Live data from Hacker News

USGS uses machine learning to show large lithium potential in Arkansas

usgs.gov

111–120 of 237 posts

Re: USGS uses machine learning to show large lithium potential in Arkansas

#111
Ah spatial autocorrelation, my old friend.

Very good work - but typically we don't build prospectivity models this way (or rather we don't validate them this way anymore). Great to see the USGS starting to dip their toe back in this though, they and the GSC were long the leaders in this, but have dropped it on the last 5-7 years.

Re: USGS uses machine learning to show large lithium potential in Arkansas

#112
post #90
post #66

Earlier quoted context omitted.

Are we getting to the critical point where we declassify a bunch of stuff as AI? Used to be expert systems were considered AI. Now anything-not-an-LLM is going to stop being AI?

That treadmills been going on for a long time. Didn’t OCR used to be classified as AI?

Yep, back when programming language syntax started trending toward more natural language, compiler development was considered AI research. Which makes sense, because in an era of assembly on punch cards, computers that could translate higher-level instructions that read more like English into machine code you used to have to write (or punch) by hand probably felt pretty intelligent.

Re: USGS uses machine learning to show large lithium potential in Arkansas

#113
Well I guess this is a good win for short term energy infrastructure, though I'm always pretty torn when its at the cost of ripping open huge swaths of earth to get at the raw material.

It is interesting to see how much of this data could be modelled based on wastewater brines from other industries in the area, assuming we go on to mine the lithium it will say a lot if the ML predictions prove accurate.

One thing I couldn't tell, and its probably just a limitation of how much time I could spend reading the source paper, is what method would be needed to extract the bulk of the lithium expected to be there. If processing brine water is sufficient that may be easier to control externalities than if they have to strip mine and get all the overburden out of the way first.

Re: USGS uses machine learning to show large lithium potential in Arkansas

#114

There's also a big lithium deposit in Nevada, and preparations for mining are underway there.[1] General Motors put in $650 million for guaranteed access to the output of this Thacker Mine. It's in a caldera in a mountain that I-80 bypassed to go through Winnemuca, Nevada. Nearest town is Mill City, NV, which is listed as a ghost town, despite being next to I-80 and a main line railroad track. The mine site is about…

Your description of the location of this mine doesn't match your Wikipedia link. Searching in Google Maps, Thacker Mine comes up as 40.58448942010599, -117.8912129833345. As you say, that is near I-80 and Mill City, and there is nothing there. But Wikipedia says it's at 41.70850912415866, -118.05475061324945 in the McDermitt Caldera, nowhere near Mill City or I-80. I'm thinking probably don't trust Google on this one…

Right. The Nevada Appeal, which actually has people on the ground, has far more info.[1] North of Thacker Pass is the area to look. The mine is building their own rail yard west of Winnemuca. The mine will be an open-pit mine like a coal mine. Sawtooth Mining division of North American Coal will do the mining. Dig down 350 feet, take out clay with lithium, process, put back clay without lithium. The processing plant will be at Thacker Pass. Big plant, maybe 1800 people. Lithium in clay is a new thing - the usual input is brine. Also a sulfuric acid plant, a power plant, housing, etc. Project assumes a loan of US$2.3 billion from the U.S. Department of Energy.

"Lithium Americas will contract with a bus company to drive workers an hour to the site for 10-hour work shifts, he added. An additional two hours will be added for transportation time. If you go to work on our project, you will have free room and board and free transportation to the site every day. You would get three free meals a day." If you're an unemployed coal miner in West Virginia, that might look good.

[1] https://www.nevadaappeal.com/news/2024/oct/12/nevada-operati...

