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.

Search Publications by: Brian DeCost (Fed)

Search Title, Abstract, Conference, Citation, Keyword or Author
Displaying 26 - 36 of 36

Physics in the Machine: Integrating Physical Knowledge in Autonomous Phase-Mapping

February 16, 2022
Author(s)
A. Gilad Kusne, Austin McDannald, Brian DeCost
Application of artificial intelligence (AI), and more specifically machine learning, to the physical sciences has expanded significantly over the past decades. In particular, science-informed AI, also known as scientific AI or inductive bias AI, has grown

Uncertainty Prediction for Machine Learning Models of Material Properties

November 23, 2021
Author(s)
Francesca Tavazza, Brian DeCost, Kamal Choudhary
Uncertainty quantification in artificial intelligence (AI)-based predictions of material properties is of immense importance for the success and reliability of AI applications in materials science. While confidence intervals are commonly reported for

An Open Combinatorial Diffraction Dataset Including Consensus Human and Machine Learning Labels with Quantified Uncertainty for Training New Machine Learning Models

June 9, 2021
Author(s)
Jason Hattrick-Simpers, Brian DeCost, Aaron Gilad Kusne, Howard Joress, Winnie Wong-Ng, Debra Kaiser, Andriy Zakutayev, Caleb Phillips, Tonio Buonassisi, Shijing Sun, Janak Thapa
Modern machine learning and autonomous experimentation schemes in materials science rely on accurate analysis of the data ingested by these models. Unfortunately, accurate analysis of the underlying data can be difficult, even for domain experts

On-the-fly closed-loop materials discovery via Bayesian active learning

November 24, 2020
Author(s)
Aaron Gilad Kusne, Heshan Yu, Huairuo Zhang, Jason Hattrick-Simpers, Brian DeCost, Albert Davydov, Leonid A. Bendersky, Apurva Mehta, Ichiro Takeuchi
Active learning—the field of machine learning (ML) dedicated to optimal experiment design—has played a part in science as far back as the 18th century when Laplace used it to guide his discovery of celestial mechanics. In this work, we focus a closed-loop

The joint automated repository for various integrated simulations (JARVIS) for data-driven materials design

November 12, 2020
Author(s)
Kamal Choudhary, Kevin Garrity, Andrew C. Reid, Brian DeCost, Adam Biacchi, Angela R. Hight Walker, Zachary Trautt, Jason Hattrick-Simpers, Aaron Kusne, Andrea Centrone, Albert Davydov, Francesca Tavazza, Jie Jiang, Ruth Pachter, Gowoon Cheon, Evan Reed, Ankit Agrawal, Xiaofeng Qian, Vinit Sharma, Houlong Zhuang, Sergei Kalinin, Ghanshyam Pilania, Pinar Acar, Subhasish Mandal, David Vanderbilt, Karin Rabe
The Joint Automated Repository for Various Integrated Simulations (JARVIS) is an integrated infrastructure to accelerate materials discovery and design using density functional theory (DFT), classical force-fields (FF), and machine learning (ML) techniques

Scientific AI in Materials Science: a Path to a Sustainable and Scalable Paradigm

July 14, 2020
Author(s)
Brian L. DeCost, Jason R. Hattrick-Simpers, Zachary T. Trautt, Aaron G. Kusne, Martin L. Green, Eva Campo
Recent years have seen an ever-increasing trend in the use of machine learning (ML) and artificial intelligence (AI) methods by the materials science, condensed matter physics, and chemistry communities. This perspective article identifies key scientific

{A high-throughput structural and electrochemical study of metallic glass formation in Ni-Ti-Al

June 4, 2020
Author(s)
Howard L. Joress, Brian L. DeCost, Suchismita Sarker, Trevor M. Braun, Logan T. Ward, Kevin Laws, Apurva Mehta, Jason R. Hattrick-Simpers
Based on a set of machine learning predictions of glass formation in the Ni-Ti-Al system, we have undertaken a high-throughput experimental study of that system. We utilized rapid synthesis followed by high- throughput structural and electrochemical