Mariana Minerals is building the fully autonomous copper mine: 220 employees, two projects, and a plan for 10 mines in 10 years

Speaker 3: Great great

Speaker 2: to get the update. We'll see you back. Yeah.

Speaker 1: We'll have to go

Speaker 2: way deeper. In the next hopefully in the next one or two quarters.

Speaker 1: Yeah. Fantastic. Sounds good. We'll talk to

Speaker 3: you soon.

Speaker 2: See you.

Speaker 1: See Have a great weekend. Up next, we have Turner Caldwell from Marina Mariana Materials. Mariana Materials, like the Mariana Trench. We'll get into it with Turner Caldwell, the co founder and CEO. Help me understand how to pronounce this company's name. I don't wanna get it wrong.

Speaker 12: Mariana Minerals. Mariana.

Speaker 1: Where does the name come from?

Speaker 12: It comes from the Marias Trench. Mariana Trench. But that's because we were looking at

Speaker 2: guess. They've got some crazy minerals down there. Or do we even There

Speaker 12: are some minerals at the bottom of the ocean. That's right. That we So are

Speaker 2: you're saying you yearn for the trenches.

Speaker 12: That's right. There you go.

Speaker 1: Okay. The business is an autonomous copper mine. Can you take me a layer deeper, explain the history of the business, the current current shape of the business, where you where you where you're taking it all?

Speaker 12: Yeah. Sure thing. So we just restarted a copper mine that we acquired at the end of last year with a major focus on autonomy across the entire stack. So that includes the kind of orchestration layers around mining operations as well as autonomous execution, which we'll do with partners. And and then also autonomy around the refining processes. So the the site is a mine and a refinery.

Speaker 1: Yeah. But but we're In practice, what does that look like? Like, you go into the mine and there's and there's some, like, ERP system or maybe just some, like, manual paper based workflow, and you're saying, like, let's go vibe code a software solution for it? Like Yeah. Or is it like more

Speaker 12: than vibe coding. Yeah. Yeah. Basically basically, the way to think about mining is that you have a whole bunch of different disciplines that have to collaborate. It's a big coordination problem. You have geologists. You have a geologic block model.

Speaker 3: Yep. You have a

Speaker 12: mine plan. You'll usually have multiple mine plans, like a long range, medium range, and short range mine plan. Okay. That has to be transferred to the mine operations teams that are running a ton of, like, large scale or not autonomous, large scale manual Yeah. Mining equipment. Then the like, what is actually in the ore usually shows up on a piece of paper to the refinery saying, like, get ready to process this.

Speaker 1: Okay.

Speaker 12: And then the refinery the folks who are running the refinery have to figure out, like, kind of the optimal process conditions to maximize recovery of copper, lithium, nickel, cobalt, manganese, iron, graphite, kind of the whole thing. Yeah. All of the different metals through the processing circuit. And so what we're doing is we're kind of integrating everything into one, like, integrated data frame first. And so there's a lot of work that goes into kind of bringing all of the data feeds back into one, like, kind of aggregated architecture. And then we'll build world models of the mines of the refineries that we then use to kind of do a reinforcement learning training that we feed up into a reinforcement learning training pipeline. And then you wanna close the loop between what reinforcement learning agents are recommending on the policies that are developed to the actual thing that's happening in the mine. And so we'll bring autonomous haul trucks in. We'll bring autonomous drill rigs in. We'll bring in autonomous loaders and dozers and graders and water trucks, kind of like all the assets that are being used to run a mine that today are, you know, 99% of mines are are manned. And we wanna go full closed loop between kind of the world models and the reinforcement learning agents and and determining what the autonomous assets actually do. And then I to the refinery.

Speaker 2: What do you think the potential efficiency gains are from going from legacy copper mine to the kind of end state, you know, fully autonomous system?

Speaker 12: Yeah. I think it'll happen in two phases. I think the first phase is gonna double productivity, through just, like, better orchestration and better logistics management and better utilization of all the equipment. The that's productivity and and and unit costs. You know, diesel is a good example for for heavy haul machinery. Like, half of the diesel consumption up to half is from, like, idle time in the in the pit on the equipment. And so there's a lot of kind of, like, short term potential gains, but I also think that autonomy is gonna fundamentally change. It's gonna unlock a lot of, like, operating modes that can't really be done with humans. And so the way that the mining industry has kind of driven down cost over an extended period of time has been through scale. So the haul trucks are getting bigger, the shovels are getting bigger, and it's all focused on kind of reducing your labor intensity. So, you know, maximizing tons of ore tons of ore moved or tons of material moved per unit of, like, labor hour. But as you move into, like, autonomous systems and eventually kind of, like, design the mines themselves to be autonomous, I think we're gonna see things get smaller. And, like, swarm mining is gonna get unlocked, and that's fundamentally gonna enable you to actually kind of, like, be more selective in how you mine. Your roads get smaller, which means you can maximize kind of recovery of the ore from the pit. Yeah. So I think it'll all happen in two phases. It's like, take the existing architecture, make it autonomous, and maximize utilization and and availability of equipment. And then there's gonna be this, like, once autonomy is kind of, like, fully demonstrated across the stack, there's gonna be this opportunity to actually attack, like, fundamentally how is how are minds mind?

