Brian DeCost

I’m a computational materials scientist focused on building data-driven models and automation tools to address fundamental and applied problems in microstructure science and alloy design.

Education

2012-2016

Ph.D. Materials Science, Carnegie Mellon University, Pittsburgh, PA

Microstructure representations: Computer vision for microstructure characterization

Advisor: Elizabeth A. Holm

2012-2014
M.S. Materials Science, Carnegie Mellon University, Pittsburgh, PA
2008-2012
B.S. Chemical Engineering, University of Florida, Gainesville, FL Summa cum Laude

Research Experience

10/2017-present
NRC Postdoctoral Associate, NIST, Gaithersburg, MD
9/2016-9/2017
Postdoctoral Research Associate, Carnegie Mellon University, Pittsburgh, PA
8/2012-8/2017
Graduate Research Assistant, Carnegie Mellon University, Pittsburgh, PA.
6/2010-5/2012

Undergraduate Research Assistant, University of Florida, Gainesville, FL.

Monte Carlo modeling of diffusion in macroporous media

Publications

2018
K. Choudhary, B.L. DeCost, and F. Tavazza, Machine learning with force-field-inspired descriptors for materials: Fast screening and mapping energy landscape, Physical Review Materials doi:10.1103/PhysRevMaterials.2.083801
B.L. DeCost, T. Francis, and E.A. Holm, High throughput quantitative metallography for complex microstructures using deep learning: A case study in ultrahigh carbon steel, Accepted for publication in Microscopy and Microanalysis arxiv:1805.08693
B.L. DeCost and E.A. Holm, Computer vision for microstructural image representation: Methods and applications, to appear in Statistical Methods for Materials science: Data Analytics in Microstructure Characterization
2017
Menon, Aditya and Gupta, Chetali and Perkins, Kedar and DeCost, Brian and Budwal, Nikita and Rios, Renee and Zhang, Kun and Poczos, Barnabas and Washburn, Newell, Elucidating Multi-Physics Interactions in Suspensions for the Design of Polymeric Dispersants: A Hierarchical Machine Learning Approach, Molecular Systems Design & Engineering doi:10.1039/C7ME00027H
DeCost, Brian L. and Hecht, Matthew D. and Francis, Toby and Webler, Bryan A. and Picard, Yoosuf N. and Holm, Elizabeth A., UHCSDB (UltraHigh Carbon Steel micrograph DataBase): tools for exploring large heterogeneous microstructure datasets, Integrating Materials and Manufacturing Innovation doi:10.1007/s40192-017-0097-0
DeCost, Brian L. and Francis, Toby and Holm, Elizabeth A., Exploring the microstructure manifold: image texture representations applied to ultrahigh carbon steel microstructures, Acta Materialia doi:10.1016/j.actamat.2017.05.014
DeCost, Brian L. and Jain, Harshvardhan and Rollett, Anthony D. and Holm, Elizabeth A., Computer vision and machine learning for autonomous characterization of AM powder feedstocks, JOM doi:10.1007/s11837-016-2226-1
DeCost, Brian L. and Holm, Elizabeth A., Characterizing powder materials using keypoint-based computer vision methods, Computational Materials Science doi:10.1016/j.commatsci.2016.08.038
2016
DeCost, Brian L. and Holm, Elizabeth A., A large dataset of synthetic SEM images of powder materials and their ground truth 3D structures, Data in Brief doi:10.1016/j.dib.2016.10.011
DeCost, Brian L. and Holm, Elizabeth A., Phenomenology of abnormal grain growth in systems with non-uniform grain boundary mobility, Metallurgical and Materials Transactions A doi:10.1007/s11661-016-3673-6
2015
DeCost, Brian L. and Holm, Elizabeth A., A computer vision approach for automated analysis and classification of microstructural image data, Computational Materials Science doi:10.1016/j.commatsci.2015.08.011

