export_ofoct.com (1)

[00:00.66] So we need to look deeper.

[00:03.32] Controversially, we've been taught that these materials will run out.

[00:07.30] We don't lack ore body deposits.

[00:09.43] We lack information of where they lie.

[00:12.08] So if you had a crystal ball, you'd just look into it and start digging out the rocks that are the best and generate the least waste.

[00:19.79] But we don't have a crystal ball.

[00:21.91] So the thing that we should do is make predictions of where these materials lie.

[00:27.49] My colleagues and I at KoBold are doing what the industry has neglected to do.

[00:33.87] We aim to predict everything, quantify what we don't know and collect information efficiently.

[00:41.04] So we're all going to try that right now.

[00:43.43] I want you to predict 1,000 meters below your feet what the concentration of copper is right where you're sitting.

[00:50.87] I want you to predict how hard it is, how fractured it is, what's its density?

[00:58.57] We aim to predict all these things and more. We're developing machine learning technologies that help us predict all of this and rigorously quantify our uncertainties in these predictions.

[01:10.52] So what does this look like in practice?

[01:12.92] When we're exploring for mines, we often fly aircraft thousands of kilometers across the Earth to try collect information such as the Earth's magnetism, its gravitational field, that tells us something about the rocks beneath.

[01:26.46] But there's a problem.

[01:28.32] For everything that we're looking at, there are going to be an infinite number of possibilities.

[01:33.64] And that's because we're building three-dimensional models to fit two-dimensional data.

[01:38.42] So if a body was smaller and closer to the surface or larger and further away, the measurement would be the same.

[01:45.06] So this body will also fit the data.

[01:47.98] And will this one, and this one, and many more.