20% of the experiment to get the full picture,” he explains.
“Many of these advances are not nearly as far off as people think—in many cases we are talking a few years, tops. A lot of people in the community have a sense of, ‘What the hell just happened?’ Hopefully, others will too,” he says with a semi-laugh.
A semi laugh huh?
Is that the kind of laugh he makes when some kid in one of today's third world nations combines all of the above and does what they are talking about in his hut a jungle somewhere? Yeah..go ahead and laugh. Remember apple? It was invented by a teenager in a third world failed state...california.
OH! One more thing...
ok. Never argue with a democrat.