Posted on 07/10/2023 3:24:20 PM PDT by nickcarraway
By harnessing patterns in mineral associations, a new machine-learning model can predict the locations of minerals on Earth and potentially, other planets. This advancement is of immense value to science and industry, as they continually explore mineral deposits to unravel the planet’s history and to mine resources for practical applications, such as rechargeable batteries.
A team led by Shaunna Morrison and Anirudh Prabhu aimed to develop a method for identifying the occurrence of particular minerals, an objective that has traditionally been considered as much an art as it is a science. This process has often been dependent on individual experience along with a healthy dose of luck.
The team created a machine learning model that uses data from the Mineral Evolution Database, which includes 295,583 mineral localities of 5,478 mineral species, to predict previously unknown mineral occurrences based on association rules.
The authors tested their model by exploring the Tecopa basin in the Mojave Desert, a well-known Mars analog environment. The model was also able to predict the locations of geologically important minerals, including uraninite alteration, rutherfordine, andersonite, and schröckingerite, bayleyite, and zippeite.
In addition, the model located promising areas for critical rare earth elements and lithium minerals, including monazite-(Ce), and allanite-(Ce), and spodumene. Mineral association analysis can be a powerful predictive tool for mineralogists, petrologists, economic geologists, and planetary scientists, according to the authors.
Reference: “Predicting new mineral occurrences and planetary analog environments via mineral association analysis” by Shaunna M Morrison, Anirudh Prabhu, Ahmed Eleish, Robert M Hazen, Joshua J Golden, Robert T Downs, Samuel Perry, Peter C Burns, Jolyon Ralph and Peter Fox, 16 May 2023, PNAS Nexus. DOI: 10.1093/pnasnexus/pgad110
And when they find the minerals the enviro lobby will sue to keep anyone from mining them
Tell Musk to start mining asteroids.
I cannot express how annoying the “AI” buzzword is becoming. It’s a carefully tuned associative algorithm, no different than what we’ve been using for decades but applied to a new dataset. But I guess “AI” brings the clicks.
They should search for Bidenite...there’s infinite money buried there.
A major research institution has just announced the discovery of the densest element yet known to science. The new element has been named Pelosium.
Pelosium has one neutron, 12 assistant neutrons, 75 deputy neutrons, and 223 assistant deputy neutrons, giving it an atomic mass of 311.
These particles are held together by dark forces called morons, which are surrounded by vast quantities of lepton-like particles called peons.
The symbol of Pelosium is PU.
Pelosium’s mass actually increases over time, as morons randomly interact with various elements in the atmosphere and become assistant deputy neutrons within the Pelosium molecule, leading to the formation of isotopes.
The characteristic of moron-promotion leads some scientists to believe that Pelosium is formed whenever morons reach a certain quantity in concentration. Author, unknown.
Please, use caution when coming into contact with this unstable matter.
By Lorra B. Chief Writer for Silent Soldier
Don’t they need them for all the EVs they mandated?
The day AI can understand a women I will pay attention.
As a well experienced gold miner and assayer I know by experience that mineral associations are important, but by no means infallible. In the case of gold, it is almost always associated with quartz of some variety or other, and/or iron, usually iron sulphide. Without one or both of those you will almost NEVER find gold. But it doesn’t work in the other direction, for the vast majority of quartz and iron deposits contain little if any gold. I am guessing the same may be true of this AI process, and that rare earth minerals, like gold, are “where you find them”. Nothing is foolproof.
Humans are a mistake of evolution, and weren’t meant to survive. Humans have no fur for warmth or protection from some injuries or predators, no fangs, no claws, are relatively weak for their body mass and can○t run for crap to avoid getting eaten by other animals.
Men should have been extinct long ago, but they survived because of a genetic mutation which gave them reasoning ability. Women are men’s penance for surviving.
Now this is a valid use for AI.
Most rare earths aren’t all that rare, they occur in forms that are difficult and expensive to refine.
Unfortunately when that day comes you won't be able to understand the AI anymore.
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.