Speaker 1: You started the company in 2024?

Speaker 12: Yep. 2024. Raised a seed round in August. We're at 220 people now across the company. We have we have two projects. One is a lithium refinery in one's a one's a lithium refinery in in East Texas that's extracting lithium from oil and gas wastewater and the and the others are kind of first large scale commercial mine.

Speaker 3: Another one.

Speaker 1: He's got two.

Speaker 3: Yeah. Exactly.

Speaker 1: Pitch I have a question.

Speaker 2: Pitch for you. Robotic canaries.

Speaker 5: Do they Well,

Speaker 12: we have we have Sensors

Speaker 5: for sure.

Speaker 12: We have a Boston Dynamics spot that is basically like mobile sensing system Mhmm. You know, instead of the canary in the coal mine. And we use them mostly for like undercarriage inspection. So like you want to keep humans away from like heavy haul machinery, the closer they get to it, obviously the more hazards that are present. But also like the chemical refineries, ideally humans aren't walking through chemical plants all the time, kind of doing thermal inspections. There's a lot of stuff that's, like, auditory, so you're, like, listening for sounds of the motors sounding weird. Words. The exactly. And then that all that all needs to feed back Yeah. Into into, like, again, the integrated kinda, like, sensing integrated, like, data frame that tells you, like, how what's the healthier systems.

Speaker 1: Okay. Did you start with copper 2024?

Speaker 12: We started with lithium in 2020. Okay.

Speaker 1: Because it because it feels like it feels like, you know, there's this whole autonomy story, more efficiency, all of that makes sense, but the price of copper has doubled since you started the company. And I feel like that just makes bringing a copper mine back online just wildly different from an economic perspective. And and it's very interesting that you're sitting at the tailwind of like two AI trends, which are just demand for copper for data center development, wires, circuitry, all this other stuff. And then you can actually be more efficient. But you can be as you can be as efficient as they were a couple years ago and just reap twice the price. It feels like the oil dynamic. Right?

Speaker 12: Yeah. That that's right. But I I I don't think so the reason you wanna be diversified is because, like, all these metals are cyclical, and you can't really, like, live and die by a single commodity price. And so the plan was always to diversify, and the plan is to continue to diversify into nickel and cobalt and uranium and graphite

Speaker 3: and rare earths.

Speaker 12: Yeah. And, you know, as we as we kind of work to build 10 projects in the next ten years. But, you know, we started working on this project kind of like well before copper had its like little explosion and and run that it's on because you don't really want to jump into projects in the middle of the hype. Like, that's when you're gonna pay the most for an asset. That's when you're going to like, the labor pool is most constrict is, like, most in demand. Yeah. The equipment suppliers that make the equipment that is specific for a specific metal are gonna have longer lead times and and and have higher pricing. And so you really do want like, we jumped into lithium when lithium was, like, at the bottom of its recent trough and jumped into copper, you know, before it started to go on this run. So the generally, we wanna work on metals that we think have a long term, like, supply demand imbalance. Yeah. And for copper, it very it's, like, very much felt. Like, grades are dropping or or deposits are getting deeper. Mineralogies are getting more complex. And it just makes this gonna be a lot harder to make copper in the future, and that's that's what we wanna work on.

Speaker 2: What were you doing before this?

Speaker 12: I was at Tesla for about a decade. Most recently, I was running our minerals and metals team. So I was building our lithium refinery in Corpus Christi in Texas and running a lot of our battery recycling work.

Speaker 1: Very cool.

Speaker 2: Kind of like the absolutely most perfect background for a company like this that any any A VC couldn't a VC couldn't dream of a more perfect resume for this business.

Speaker 1: What what's all the text in the gulf behind you for that map?

Speaker 2: Yeah. What does that say?

Speaker 1: I understand that it's a map of America, but what's in the what what's all the text for?

Speaker 12: So these are all it's basically calling out, like, things that they don't have space for the words on map. Okay. So it's just it's a it's a legend you got.

Speaker 1: A crazy detailed legend. Yep.