Scientists have made a groundbreaking discovery in the field of mineral exploration using artificial intelligence (AI). By analyzing patterns in mineral associations, a new machine learning model has been developed to accurately predict the locations of minerals on Earth and potentially on other planets. This advancement holds tremendous value for both scientific research and industrial applications, particularly in uncovering the planet’s history and extracting resources like rechargeable batteries.
Led by Shaunna Morrison and Anirudh Prabhu, a team set out to create a method for identifying specific minerals—an endeavor that has long been considered both an art and a science, relying heavily on individual experience and serendipity.
The researchers developed a machine learning model that utilizes data from the Mineral Evolution Database, which encompasses 295,583 mineral localities and 5,478 mineral species. By employing association rules, the model can predict the occurrence of previously unknown minerals.
To test the model’s effectiveness, the team conducted an exploration of the Tecopa basin in the Mojave Desert—an environment known for its similarities to Mars. Remarkably, the model accurately predicted the presence of geologically significant minerals, such as uraninite alteration, rutherfordine, andersonite, schröckingerite, bayleyite, and zippeite.
Moreover, the model identified promising areas for critical rare earth elements and lithium minerals, including monazite-(Ce), allanite-(Ce), and spodumene. The ability to analyze mineral associations proves to be a powerful predictive tool for mineralogists, petrologists, economic geologists, and planetary scientists, as highlighted by the authors.
Reference: “Predicting new mineral occurrences and planetary analog environments via mineral association analysis” by Shaunna M Morrison, Anirudh Prabhu, Ahmed Eleish, Robert M Hazen, Joshua J Golden, Robert T Downs, Samuel Perry, Peter C Burns, Jolyon Ralph and Peter Fox, 16 May 2023, PNAS Nexus.
DOI: 10.1093/pnasnexus/pgad110
Table of Contents
Frequently Asked Questions (FAQs) about mineral exploration
What is the significance of using AI in predicting mineral locations?
Using AI in predicting mineral locations has significant implications for both scientific research and industrial applications. It allows for a more accurate identification of minerals on Earth and other planets, aiding in the exploration of mineral deposits and unraveling the planet’s history. This technology is particularly valuable for mining resources used in practical applications like rechargeable batteries.
How does the machine learning model work?
The machine learning model utilizes data from the Mineral Evolution Database, which contains extensive information on mineral localities and species. By analyzing patterns in mineral associations, the model can predict the occurrence of previously unknown minerals. It employs association rules to make these predictions, harnessing the power of AI to provide accurate results.
What were the findings of the research team’s exploration in the Mojave Desert?
During their exploration in the Mojave Desert, the research team tested the model’s capabilities. The model successfully predicted the locations of geologically significant minerals, including uraninite alteration, rutherfordine, andersonite, schröckingerite, bayleyite, and zippeite. Additionally, it identified promising areas for critical rare earth elements and lithium minerals such as monazite-(Ce), allanite-(Ce), and spodumene.
Who can benefit from this predictive tool?
Mineral association analysis, enabled by the machine learning model, can be highly beneficial for various professionals. Mineralogists, petrologists, economic geologists, and planetary scientists can utilize this tool to enhance their research and exploration efforts. The predictive capabilities of the model offer valuable insights into mineral occurrences and aid in identifying potential resource-rich areas.
More about mineral exploration
- Predicting new mineral occurrences and planetary analog environments via mineral association analysis: Link
- Mineral Evolution Database: Link
- Rare Earth Elements: Link
- Lithium Minerals: Link
- Rechargeable Batteries: Link