Presentations

2018
B.L. DeCost, H. Yu, X. Zhang, S. Lee, Y. Liang, I. Takeuchi, J. Hattrick-Simpers, and A.G. Kusne, Autonomous X-ray diffraction system for accelerated combinatorial phase mapping, Oral presentation, COMBI 2018, Yokohama, Kanagawa, Japan. 03 October 2018
B.L. DeCost, H. Yu, X. Zhang, S. Lee, Y. Liang, I. Takeuchi, J. Hattrick-Simpers, and A.G. Kusne, Autonomous experimental phase diagram acquisition, Oral presentation, AIMS 2018, Gaithersburg, MD, USA. 08 August 2018
B.L. DeCost, H. Yu, X. Zhang, S. Lee, Y. Liang, I. Takeuchi, J. Hattrick-Simpers, and A.G. Kusne, Active learning for accelerated phase diagram acquisition: mapping metal-insulator transition materials, Oral presentation, MLSE 2018, Pittsburgh, PA, USA. 08 June 2018
B.L. DeCost et al., Autonomous materials characterization systems: X-ray diffraction and electrochemical prototypes, Poster presentation, MGI PI meeting, College Park, MD, USA. 27 March 2018
B.L. DeCost, T. Francis, and E.A. Holm, Towards high throughput quantitative metallography for complex microstructures with deep semantic segmentation models: A case study in ultrahigh carbon steel, Invited oral presentation; presented by E.A. Holm, TMS 2018, Phoenix, AZ, USA. 14 March 2018
B.L. DeCost, J. Hattrick-Simpers, Y. Liang, I. Takeuchi, and A.G. Kusne, Active machine learning for combinatorial exploration of metal-insulator transitions, Oral presentation, APS, Los Angeles, CA, USA. 09 March 2018
2017
B.L. DeCost, T. Francis and E.A. Holm, Deep microstructure segmentation: towards autonomous characterization, Poster presentation, Gordon Research Conference on Physical Metallurgy, Biddeford, ME, USA. 17 July 2017
B.L. DeCost, Some opportunities and challenges in microstructure informatics, Invited oral presentation, NIST, Gaithersburg, MD, USA. 15 February 2017
2016
B.L. DeCost, H. Jain, A.D. Rollett, and E.A. Holm, Exploring and evaluating powder micrographs with machine vision, Oral presentation, MS&T 2016, Salt Lake City, UT, USA. 27 October 2016
B.L. DeCost and E.A. Holm, Modeling abnormal grain growth mechanisms with the transgranular network and generic graph kernels, Oral presentation, Recrystallization and Grain Growth 2016, Pittsburgh, PA, USA. 19 July 2016
E.A. Holm and B.L. DeCost, Microstructure image analysis using computer vision and machine learning, Invited; presented for E.A. Holm, 3D Materials Science, St, Charles, IL, USA. 12 July 2016
B.L. DeCost and E.A. Holm, Keypoint-based computer vision approach for characterizing additive manufacturing powder feedstocks, Oral presentation, TMS 2016, Nashville, TN, USA. 18 February 2016
B.L. DeCost and E.A. Holm, Applying graph kernel methods for understanding abnormal grain growth, Oral presentation, TMS 2016, Nashville, TN, USA. 18 February 2016
B.L. DeCost, Microstructure as visual texture: keypoint-based computer vision techniques for microstructure characterization, Invited oral presentation, Air Force Research Laboratory, Dayton, OH, USA. 10 February 2016
2015
B.L. DeCost and E.A. Holm, Computer vision for automatic microstructure characterization, Oral presentation, MS&T 2015, Columbus, OH, USA. 6 October 2015
B.L. DeCost and E.A. Holm, Network features and rare microstructural events, Poster presentation, MS&T 2015, Columbus, OH, USA. 6 October 2015
B.L. DeCost and E.A. Holm, An automatic microstructure recognition system, Poster presentation, Gordon Research Conference on Physical Metallurgy, Biddeford, ME, USA. 20 July 2015
B.L. DeCost and E.A. Holm, The transgranular network: predicting rare microstructural events, Oral presentation, TMS 2015, Orlando, FL, USA. 17 March 2015
B.L. DeCost and E.A. Holm, An automatic microstructure recognition system, Poster presentation, TMS 2015, Orlando, FL, USA. 16 March 2015
2014
B.L. DeCost and E.A. Holm, Abnormal grain growth due to non-uniform grain boundary mobility, Oral presentation, MS&T 2014, Pittsburgh, PA, USA. 16 October 2014
B.L. DeCost, Towards stable nanocrystalline metals: a computational approach, Oral presentation, ASM Young Members Night, Pittsburgh, PA, USA. 20 February 2014
2013
B.L. DeCost and E.A. Holm, Monte Carlo study of low temperature abnormal grain growth: on the influence of high mobility boundaries, Poster presentation, MS&T 2013, Montreal, QC, Canada.
2012
B.L. DeCost, R. Mueller, and S. Vasenkov, Monte Carlo simulation of long range self-diffusion in model porous membranes, Poster presentation, University of Florida Undergraduate Research Symposium, Gainesville, FL, USA. March 2012

Awards and Grants

Fall 2017
NRC Postdoctoral Research Associate Program, National Research Council
May 2017
Paxton Award for Best Doctoral Dissertation, MSE, Carnegie Mellon University
March 2015
Best Poster Presentation, MSE Graduate Symposium, Carnegie Mellon University
January 2015
John and Claire Bertucci Graduate Fellowship
April 2008
Eagle Scout Rank, Boy Scouts of America

Teaching Experience

September 2018
Instructor, Machine Learning in Materials Science workshop, TMS, Pittsburgh, PA
July 2018
Instructor, Machine Learning in Materials Science bootcamp, NIST/UMD, Rockville MD
June 2018
Presenter, ODI Data Science Jamboree, NIST, Gaithersburg MD
Spring 2018
Instructor, Deep learning demo, NIST, Gaithersburg MD
Summer 2017
Instructor, Holm group computer vision bootcamp, Carnegie Mellon University, Pittsburgh PA
Spring 2016
Student, Evidence-based teaching methods in STEM, Carnegie Mellon University, Pittsburgh PA
Fall 2015
Course Assistant, 27-515 Introduction to computational materials science, Carnegie Mellon University, Pittsburgh PA
Spring 2015
Course Assistant, 27-705 Nanostructured materials, Carnegie Mellon University, Pittsburgh PA
Spring 2015
Recitation Teaching Assistant, 27-100 Engineering materials of the future, Carnegie Mellon University, Pittsburgh PA
Summer 2014
Instructor, Using SPPARKS for microstructure science, Carnegie Mellon 3D Microstructure Summer School, Pittsburgh PA
Fall 2013
Course Assistant, 27-766 Diffusion in materials, Carnegie Mellon University, Pittsburgh PA