Earth AI Integrates Mining Search for Critical Minerals
▼ Summary
– Earth AI’s AI models identify promising locations for critical minerals in Australia, but lab processing delays have become a major bottleneck.
– Lab backlogs have more than doubled due to increased interest in new mineral sources, causing delays of up to five months for sample results.
– Earth AI is building its own labs to reduce processing time from five months to five days.
– The startup relies on drilling to confirm mineral distribution, as subsurface exploration cannot yet replace physical extraction.
– In-house labs will accelerate exploration by providing timely data to guide drilling decisions, while third-party labs will still validate final economic assessments.
A model’s performance hinges on the quality of its data, and for Roman Teslyuk, the bottleneck wasn’t his algorithms,it was the lab.
“I hate delays,” Teslyuk, founder and CEO of Earth AI, told TechCrunch.
For several years, Earth AI has been hunting for critical minerals such as copper, platinum, and palladium across remote parts of Australia where previous exploration efforts had turned up nothing. The company’s AI models flagged several promising sites, and drilling confirmed their potential. Yet the pace of pinpointing the richest mineral deposits has been frustratingly slow.
The culprit, Teslyuk explained, was the laboratory supply chain.
“Since we ramped up the drilling capacity, we started getting these massive delays,” he said. Standard commercial labs processing rock samples for signs of critical minerals typically face backlogs of roughly two months. But with surging interest in developing new mineral sources, those wait times have more than doubled. “We’re 7 km behind , 7,000 meters of samples we don’t have data about.”
To solve this, Earth AI is building its own in-house labs, the startup exclusively revealed to TechCrunch. The goal: slash turnaround from five months to just five days.
Teslyuk noted that Earth AI’s models excel at identifying areas that could eventually support a mine. But once those targets are highlighted, the startup still must drill to confirm what lies beneath and how minerals are distributed. While subsurface exploration technology has advanced, drilling remains irreplaceable.
After drill cores are extracted, they require lab processing. “We don’t know whether we hit gold or not. We can’t see it with our eyes,” he said.
For final assessments of a mine’s economic viability,especially those that could inform a sale,Earth AI will continue relying on third-party labs to validate its discoveries. However, during the exploration phase, a fast internal lab can dramatically cut costs. It ensures the drill is directed to the most promising locations, feeding better data back into the model.
“If you don’t have the answers in time, you have to wait for five months for the answer, the next question [of where to drill] is not as good as it could be,” Teslyuk said. “To minimize drilling, you want to effectively ask the right questions, to get the information in time so you can narrow down exactly where to go.”
(Source: TechCrunch)
