New and interesting uses for machine learning seem to arise daily. Researchers from Lawrence Berkeley National Laboratory recently trained an algorithm to predict structural characteristics of certain metal alloys that slashes computational power usually required for such calculations. The new approach is expected to accelerate research of new advanced alloys for applications spanning automotive to aerospace and much more.
Their work – Predicting defect behavior in B2 intermetallics by merging ab initio modeling and machine learning – is published in a recent issue of Nature Computational Materials. As an extension of this proof-of-concept work, an open source Python toolkit for modeling point defects in semiconductors and insulators (PyCDT) has been developed.
Traditionally, researchers have used a computational quantum mechanical method known as density functional calculations to predict what kinds of defects can be formed in a given structure and how they affect the material’s properties. This approach is computationally challenging and has limited its use, according to an article on the work posted on the NERSC site.
“Density functional calculations work well if you are modeling one small unit, but if you want to make your modeling cell bigger the computational power required to do this increases substantially,” says Bharat Medasani, a former Berkeley Lab postdoc and lead author of the paper. “And because it is computationally expensive to model defects in a single material, doing this kind of brute force modeling for tens of thousands of materials is not feasible.”
Medasani and his colleagues developed and trained machine learning algorithms to predict point defects in intermetallic compounds, focusing on the widely observed B2 crystal structure. Initially, they selected a sample of 100 of these compounds from the Materials Project Database and ran density functional calculations on supercomputers at the National Energy Research Scientific Computing Center (NERSC), a DOE Office of Science User Facility at Berkeley Lab, to identify their defects.
The overall result is it is no longer necessary to run costly first principle calculations to identify defect properties for every new metallic compound, say the researchers.
“This tool enables us to predict metallic defects faster and robustly, which will in turn accelerate materials design,” says Kristin Persson, a Berkeley Lab Scientist and Director of the Materials Project, an initiative aimed at drastically reducing the time needed to invent new materials by providing open web-based access to computed information on known and predicted materials.