The authors evaluated their model by exploring the Tecopa basin in the Mojave Desert, a widely known Mars analog environment. The design was likewise able to forecast the areas of geologically crucial minerals, including uraninite modification, andersonite, rutherfordine, and schröckingerite, bayleyite, and zippeite.
In addition, the model situated promising areas for vital uncommon earth elements and lithium minerals, consisting of monazite-( Ce), and allanite-( Ce), and spodumene. Mineral association analysis can be an effective predictive tool for mineralogists, petrologists, economic geologists, and planetary researchers, according to the authors.
Reference: “Predicting new mineral events and planetary analog environments by means of 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.
Pink crystal spodumene. Credit: Robert Lavinsky
By utilizing patterns in mineral associations, a new machine-learning model can anticipate the places of minerals on Earth and potentially, other planets. This development is of immense value to science and industry, as they constantly check out mineral deposits to unwind the planets history and to mine resources for useful applications, such as rechargeable batteries.
A team led by Shaunna Morrison and Anirudh Prabhu aimed to establish a technique for determining the occurrence of particular minerals, a goal that has generally been considered as much an art as it is a science. This procedure has frequently depended on specific experience in addition to a healthy dosage of luck.
The team created an artificial intelligence design that uses data from the Mineral Evolution Database, which includes 295,583 mineral areas of 5,478 mineral species, to predict formerly unknown mineral incidents based upon association rules.