Re: USGS uses machine learning to show large lithium potential in Arkansas

#115

ugh i really don't want people to mine in the mobile basin. that's one of the most diverse ecosystems in north america. https://www.youtube.com/watch?v=8j9coyJeB4Q

A significant reason the real holders of power in the world today are Saudi Arabia and China is because we've refused to gather and use our resources while they have theirs. It's high time we realize that Pax Americana is our era to lose, (re)start mining and (re)start development.

the mobile bay already has a lot of oil mining: https://www.google.com/search?client=firefox-b-1-d&q=oil+rig...

we don't need it happening upstream.

and watch as the nations destroy themselves (ecosystems)

Re: USGS uses machine learning to show large lithium potential in Arkansas

#116
post #21

From the paper's method section, a bit more about which type of ML algo was used: An RF machine-learning model was developed to predict lithium concentrations in Smackover Formation brines throughout southern Arkansas. The model was developed by (i) assigning explanatory variables to brine samples collected at wells, (ii) tuning the RF model to make predictions at wells and assess model performance, (iii) mapping spa…

Put another way, this is pretty similar to the interpolation approaches that would normally be used for datasets like this in the world of mineral exploration. Kriging/co-kriging (i.e. gaussian processes) is the more commonly used approach in this particular field due to both the long history and the available hyperparameters for things like spatial aniostropy.

However, kriging is really quite difficult to use with non-continuous inputs. RF is a lot more forgiving there. You don't need to develop a covariance model for discrete values (or a covariance model for how the different inputs relate, either).

Re: USGS uses machine learning to show large lithium potential in Arkansas

#117

There's also a big lithium deposit in Nevada, and preparations for mining are underway there.[1] General Motors put in $650 million for guaranteed access to the output of this Thacker Mine. It's in a caldera in a mountain that I-80 bypassed to go through Winnemuca, Nevada. Nearest town is Mill City, NV, which is listed as a ghost town, despite being next to I-80 and a main line railroad track. The mine site is about…

Your description of the location of this mine doesn't match your Wikipedia link. Searching in Google Maps, Thacker Mine comes up as 40.58448942010599, -117.8912129833345. As you say, that is near I-80 and Mill City, and there is nothing there. But Wikipedia says it's at 41.70850912415866, -118.05475061324945 in the McDermitt Caldera, nowhere near Mill City or I-80. I'm thinking probably don't trust Google on this one…

Looks like Google got "Thacker Pass Lithium Mine" in the McDermitt Caldera confused with an old gold mine called "Thacker Placer Mine" that was southeast of Mill City: https://westernmininghistory.com/mine-detail/10042614/

Re: USGS uses machine learning to show large lithium potential in Arkansas

#118
post #21

From the paper's method section, a bit more about which type of ML algo was used: An RF machine-learning model was developed to predict lithium concentrations in Smackover Formation brines throughout southern Arkansas. The model was developed by (i) assigning explanatory variables to brine samples collected at wells, (ii) tuning the RF model to make predictions at wells and assess model performance, (iii) mapping spa…

Did they actually verify the predictions? In my reading of the article I didn't see any core samples being made to verify the model is correct.

There wouldn't be any core for this. It would be a holdout of the brine samples used in training. The thing that would be being produced is brine, so lithium concentrations in brine samples are the validation dataset as well. In other words, this is spatial interpolation.

Re: USGS uses machine learning to show large lithium potential in Arkansas

#119

Well I guess this is a good win for short term energy infrastructure, though I'm always pretty torn when its at the cost of ripping open huge swaths of earth to get at the raw material. It is interesting to see how much of this data could be modelled based on wastewater brines from other industries in the area, assuming we go on to mine the lithium it will say a lot if the ML predictions prove accurate. One thing I c…

You physically can't remove the overburden for this. The Smackover is at a depth of multiple kilometers in most of these areas.

It's mining brine. I.e. the "mines" are basically deep water wells.

The limestone itself doesn't have any lithium. It's the water in the pores in the limestone that is relatively concentrated in lithium.

In most of these cases, you're already producing brines from the smackover formation as a part of existing oil and gas production, but the brine is being re-injecting after oil is separated from it. The idea is that it's better to keep those and evaporate them down for lithium production.

That does require large evaporation ponds, generally speaking, but it's not strip mining.

Re: USGS uses machine learning to show large lithium potential in Arkansas

#120

ugh i really don't want people to mine in the mobile basin. that's one of the most diverse ecosystems in north america. https://www.youtube.com/watch?v=8j9coyJeB4Q

A significant reason the real holders of power in the world today are Saudi Arabia and China is because we've refused to gather and use our resources while they have theirs. It's high time we realize that Pax Americana is our era to lose, (re)start mining and (re)start development.

The counter view is that it's better to save your natural resources for when you really need them and pay others to exhaust their own, rather than to exhaust yours before you have to.
Post reply on HN