Skip to main content
U.S. flag

An official website of the United States government

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you’ve safely connected to the .gov website. Share sensitive information only on official, secure websites.

Brian DeCost (Fed)

Brian DeCost is a materials research engineer in the Data and AI Driven Materials Science Group at the National Institute of Standards and Technology. He earned a B.S. in Chemical Engineering at the University of Florida and a Ph.D. in Materials Science and Engineering at Carnegie Mellon University. Brian’s research focuses on developing and applying scientific machine learning methods and automation tools to address fundamental and applied problems in microstructure science and alloy design, with a particular focus on active learning for autonomous experiment planning and execution.


postdoctoral opportunity: Scientific machine learning methods for trustable accelerated materials characterization and design


Accelerating Defect Predictions in Semiconductors Using Graph Neural Networks

Md. Habibur Rahman, Prince Gollapalli, Panayotis Manganaris, Satyesh Kumar Yadav, Ghanshyam Pilania, Arun Kumar Mannodi-Kanakkithodi, Brian DeCost, Kamal Choudhary
First principles computations reliably predict the energetics of point defects in semiconductors, but are constrained by the expense of using large supercells

Flexible formulation of value for experiment interpretation and design

Matthew Carbone, Hyeong Jin Kim, Chandima Fernando, Shinjae Yoo, Daniel Olds, Howie Joress, Brian DeCost, Bruce D. Ravel, Yugang Zhang, Phillip Michael Maffettone
The challenge of optimal design of experiments pervades materials science, physics, chemistry, and biology. Bayesian optimization has been used to address this
Created September 12, 2019, Updated April 11, 2024