The land AI algorithms found critical minerals in places that everyone else ignored

Last summer, the Kobold Mining Startup took a dip when he said he had discovered in Zambia one of the world's largest copper deposits in more than a decade.

Now, another startup, <a target="_blank" rel="nofollow" href="https://earth-ai.com”>Land aiexclusively told Techcrunch about his own discovery: promising critical mineral deposits in parts of Australia that other mining attire had ignored for decades. While it is not yet known if they are as large as Kobold's, the news suggests that future supplies of critical minerals of a combination of field data analyzed by artificial intelligence are probable.

“The real and real border (in mining) is not as geographical as technological,” Roman Teslyuk, founder and CEO of Earth ai, told Techcrunch.

Earth ai has identified copper, cobalt and gold deposits in the territory of the north and silver, molybdenum and tin in another in Nueva Wales del Sur, 310 miles (500 kilometers) northwest of Sydney.

Earth ai emerged from Teslyuk's postgraduate studies. Teslyuk, originally from Ukraine, was working for a doctorate at the University of Sydney, where he became familiar with the mining industry in Australia. There, the Government has the rights to mineral deposits, and creak them in terms of six years. Since the 1970s, he said, exploration companies must present their data to a national archive.

“For some reason, nobody is using them,” he said. “If I could build an algorithm that can absorb all that knowledge and learn from the failures and successes of millions of geologists in the past, I can make much better predictions about where to find minerals in the future.”

Teslyuk began the ai ​​of the Earth as a software company focused on making predictions on possible deposits and then approaching customers who could be interested in exploring more sites. But customers doubted to invest, partly because they did not want to bet on millions about the predictions of an unseeding technology.

“Mining is a very conservative industry,” said Teslyuk. “Everything outside the approved dogma is considered heresy.”

Then, Earth ai decided to develop his own drilling team to demonstrate that the sites he identified were as promising as his software suggested. The company was accepted in the spring cohort of 2019 and Combinator, and spent the following years refining its hardware and software. In January, <a target="_blank" rel="nofollow" href="https://www.axios.com/pro/climate-deals/2025/01/27/earth-ai-roman-teslyuk-tamarack-cantos”>Earth ai raised a B $ 20 million series

Although the company uses ai to search for minerals like Kobold, Teslyuk says that a different tactic is needed. The land ai algorithms, he said, are trained to scan wide and efficient areas to find deposits that could otherwise have been overlooked.

“The way we used to explore for metals in the past, 20^th Century, it only takes a long time, a long time. Decades are needed to find something, “said Teslyuk.” With the modern rhythm of the world, you can't wait so long. “