PAMS Seminar: Dr. Dilpuneet Aidhy, "Properties of Concentrated Alloys Predicted from Atomistic Calculations and Machine Learning"

Dr. Aidhy is an assistant professor in the department of mechanical engineering at the University of Wyoming. His areas of expertise are atomistic modeling of materials using density functional theory, molecular dynamics simulations and data-science methods.

Abstract:

Concentrated alloys, including high entropy alloys (HEAs), consist of multiple principal elements that are randomly distributed on a crystal lattice. The random distribution of elements leads to a varying energy landscape at each atomic site. Consequently, large variations in various types of defect energies including point defects and stacking faults is commonly observed in HEAs. Statistically capturing the variation requires performing large number of density functional theory calculations. The challenge is compounded due to the exponentially large number of compositions that are possible in HEAs. We solve the problem by leveraging machine learning tools where the defect energies computed from binary alloys are used to train the models to predict energies in multi-element alloys. We demonstrate accurate predictions of defect energies in Ni-based HEAs. A major benefit of this approach is that once the binary database is built and the model is trained, defect energies can be easily predicted thereby bypassing the need to perform large number of calculations every time a new composition is discovered.

This seminar will be held exclusively on Zoom (955 5209 1021). Please visit the Physics Seminars page for a link.

Free