Artificial intelligence paves the way for the discovery of new rare earth compounds

Artificial intelligence is advancing the way scientists explore materials. Researchers from the Ames Lab and Texas A&M University trained a machine learning (ML) model to assess the stability of rare earth compounds. This work was supported by the Laboratory Directed Research and Development (LDRD) program of the Ames Laboratory. The framework they developed builds on current state-of-the-art methods for experimenting with compounds and understanding chemical instabilities.

Ames Lab has been a leader in rare earth research since the mid-20and century. Rare earth elements have a wide range of uses, including clean energy technologies, energy storage, and permanent magnets. The discovery of new rare earth compounds is part of a larger effort by scientists to expand access to these materials.

The current approach is based on machine learning (ML), a form of artificial intelligence (AI), which is driven by computer algorithms that improve through the use of data and experience. The researchers used the improved Ames Laboratory Rare Earth Database (RIC 2.0) and high-throughput Density Functional Theory (DFT) to lay the groundwork for their ML model.

High-throughput screening is a computational scheme that allows a researcher to quickly test hundreds of models. DFT is a quantum mechanical method used to study the thermodynamic and electronic properties of many body systems. Based on this collection of information, the developed ML model uses regression learning to assess the phase stability of compounds.

Tyler Del Rose, a graduate student at Iowa State University, conducted much of the basic research needed for the database by writing algorithms to search the web for information to complete the database and DFT calculations . He has also worked on experimental validation of AI predictions and helped improve ML-based models by ensuring they are representative of reality.

“Machine learning is really important here because when we’re talking about new compositions, the ordered materials are all very well known to everyone in the rare earth community,” said Ames Lab scientist Prashant Singh, who led the DFT plus machine learning effort with Guillermo Vazquez. and Raymundo Arroyave. “However, when you add disorder to known materials, it’s very different. The number of compositions becomes dramatically larger, often thousands or millions, and you can’t study every possible combination using theory or experiences.”

Singh explained that material analysis is based on a discrete feedback loop in which the AI/ML model is updated using a new DFT database based on structural and phase-in-time information. real obtained from our experiments. This process ensures that information is passed from one step to the next and reduces the risk of errors.

Yaroslav Mudryk, the project supervisor, said the framework was designed to explore rare earth compounds because of their technological importance, but its application is not limited to rare earth research. The same approach can be used to train an ML model to predict magnetic properties of compounds, process controls for transformative manufacturing, and optimize mechanical behaviors.

“It’s not really aimed at discovering a particular compound,” Mudryk said. “It was, how do we design a new approach or a new tool for the discovery and prediction of rare earth compounds? And that’s what we did.”

Mudryk stressed that this work is just the beginning. The team is exploring the full potential of this method, but they are optimistic that there will be a wide range of applications for the framework in the future.

Source of the story:

Materials provided by DOE/Ames Laboratory. Note: Content may be edited for style and length.

Comments are closed.