New machine learning model spots rare minerals on Earth and other planets

What will they find?
Loukia Papadopoulos
Rare minerals.jpg
Rare minerals.

Ivan Reshetnikov/iStock 

Scientists have invented a machine learning model that can predict the locations of minerals on Earth, and even other planets, by taking advantage of patterns in mineral associations. 

This is according to a press release published on Wednesday by

Shaunna Morrison, Anirudh Prabhu, and their colleagues successfully engineered a tool for finding occurrences of specific minerals relying on individual experience, along with some luck.

To do this, they used data from the Mineral Evolution Database, which includes 295,583 mineral localities of 5,478 mineral species, to predict previously unknown mineral occurrences based on association rules. The researchers tried out their model on the Tecopa basin in the Mojave Desert.

The machine learning model was also able to pinpoint the locations of geologically important minerals, including uraninite alteration, rutherfordine, andersonite, schröckingerite, bayleyite, and zippeite.

It also identified promising areas for critical rare earth elements and lithium minerals, including monazite-(Ce), allanite-(Ce), and spodumene. 

A powerful predictive tool

Now, the scientists hope their invention will be a powerful predictive tool for mineralogists, petrologists, economic geologists, and planetary scientists, according to

The mineral deposits found through this process will serve to both better understand the history of our planet and to extract for use in technologies like rechargeable batteries.

In January of 2023, Europe's biggest deposit of rare earth metals, measuring over one million metric tons, was found in Sweden. The country's state mining company, LKAB, found vast amounts of rare earth metals in Kiruna, northern Sweden, known for its iron ore mines.

"This is the largest known deposit of rare earth elements in our part of the world, and it could become a significant building block for producing the critical raw materials that are absolutely crucial to enable the green transition. We face a supply problem. Without mines, there can be no electric vehicles," Jan Moström, President and Group CEO of LKAB, said at the time in a statement.

The paper is published in the journal PNAS Nexus.

Study abstract:

The locations of minerals and mineral-forming environments, despite being of great scientific importance and economic interest, are often difficult to predict due to the complex nature of natural systems. In this work, we embrace the complexity and inherent “messiness” of our planet's intertwined geological, chemical, and biological systems by employing machine learning to characterize patterns embedded in the multidimensionality of mineral occurrence and associations. These patterns are a product of, and therefore offer insight into, the Earth's dynamic evolutionary history. Mineral association analysis quantifies high-dimensional multicorrelations in mineral localities across the globe, enabling the identification of previously unknown mineral occurrences, as well as mineral assemblages and their associated paragenetic modes. In this study, we have predicted (i) the previously unknown mineral inventory of the Mars analogue site, Tecopa Basin, (ii) new locations of uranium minerals, particularly those important to understanding the oxidation–hydration history of uraninite, (iii) new deposits of critical minerals, specifically rare earth element (REE)- and Li-bearing phases, and (iv) changes in mineralization and mineral associations through deep time, including a discussion of possible biases in mineralogical data and sampling; furthermore, we have (v) tested and confirmed several of these mineral occurrence predictions in nature, thereby providing ground truth of the predictive method. Mineral association analysis is a predictive method that will enhance our understanding of mineralization and mineralizing environments on Earth, across our solar system, and through deep time.