Click here to learn about Academy events, publications and initiatives around COVID-19.

We are experiencing intermittent technical difficulties. At this time, you may not be able to log in, register for an event, or make a donation via the website. We appreciate your patience, and apologize for any inconvenience this may cause.

Our site is under planned maintenance. At this time, you will not be able to log in, register for an event, or make a donation via the website. We appreciate your patience, and apologize for any inconvenience this may cause.

Support The World's Smartest Network
×

Help the New York Academy of Sciences bring late-breaking scientific information about the COVID-19 pandemic to global audiences. Please make a tax-deductible gift today.

DONATE
This site uses cookies.
Learn more.

×

This website uses cookies. Some of the cookies we use are essential for parts of the website to operate while others offer you a better browsing experience. You give us your permission to use cookies, by continuing to use our website after you have received the cookie notification. To find out more about cookies on this website and how to change your cookie settings, see our Privacy policy and Terms of Use.

We encourage you to learn more about cookies on our site in our Privacy policy and Terms of Use.

eBriefing

Advances in AI for Materials

Advances in AI for Materials
Reported by
Liang Dong and Jennifer L. Costley

Posted December 02, 2020

Presented By

The New York Academy of Sciences

Previous conferences and workshops covering artificial intelligence (AI) for Materials Science have mainly focused on introducing AI into materials simulations, which is only the first step in new materials discovery. These efforts have largely ignored AI’s promise for materials synthesis and translating research into high-volume industrial production.

On October 6-7, 2020, the New York Academy of Sciences hosted the AI for Materials symposium to provide a broader perspective on leveraging the benefits of AI in material simulations, experiments, and development efforts for high volume production. The symposium brought together materials scientists, industry experts, and AI researchers to cover the application of AI throughout the entire life cycle of new materials, from lab discovery to industrial production. These leaders also shape future research directions, identify urgent issues in this rising field, and foster interdisciplinary collaboration opportunities.


In This eBriefing, You’ll Learn

  • How machine learning is being applied to understand the physical processes behind materials science
  • Approaches to improve the data infrastructures used in materials science research to facilitate easier integration and promote a better data sharing environment
  • How AI is being applied to address industry-related issues in materials science, including the scalability of materials production from the lab to the factory and the synthetic and catalytic routes of new materials

Speakers and Panelists

Leon Bottou
Léon Bottou, PhD

Facebook AI Research

Carla Gomes
Carla Gomes, PhD

Cornell University

Rama Vasudevan
Rama Vasudevan, PhD

Oak Ridge National Laboratory

Rampi Ramprasad
Rampi Ramprasad, PhD

Georgia Institute of Technology

Matthias Scheffler
Matthias Scheffler, PhD

The Fritz Haber Institute

Elsa Olivetti
Elsa Olivetti, PhD

MIT

Muratahan Aykol
Muratahan Aykol, PhD

Toyota Research Institute

Nobuyuki Matsuzawa
Nobuyuki N. Matsuzawa, PhD

Panasonic Corporation

Michael Helander
Michael Helander, PhD

OTI Lumionics

Sam Samdani
Sam Samdani, PhD

McKinsey & Company

Philipp Harbach
Philipp Harbach, PhD

Merck KGaA

James Warren
James Warren, PhD

National Institute of Standards and Technology

Greg Mulholland
Greg Mulholland

Citrine Informatics

Tim Robertson, PhD
Tim Robertson, PhD

Schrödinger, Inc.

Phillip M. Maffettone
Phillip M. Maffettone, DPhil

Brookhaven National Laboratory

Physics and Causality in Machine Learning

Speakers

Léon Bottou, PhD
Facebook AI Research

Léon received a Ph.D. in Computer Science from Université de Paris-Sud. His research career has taken him to AT&T Bell Laboratories, AT&T Labs Research, NEC Labs America, Microsoft, and now Facebook AI Research. The long-term goal of Léon's research is to understand and replicate human-level intelligence. Because this goal requires conceptual advances that cannot be anticipated, Léon’s research has followed many practical and theoretical turns, including neural networks applications, stochastic gradient learning algorithms, statistical properties of learning systems, computer vision applications with structured outputs, and theory of large-scale learning. Léon's research aims to clarify the relation between learning and reasoning, with focus on the many aspects of causation.

Léon Bottou (Facebook AI Research)

Carla Gomes, PhD
Cornell University

Carla is the Ronald C. and Antonia V. Nielsen Professor of Computing and Information Science and the Director of the Institute for Computational Sustainability at Cornell University. She received a Ph.D. from the University of Edinburgh. Her research area is artificial intelligence with a focus on Computational Sustainability. Computational Sustainability aims to develop computational methods to help solve some of the key challenges concerning environmental, economic, and societal issues to help put us on a path towards a sustainable future. Carla is a Fellow of the Association for the Advancement of Artificial Intelligence (AAAI), a Fellow of the Association for Computing Machinery (ACM), and a Fellow of the American Association for the Advancement of Science (AAAS).

