1
|
Mannodi-Kanakkithodi A, McDannald A, Sun S, Desai S, Brown KA, Kusne AG. A framework for materials informatics education through workshops. MRS Bull 2023; 48:1-10. [PMID: 37361859 PMCID: PMC10153775 DOI: 10.1557/s43577-023-00531-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Accepted: 03/31/2023] [Indexed: 06/28/2023]
Abstract
Abstract The burgeoning field of materials informatics necessitates a focus on educating the next generation of materials scientists in the concepts of data science, artificial intelligence (AI), and machine learning (ML). In addition to incorporating these topics in undergraduate and graduate curricula, regular hands-on workshops present the most effective medium to initiate researchers to informatics and have them start applying the best AI/ML tools to their own research. With the help of the Materials Research Society (MRS), members of the MRS AI Staging Committee, and a dedicated team of instructors, we successfully conducted workshops covering the essential concepts of AI/ML as applied to materials data, at both the Spring and Fall Meetings in 2022, with plans to make this a regular feature in future meetings. In this article, we discuss the importance of materials informatics education via the lens of these workshops, including details such as learning and implementing specific algorithms, the crucial nuts and bolts of ML, and using competitions to increase interest and participation. Graphical abstract
Collapse
Affiliation(s)
| | - Austin McDannald
- Materials Measurement Science Division, National Institute of Standards and Technology, Gaithersburg, USA
| | | | - Saaketh Desai
- Center for Integrated Nanotechnologies, Sandia National Laboratories, Albuquerque, USA
| | | | - A. Gilad Kusne
- Materials Measurement Science Division, National Institute of Standards and Technology, Gaithersburg, USA
| |
Collapse
|
2
|
Lolla S, Liang H, Kusne AG, Takeuchi I, Ratcliff W. A semi-supervised deep-learning approach for automatic crystal structure classification. J Appl Crystallogr 2022; 55:882-889. [PMID: 35974721 PMCID: PMC9348870 DOI: 10.1107/s1600576722006069] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/10/2021] [Accepted: 06/08/2022] [Indexed: 05/31/2023] Open
Abstract
A semi-supervised model to predict crystal structures from powder neutron diffraction patterns has been developed. The models have higher accuracies than current approaches while covering more space groups. The structural solution problem can be a daunting and time-consuming task. Especially in the presence of impurity phases, current methods, such as indexing, become more unstable. In this work, the novel approach of semi-supervised learning is applied towards the problem of identifying the Bravais lattice and the space group of inorganic crystals. The reported semi-supervised generative deep-learning model can train on both labeled data, i.e. diffraction patterns with the associated crystal structure, and unlabeled data, i.e. diffraction patterns that lack this information. This approach allows the models to take advantage of the troves of unlabeled data that current supervised learning approaches cannot, which should result in models that can more accurately generalize to real data. In this work, powder diffraction patterns are classified into all 14 Bravais lattices and 144 space groups (the number is limited due to sparse coverage in crystal structure databases), which covers more crystal classes than other studies. The reported models also outperform current deep-learning approaches for both space group and Bravais lattice classification using fewer training data.
Collapse
|
3
|
DeCost BL, Hattrick-Simpers JR, Trautt Z, Kusne AG, Campo E, Green ML. Scientific AI in Materials Science: a Path to a Sustainable and Scalable Paradigm. Mach Learn Sci Technol 2020; 1:10.1088/2632-2153/ab9a20. [PMID: 33655211 PMCID: PMC7919383 DOI: 10.1088/2632-2153/ab9a20] [Citation(s) in RCA: 21] [Impact Index Per Article: 5.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/12/2022] Open
Abstract
Recently there has been 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, technical, and social opportunities that the materials community must prioritize to consistently develop and leverage Scientific AI (SciAI) to provide a credible path towards the advancement of current materials-limited technologies. Here we highlight the intersections of these opportunities with a series of proposed paths forward. The opportunities are roughly sorted from scientific/technical (e.g. development of robust, physically meaningful multiscale material representations) to social (e.g. promoting an AI-ready workforce). The proposed paths forward range from developing new infrastructure and capabilities to deploying them in industry and academia. We provide a brief introduction to AI in materials science and engineering, followed by detailed discussions of each of the opportunities and paths forward.
Collapse
Affiliation(s)
- B L DeCost
- National Institute of Standards and Technology, Gaithersburg, MD, USA
| | | | - Z Trautt
- National Institute of Standards and Technology, Gaithersburg, MD, USA
| | - A G Kusne
- National Institute of Standards and Technology, Gaithersburg, MD, USA
| | - E Campo
- National Science Foundation, Arlington, VA, USA
- Campostella Research & Consulting, LLC, Alexandria, VA, USA
| | - M L Green
- National Institute of Standards and Technology, Gaithersburg, MD, USA
| |
Collapse
|
4
|
Hattrick-Simpers JR, Zakutayev A, Barron SC, Trautt ZT, Nguyen N, Choudhary K, DeCost B, Phillips C, Kusne AG, Yi F, Mehta A, Takeuchi I, Perkins JD, Green ML. An Inter-Laboratory Study of Zn-Sn-Ti-O Thin Films using High-Throughput Experimental Methods. ACS Comb Sci 2019; 21:350-361. [PMID: 30888788 DOI: 10.1021/acscombsci.8b00158] [Citation(s) in RCA: 10] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/29/2022]
Abstract
High-throughput experimental (HTE) techniques are an increasingly important way to accelerate the rate of materials research and development for many technological applications. However, there are very few publications on the reproducibility of the HTE results obtained across different laboratories for the same materials system, and on the associated sample and data exchange standards. Here, we report a comparative study of Zn-Sn-Ti-O thin films materials using high-throughput experimental methods at National Institute of Standards and Technology (NIST) and National Renewable Energy Laboratory (NREL). The thin film sample libraries were synthesized by combinatorial physical vapor deposition (cosputtering and pulsed laser deposition) and characterized by spatially resolved techniques for composition, structure, thickness, optical, and electrical properties. The results of this study indicate that all these measurement techniques performed at two different laboratories show excellent qualitative agreement. The quantitative similarities and differences vary by measurement type, with 95% confidence interval of 0.1-0.2 eV for the band gap, 24-29 nm for film thickness, and 0.08 to 0.37 orders of magnitude for sheet resistance. Overall, this work serves as a case study for the feasibility of a High-Throughput Experimental Materials Collaboratory (HTE-MC) by demonstrating the exchange of high-throughput sample libraries, workflows, and data.
Collapse
Affiliation(s)
- Jason R. Hattrick-Simpers
- National Institute of Standards and Technology (NIST), Gaithersburg, Maryland 20899-3460, United States
| | - Andriy Zakutayev
- National Renewable Energy Laboratory (NREL), Golden, Colorado 80401, United States
| | - Sara C. Barron
- National Institute of Standards and Technology (NIST), Gaithersburg, Maryland 20899-3460, United States
| | - Zachary T. Trautt
- National Institute of Standards and Technology (NIST), Gaithersburg, Maryland 20899-3460, United States
| | - Nam Nguyen
- National Institute of Standards and Technology (NIST), Gaithersburg, Maryland 20899-3460, United States
| | - Kamal Choudhary
- National Institute of Standards and Technology (NIST), Gaithersburg, Maryland 20899-3460, United States
| | - Brian DeCost
- National Institute of Standards and Technology (NIST), Gaithersburg, Maryland 20899-3460, United States
| | - Caleb Phillips
- National Renewable Energy Laboratory (NREL), Golden, Colorado 80401, United States
| | - A. Gilad Kusne
- National Institute of Standards and Technology (NIST), Gaithersburg, Maryland 20899-3460, United States
| | - Feng Yi
- National Institute of Standards and Technology (NIST), Gaithersburg, Maryland 20899-3460, United States
| | - Apurva Mehta
- SLAC National Accelerator Laboratory, Menlo Park, California 94025, United States
| | - Ichiro Takeuchi
- University of Maryland, College Park, Maryland 20742, United States
| | - John D. Perkins
- National Renewable Energy Laboratory (NREL), Golden, Colorado 80401, United States
| | - Martin L. Green
- National Institute of Standards and Technology (NIST), Gaithersburg, Maryland 20899-3460, United States
| |
Collapse
|
5
|
Kotevska O, Kusne AG, Samarov DV, Lbath A, Battou A. Dynamic Network Model for Smart City Data-Loss Resilience Case Study: City-to-City Network for Crime Analytics. IEEE Access 2017; 5:20524-20535. [PMID: 29250476 PMCID: PMC5729770 DOI: 10.1109/access.2017.2757841] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/07/2023]
Abstract
Today's cities generate tremendous amounts of data, thanks to a boom in affordable smart devices and sensors. The resulting big data creates opportunities to develop diverse sets of context-aware services and systems, ensuring smart city services are optimized to the dynamic city environment. Critical resources in these smart cities will be more rapidly deployed to regions in need, and those regions predicted to have an imminent or prospective need. For example, crime data analytics may be used to optimize the distribution of police, medical, and emergency services. However, as smart city services become dependent on data, they also become susceptible to disruptions in data streams, such as data loss due to signal quality reduction or due to power loss during data collection. This paper presents a dynamic network model for improving service resilience to data loss. The network model identifies statistically significant shared temporal trends across multivariate spatiotemporal data streams and utilizes these trends to improve data prediction performance in the case of data loss. Dynamics also allow the system to respond to changes in the data streams such as the loss or addition of new information flows. The network model is demonstrated by city-based crime rates reported in Montgomery County, MD, USA. A resilient network is developed utilizing shared temporal trends between cities to provide improved crime rate prediction and robustness to data loss, compared with the use of single city-based auto-regression. A maximum improvement in performance of 7.8% for Silver Spring is found and an average improvement of 5.6% among cities with high crime rates. The model also correctly identifies all the optimal network connections, according to prediction error minimization. City-to-city distance is designated as a predictor of shared temporal trends in crime and weather is shown to be a strong predictor of crime in Montgomery County.
Collapse
Affiliation(s)
- Olivera Kotevska
- National Institute of Standards and Technology, Gaithersburg, MD 20899, USA
| | - A. Gilad Kusne
- National Institute of Standards and Technology, Gaithersburg, MD 20899, USA
| | - Daniel V. Samarov
- National Institute of Standards and Technology, Gaithersburg, MD 20899, USA
| | - Ahmed Lbath
- University of Grenoble Alpes, 38400 Grenoble, France
| | - Abdella Battou
- National Institute of Standards and Technology, Gaithersburg, MD 20899, USA
| |
Collapse
|
6
|
Fackler SW, Alexandrakis V, König D, Kusne AG, Gao T, Kramer MJ, Stasak D, Lopez K, Zayac B, Mehta A, Ludwig A, Takeuchi I. Combinatorial study of Fe-Co-V hard magnetic thin films. Sci Technol Adv Mater 2017; 18:231-238. [PMID: 28458744 PMCID: PMC5402764 DOI: 10.1080/14686996.2017.1287520] [Citation(s) in RCA: 5] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 02/11/2016] [Revised: 01/24/2017] [Accepted: 01/24/2017] [Indexed: 06/07/2023]
Abstract
Thin film libraries of Fe-Co-V were fabricated by combinatorial sputtering to study magnetic and structural properties over wide ranges of composition and thickness by high-throughput methods: synchrotron X-ray diffraction, magnetometry, composition, and thickness were measured across the Fe-Co-V libraries. In-plane magnetic hysteresis loops were shown to have a coercive field of 23.9 kA m-1 (300 G) and magnetization of 1000 kA m-1. The out-of-plane direction revealed enhanced coercive fields of 207 kA m-1 (2.6 kG) which was attributed to the shape anisotropy of column grains observed with electron microscopy. Angular dependence of the switching field showed that the magnetization reversal mechanism is governed by 180° domain wall pinning. In the thickness-dependent combinatorial study, co-sputtered composition spreads had a thickness ranging from 50 to 500 nm and (Fe70Co30)100-xVx compositions of x = 2-80. Comparison of high-throughput magneto-optical Kerr effect and traditional vibrating sample magnetometer measurements show agreement of trends in coercive fields across large composition and thickness regions.
Collapse
Affiliation(s)
- Sean W. Fackler
- Department of Materials Science & Engineering, University of Maryland, College Park, MD, USA
| | - Vasileios Alexandrakis
- Materials Measurement Science Division, Institute for Materials, Ruhr-Universität Bochum, Bochum, Germany
| | - Dennis König
- Materials Measurement Science Division, Institute for Materials, Ruhr-Universität Bochum, Bochum, Germany
| | - A. Gilad Kusne
- National Institute of Standards and Technology, Gaithersburg, MD, USA
| | - Tieren Gao
- Department of Materials Science & Engineering, University of Maryland, College Park, MD, USA
| | - Matthew J. Kramer
- Ames Laboratory and Materials Science and Engineering, Iowa State University, Ames, IA, USA
| | - Drew Stasak
- Department of Materials Science & Engineering, University of Maryland, College Park, MD, USA
| | - Kenny Lopez
- Department of Materials Science & Engineering, University of Maryland, College Park, MD, USA
| | - Brad Zayac
- Department of Materials Science & Engineering, University of Maryland, College Park, MD, USA
| | - Apurva Mehta
- Stanford Synchrotron Radiation Lightsource/SLAC, Stanford University, Menlo Park, CA, USA
| | - Alfred Ludwig
- Materials Measurement Science Division, Institute for Materials, Ruhr-Universität Bochum, Bochum, Germany
| | - Ichiro Takeuchi
- Department of Materials Science & Engineering, University of Maryland, College Park, MD, USA
| |
Collapse
|
7
|
Kusne AG, Keller D, Anderson A, Zaban A, Takeuchi I. High-throughput determination of structural phase diagram and constituent phases using GRENDEL. Nanotechnology 2015; 26:444002. [PMID: 26469294 DOI: 10.1088/0957-4484/26/44/444002] [Citation(s) in RCA: 23] [Impact Index Per Article: 2.6] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/05/2023]
Abstract
Advances in high-throughput materials fabrication and characterization techniques have resulted in faster rates of data collection and rapidly growing volumes of experimental data. To convert this mass of information into actionable knowledge of material process-structure-property relationships requires high-throughput data analysis techniques. This work explores the use of the Graph-based endmember extraction and labeling (GRENDEL) algorithm as a high-throughput method for analyzing structural data from combinatorial libraries, specifically, to determine phase diagrams and constituent phases from both x-ray diffraction and Raman spectral data. The GRENDEL algorithm utilizes a set of physical constraints to optimize results and provides a framework by which additional physics-based constraints can be easily incorporated. GRENDEL also permits the integration of database data as shown by the use of critically evaluated data from the Inorganic Crystal Structure Database in the x-ray diffraction data analysis. Also the Sunburst radial tree map is demonstrated as a tool to visualize material structure-property relationships found through graph based analysis.
Collapse
Affiliation(s)
- A G Kusne
- Materials Measurement Science Division, National Institute of Standards and Technology, Gaithersburg, MD 20899, USA
| | | | | | | | | |
Collapse
|