Artificial intelligence, the startup that uses it to find “green” metals

These vehicles are difficult to roll over“, assures me geologist Wilson Bonner as the four-wheeled off-road vehicle he’s driving suddenly leans to one side, almost knocking me into the mud stirred up by the wheels. We are climbing the side of a wooded hill in rural Ontario, in Canada, on a cold fall day, headed to a destination that according to the company Bonner works for, the startup KoBold Metals, represents the union between aartificial intelligence (Ai) cutting edge and one of the oldest industrial sectors of mankind, the mining one.

Flying drone with camera

Indeed, we completed the half-hour journey relatively undisturbed, finally making it through a stretch dotted with broken trees and trampled scrub along a strip of muddy ground. A black tube, as wide as my arm, protrudes from the ground: it is the upper end of a hole almost a kilometer deep, dug by a drilling rig about the size of a truck that sits nearby. Not a pretty sight, but this hollow could score one breakthrough for the future of miningan industry crucial to the world’s transition to renewable energy.

As many parts of the globe begin to switch from fossil fuels to greener alternatives, the global race to find large quantities of cobalt, lithium and other metals needed to build the electric car batteries, solar panels and wind turbines that we will need. However, locating new mineral deposits is increasingly difficult and costly. Most of the world’s reserves have already been exploited. Those that remain tend to be in remote locations, deep underground. Typically, miners report that only one out of a hundred explorations proves to be fruitful.

See also  Enel aims at 75% of energy from renewable sources in 2025

The union between Ai and the mining sector

KoBold Metals, a startup founded four years ago, is one of the companies that are trying to speed up this process and make it cheaper and more efficient using artificial intelligence. The company has built a titanic database incorporating all the information gathered about the earth’s crust, the equivalent of thirty million pages of geological reports, soil samples, satellite images, academic research papers and handwritten reports a century ago. A team of data analysts converts this information into machine-readable datafor example by scanning written reports with optical character recognition (OCR) software or by standardizing recorded geophysical information into different digital formats.

The data is then analyzed by machine learning algorithms that identify geological patterns and other characteristics of places where the metals were found in the past. The algorithms can then be used to find promising areas that have not yet been explored, yielding a series of maps indicating where the coveted metals are likely to be located. Backed by investors such as venture capital firm Andreessen Horowitz and Breakthrough Energy Ventures by Bill GatesKoBold fielded the first metal exploration teams last summer in Zambia, Greenland and Canada, where the site I visited is located in Ontario, near Crystal Lake.

See also  Cloud software is suffering a cold November rain. Can Snowflake and Salesforce turn it around?


Source link

Thank you for reading this post, don't forget to subscribe!

We will be happy to hear your thoughts

Leave a reply

%d bloggers like this: