Sign up for our newsletter to receive these emails in your inbox.


Despite the world’s growing population and economy, resources are becoming more abundant. The reason is the growth in knowledge. One aspect of that growth is learning to do more with less—think about satellites or cell towers replacing miles of cable—but another is simply finding more resources. KoBold Metals, a mineral exploration company, is a perfect example. In Zambia, where people have mined for millennia, the company recently found what The New York Times called the “largest copper discovery in more than a decade” through the careful application of knowledge.

KoBold’s approach to exploration will sound familiar: a large dataset combined with artificial intelligence. Their system uses a wide variety of geological data to predict the location of mineral deposits. Crucially, their models also calculate the uncertainty of these predictions and determine what kind of information is needed to improve their accuracy. The process then moves to the field, where KoBold’s geologists survey and sample promising terrain while artificial intelligence uses that new information to determine what to measure next and, ultimately, where to drill. All this calculation saves time and money. Kobold’s founders claim their system “shortened the learning cycle from a season to a day” and “generated predictions with 80 percent lower false positive and false negative rates compared to conventional predictions.”

These advantages rely on KoBold’s massive database, called TerraShed, which can standardize and analyze everything from hand-drawn maps and typed reports to electromagnetic measurements. According to Kurt House, KoBold’s CEO, TerraShed now contains three percent of all geological data and has led the company to around sixty exploration projects.

House puts it nicely: “We don’t drill for metals, we drill for information.”

Malcolm Cochran, Digital Communications Manager


Culture & Tolerance:

Economics:

Energy & Environment:

Food & Hunger:

Health & Demographics:

Science & Technology:

Violence:

Tweets: