Artificial Intelligence and Machine Learning for Ceramics and Glasses
Join ACerS and MRS for a two-day virtual workshop, March 26-27, 2024, 11 a.m. – 2:30 p.m. EST
Workshop Description
The realm of materials science stands at the forefront of a wave wherein machine learning (ML) and artificial intelligence (AI) are playing revolutionizing roles. This joint MRS/ACerS workshop is designed to offer insights into the integration of ML and AI in the field of materials science especially for ceramics and glasses, offering a platform for researchers to delve into applications of ML and AI in understanding, developing, and optimizing materials. This workshop will not only showcase cutting-edge research and developments in the field but it also aims to provide a practical guide for incorporating ML into materials science research. Specific topics covered in the workshop include:
- Get started with Materials and ML (Covering data handling, foundational ML concepts, and how it can be applied in materials research)
- ML and Materials Synthesis (How ML is enabling the discovery of novel materials, the integration of AI in automated laboratories, and the development of self-driving labs)
- ML and Materials Modeling (How ML assists atomic-scale simulations, microstructure modeling, macroscopic property predictions, and advancements in simulating material behaviors)
- ML and Materials Characterization (Integration of ML in cutting-edge materials characterization tools such as microscopy, spectroscopy, and synchrotron for faster interpretation of complex data and accelerated physics discovery)
Who Should Attend:
- Materials scientists interested in leveraging ML and AI in their work.
- AI specialists interested in applying ML in the physical sciences.
- Graduate students interested in ML for materials science and physical sciences and engineering.
- Industry professionals exploring innovative solutions for enhancement and productivity.
- Others interested in ML and materials science.
Join us in this exciting workshop to gain insights into the latest research and engage with pioneers in the intersection between ML and materials science.
Workshop Organizers
Yongtao Liu, Oak Ridge National Lab
Bio: Yongtao Liu is a R&D scientist in Data NanoAnalytics Group at the Center for Nanophase Materials Sciences (CNMS), Oak Ridge National Laboratory (ORNL). He obtained his Ph.D. degree from The University of Tennessee, Knoxville in 2020. Driven by a passion for advancing scientific discovery through the fusion of machine learning and microscopy techniques, Dr. Liu's present research focuses on developing cutting-edge autonomous microscopy by harnessing the power of machine learning to accelerate physics and materials discoveries in ferroelectrics, photovoltaics, and optoelectronic materials. Dr. Liu has been the recipient of accolades including MRS Graduate Student Silver Award, AVS Graduate Student Research Award in 2019, Joseph E. Spruiell Award for Excellence in Research, CNMS Postdoctoral Award, Microscopy Society of America (MSA) Postdoctoral Scholar Award, ORNL Outstanding Scholarly Output Award, and R&D 100 Award.
Amanda Krause, Carnegie Mellon University
Bio: Amanda R. Krause is an assistant professor in the Materials Science and Engineering Department at Carnegie Mellon University. Before joining CMU, she was an assistant professor of MSE at the University of Florida. She received her B.S. and M.S. in Materials Science and Engineering from Virginia Tech, and her Ph.D. in Materials Science from Brown University. Before joining University of Florida in 2019, she was a lecturer and post-doctoral research associate at Lehigh University. Her research focus is engineering grain boundaries and interfaces for improving the mechanical performance, degradation response, and thermal properties of ceramics used in extreme environments. She is a recipient of the NSF CAREER award (2022).
Collin Wilkinson, Alfred University
Bio: Dr. Collin Wilkinson is an Assistant Professor of Glass Science at Alfred University. Collin earned a Bachelor’s in Physics at Coe College followed by a Ph.D. in Material Science at the Pennsylvania State University. He served as director of research and development and director of research and development of small startups focusing on next-generation recycling technology through material informatics. Collin is the inventor or co-inventor of several new glass compositions for green applications. Collin joined the faculty at Alfred University in 2022 and his current research revolves around building computational tools for simulations of extreme conditions, understanding the fundamental physics of glassy materials, and engineering better solutions for sustainable glass technology. Collin is the author of over 50 peer-reviewed publications and 4 patents. He is additionally the chair of the undergraduate research committee at Alfred University where he has created a research program for undergraduates from around the world in glass and ceramics.
Day 1, Session 1: How to get started with materials and machine learning
Tuesday, March 26 11:00 a.m. - 12:05 p.m. EST
11:05-11:35 A.M. EST
A Diversity of AI Opportunities Revealed by High Throughput Experimentation
John Gregoire, California Institute of Technology
Bio: John Gregoire is a Research Professor of Applied Physics and Materials Science and leads the High Throughput Experimentation group at Caltech,where he is also the Team Lead for Photoactive Materials in the Liquid Sunlight Alliance, a U.S. DOE Energy Innovation Hub. His research team explores, discovers and understands energy-related materials via combinatorial and high throughput experimental methods and their integration with materials theory and artificial intelligence. The group seeks to accelerate scientific discovery by automating critical components of research workflows, from synthesis and screening to data interpretation and hypothesis generation. He received his B.A. in Math and Physics from Concordia College and PhD in Physics from Cornell University
11:35 A.M. - 12:05 P.M. EST
Innovating at the Interface: Opinionated Tips for Materials Scientists Exploring Machine Learning
Daniel Roberto Cassar, Ilum School of Science, Brazil
Bio: Daniel Cassar is a professor of Data Science at the Ilum School of Science, part of the Brazilian Center for Research in Energy and Materials (CNPEM). He received his Ph.D. in Materials Science and Engineering in 2014 and his B.S. in Materials Engineering in 2009, both from the Federal University of São Carlos (UFSCar), Brazil. He worked as a postdoctoral researcher at the Center for Research, Technology, and Education in Vitreous Materials (CeRTEV) from 2014 to 2021, where he studied dynamic processes in glasses and developed machine learning algorithms to predict glass properties. His current research interests lie at the interface between materials science and computer science, in particular the development of artificial intelligence tools to accelerate the development of new materials. Daniel has published more than 30 peer-reviewed papers in international indexed journals and is the developer of free software tools for glass scientists, GlassPy being the most popular.
Day 1, Session 2: ML and Materials Synthesis
12:05 - 2:30 P.M. EST
12:50-12:35 P.M. EST
Nuclear waste glass formulation using machine learning property models with prediction uncertainty
Xiaonan Lu, Pacific Northwest National Laboratory
Bio: Xiaonan Lu is a Material Scientist in the Radiological Materials Group under the Energy and Environment Directorate at the Pacific Northwest National Laboratory. She holds a PhD degree in Materials Science and Engineering (2018) from the University of North Texas. Her research interests include assessing various aspects of nuclear waste glasses from design, fabrication, corrosion, characterization, and modeling; studying atomistic structural features of multi-component glasses using classical molecular dynamics simulation; investigating composition-structure-property relationships through regression and machine learning approaches; developing computer programming codes for waste glass formulation/optimization routines with prediction and process uncertainties.
12:35-1:05 P.M. EST
Combinatorial Printing for High-Throughput Materials Discovery
Yanliang Zhang, University of Notre Dame
Bio: Yanliang Zhang is an Associate Professor in the Department of Aerospace and Mechanical Engineering. He received Ph.D. degree in Mechanical Engineering from Rensselaer Polytechnic Institute in 2011, and spent over one year in industry prior to his academic positions. Dr. Zhang’s research work has been published on numerous scientific journals of high impact, including Nature Materials, Science Advances, Advanced Materials, Nano Letters, Scientific Reports, Energy Conversion and Management, Applied Physics Letters, etc.
BREAK: 1:05-1:20 P.M.
1:20-1:50 P.M. EST
Collaborative Intelligence in Laboratory Materials Research
Shijing Sun, University of Washington
Bio: Dr. Shjijing Sun is an assistant professor at the University of Washington. Her research primarily focuses on autonomous materials design specifically aimed at advancing clean energy technologies. Before joining UW, Dr. Sun held the position of a senior research scientist at the Toyota Research Institute located in Silicon Valley. During her time there, she dedicated her efforts to the development of AI-powered solutions that aimed to accelerate research and development in the fields of electric vehicle (EV) batteries and fuel cells. Prior to her work at Toyota Research Institute, Dr. Sun worked as a research scientist at the Department of Mechanical Engineering at MIT, where she led a team that focused on the development of high-throughput synthesis and characterisation methods for thin-film solar cells. Dr. Sun completed her academic studies at Trinity College, University of Cambridge, where she obtained her B.A. in Natural Sciences, and M.Sci., and Ph.D. degrees in materials science. She has published over 50 papers and conference proceedings.
1:50-2:20 A.M. EST
Accelerating Inorganic Materials Synthesis and Characterization in Autonomous Laboratories
Yan Zeng, Florida State University
Bio: Yan Zeng is an Assistant Professor in the Department of Chemistry and Biochemistry at Florida State University. Zeng was a Staff Scientist, and earlier a postdoctoral researcher, at Lawrence Berkeley National Laboratory between 2020 and 2023, where she built an autonomous inorganic solid-state synthesis laboratory (the A-Lab) with a team at LBNL and UC Berkeley. She was also interested in finding new materials and exploring synthesis methods to make them. She obtained her PhD degree (2020) in Materials Engineering from McGill University, developing Li-ion battery cathode materials using hydrothermal synthesis. Her current research interests lie at the intersection of lab automation, energy storage materials, synthesis methodology, and battery recycling processes.
Day 2 Session 3: Machine Learning and Materials Modeling
Thursday, March 27 11:05 A.M. - 12:05 P.M. EDT
11:05-11:35 A.M. EST
Application of statistical approaches to proton-conducting phosphate glasses: Study of the effect of oxide components on proton mobility and thermal stability
Takahisa Omata, Tohoku University, Japan
Bio: Takahisa Omata is a Professor at the Institute of Multidisciplinary Research for Advanced Materials (IMRAM), Tohoku University, Japan. He received his B. S. (1987) and M. S. (1989) in Applied Chemistry at Yokohama National University, Japan, and began his research career as a researcher for Mitsui Mining Co., Ltd, Japan. He received his Ph.D. in Materials Science (1994) at Tokyo Institute of Technology, and joined the Department of Chemical Technology, Kanagawa Institute of Technology, Japan, as an assistant professor. He moved to Osaka University in 1996, and became an associate professor in 2001. In 2016, he moved to Tohoku University as a professor.
His expertise pertains to the chemistry of inorganic materials. He has published more than a hundred refereed journal papers. He received CerSJ Awards for advancements in ceramic science and technology (1999), CerSJ Awards for academic achievements in ceramic science and technology (2014), Award of the Outstanding Papers Published in the JCerSJ (1999) from The Ceramics Society of Japan and the Spriggs Phase Equilibria Award from The American Ceramic Society in 2017.
His current research interests include narrow band-gap and multinary wurtzite-type oxides semiconductors, II-VI, I-III-VI2 and III-V semiconductor quantum dots applicable to phosphors and solar cells, and proton conducting glasses for the intermediate temperature fuel cell
11:35-12:05 P.M. EST
Materials Design from Atomistic Simulations and Electron Microscopy Guided by Explainable Scientific Machine Learning
Ayana Ghosh, Oak Ridge National Lab
Bio: Ayana Ghosh is a Research Scientist at the Computational Sciences & Engineering Division at Oak Ridge National Laboratory (ORNL). She completed her MS and PhD in Materials Science and Engineering at the University of Connecticut in 2020, after earning her BS in Physics and Abstract Mathematics from the University of Michigan-Flint in 2015. Her research revolves around the application of scientific machine learning methods, coupled with first principles computations and experiments, to explore a diverse array of functional materials. These materials span from inorganic perovskites and two-dimensional systems to organic crystals and polymers. She has authored 35 papers published in peer-reviewed journals. Her most recent accolades include receiving awards at the Rising Stars in Computational and Data Sciences 2022 at Sandia National Laboratories and Extraordinary Performance Awards in 2022 and 2023 from ORNL.
Day 2 Session 4: Machine Learning and Materials Characterization
12:05 - 2:30 P.M. EST
12:05-12:35 P.M. EST
Theory-informed AI/ML for Materials Characterization
Maria Chan, Argonne National Laboratory
Bio: Maria Chan is a scientist with the Center for Nanoscale Materials who studies nanomaterials and renewable energy materials, including solar cells and batteries and other energy storage, as well as photo- and electro-catalysts, thermal transport, and thermoelectrics. Particular focus is on using machine learning for efficient computational approaches and for interfacing computational models with materials characterization (x-ray, electron, and scanning probe). She is a senior fellow at the Northwestern Argonne Institute for Science and Engineering, and a fellow of the University of Chicago Consortium for Advanced Science and Engineering. She is also an associate editor at the ACS Journal Chemistry of Materials, a member of the Condensed Matter and Materials Research Committee of the National Academies of Sciences, Engineering, and Medicine, and serves on the advisory boards for the journal APL-Machine Learning, Duke’s aiM-NRT AI training project, and CEDARS EFRC.
12:35-1:05 P.M. EST
Deep Learning Defect Detection in Electron Microscopy of Radiation Damage
Dane Morgan, University of Wisconsin - Madison
Bio: : Dane Morgan is the Harvey D. Spangler Professor of Engineering in the department of Materials Science and Engineering at the University of Wisconsin, Madison. His work combines thermostatistics, thermokinetics, and informatics analysis with atomic scale calculations to understand and predict materials properties. Morgan is presently training or has graduated/trained over 70 graduate students and postdoctoral researchers and he leads the Informatics Skunkworks, which has helped engage over 400 undergraduates at the interface of data science and science and engineering. He has received multiple teaching and research awards and has published over 350 papers in materials science
BREAK: 1:05-1:20 P.M.
1:20-1:50 P.M. EST
Machine Learning for High Throughput Characterization of Nanoelectronics
Matthew Hauwiller, Seagate Technology
Bio: Matthew Hauwiller is a senior engineer in the Wafer Metrology Group at Seagate Technology with a background in inorganic nanomaterials, electron microscopy, and image analysis. Matthew received his Ph.D. in Physical Chemistry from the University of California, Berkeley and did his Postdoctoral Research in Material Science and Engineering at MIT. He images the structure and composition of materials at the nanoscale, seeking to elucidate structure-property relationships for the development of better performing devices. Matthew has co-authored 16 peer-reviewed scientific journal publications and contributed 15 presentations to national and international technical conferences.
1:50-2:20 P.M. EST
Boosting Prediction of NMR properties in Disordered Solids with Machine Learning
Thibault Charpentier, Université Paris-Saclay, France
Bio: Dr. Thibault Charpentier is Research Director at CEA Paris-Saclay since 2008. He earned his Ph.D. in Solid State Physics in 1998 from the University of Orsay in the field of NMR spectroscopy of quadrupolar nuclei. After he continued the field of 'solid-state NMR' at a French national institution, CEA, as a research scientist until now. His research interests span NMR theory, development of NMR methodologies and studies of nuclear waste materials such as glasses and cements. Much of his work has studied the structure of oxide glasses, the impact of irradiation and their chemical durability (aqueous corrosion). In parallel, he has explored some theoretical aspects of Spin Dynamics in NMR (Dipolar Order under magic-angle spinning, Floquet-Magnus Theory) and developed numerical methods for modeling NMR spectra of disordered systems. His current research focuses on developing computational methodologies based on DFT and Molecular Dynamics for modeling NMR experiments of materials from first principles. Recently, he examined machine learning methodologies to predict NMR properties in oxide glasses and deep-learning techniques for atomistic scale simulations. Thibault Charpentier has over 180 refereed publications.
Registration rates
| Regular rate | $125 |
| ACerS/MRS member rate* | $100 |
| Student rate | $45 |
| ACerS/MRS student member rate* | $25 |
Sponsors