Carla Gomes (Cornell University)

Rama Vasudevan, PhD
Oak Ridge National Laboratory

Rama is the Research and Development Associate at the Center for Nanophase Materials Sciences, Oak Ridge National Laboratory. His research focuses on utilizing scanning probe microscopy (SPM) at the mesoscopic and atomic level to unearth structure-property relations in various systems, including ferroics, manganites, and others. In parallel, as vast amounts of imaging and spectroscopic data are gathered, he develops and implements tools from existing computational science literature towards tackling materials science problems and unearthing physics from deep data analysis of SPM-acquired datasets. Rama received his PhD in Materials Science from the University of New South Wales.

Rama Vasudevan (Oak Ridge National Laboratory)

Further Readings

General

Hill J, Mulholland G, Persson K, et al.

MRS Bulletin. 2016 May;41(5):399-409.

Bottou

Chen Z, Zhang J, Arjovsky M, Bottou L.

arXiv. 2019 Sep 29;1909.13334.

Gomes

Gomes CP, Bai J, Xue Y, et al.

MRS Communications. 2019 Apr;9(02):1-9.

Data Infrastructures for Materials Science

Speakers

Rampi Ramprasad, PhD
Georgia Institute of Technology

Rampi is the Michael E. Tennenbaum Family Chair and Georgia Research Alliance Eminent Scholar in Energy Sustainability at Georgia Tech. His area of expertise is developing and utilizing computational and data-driven (machine learning) methods to design and discover new materials. Materials classes under study include polymers, metals, and ceramics (mainly dielectrics and catalysts), and application areas include energy production and energy storage. Rampi received his B Tech in Metallurgical Engineering at the Indian Institute of Technology, Madras, India, and a PhD in Materials Science & Engineering at the University of Illinois, Urbana-Champaign.

Rampi Ramprasad (Georgia Institute of Technology)

Matthias Scheffler, PhD
The Fritz Haber Institute 

Matthias is Director of the NOMAD Laboratory at the Fritz Haber Institute of the Max Planck Society. His research focuses on understanding fundamental aspects of physical and chemical properties of surfaces, interfaces, clusters, nanostructures, and bulk based on electronic-structure theory. In recent years, Matthias developed neural-network and compressed-sensing methods to detect structure and patterns in “big data of materials,” to create “maps of materials properties,” and identify “materials genes” that affect or even actuate materials properties. His “big-data” activities also include creating a FAIR data infrastructure (data are findable and AI-ready) and the largest data store for computational materials science data.

Matthias Scheffler (The Fritz Haber Institute)

Elsa Olivetti, PhD
Massachusetts Institute of Technology

Elsa is the Esther and Harold E. Edgerton Associate Professor in Materials Science and Engineering at MIT. She received her PhD from the same department in 2007. Elsa’s research focuses on improving the environmental and economic sustainability of materials in the context of rapid-expanding global demand. Her research addresses two major problems where solutions could yield significant environmental benefit: first, improving the sustainability of materials through increased use of recycled and renewable materials, recycling-friendly material design, and intelligent waste disposition; and second, understanding the implications of substitution, dematerialization, and waste mining on materials markets.  Her research spans three levels of materials production: operational-level, industrial network-level, and market-level strategies.

Elsa Olivetti (Massachusetts Institute of Technology)

Muratahan Aykol, PhD
Toyota Research Institute

Muratahan is a Senior Research Scientist in Accelerated Materials Design and Discovery at the Toyota Research Institute. Before that, he was a postdoctoral research fellow at Lawrence Berkeley National Laboratory, working on materials informatics and infrastructure. He received his BS and MS degrees from the Middle East Technical University and a PhD in Materials Science from Northwestern University. His research focuses on machine-learning, material computations, and network science for materials discovery.

Muratahan Aykol (Toyota Research Institute)

Further Readings

Ramprasad

Kim C, Chandrasekaran A, Huan TD, et al.

J Phys Chem C . 2018 Jul 18;122:17575.

Scheffler

Ghiringhelli LM, Vybiral J, Levchenko SV, et al.

Phys Rev Lett. 2015 Mar 13;114(10):105503.

Goldsmith BR, Boley M, Vreeken J, et al.

New J Phys. 2017 Jan;19:013031.

Sutton C, Boley M, Ghiringhelli LM, et al.

Nat. Commun. 2020;11:4428.

Olivetti

Aykol

Aykol M, Herring P, Anapolsky A.

Nat Rev Mater. 2020 June 15;5:725-727.

Montoya JH, Winther KT, Flores RA, et al.

Chem Sci. 2020 July 30;11:8517.

Aykol M, Hedge VI, Hung L, et al.

Nat Commun. 2019 May 1;10:2018.

AI in Materials Production and Industry

Speakers

Nobuyuki N. Matsuzawa, PhD
Panasonic Corporation

Nobu obtained his PhD in computational materials science in 1994 from The University of Tokyo.  He started his career at Sony in 1987, developing various organic materials for electronic devices and lithography processes for semiconductor manufacturing. He served as a visiting research scientist at DuPont Central Research and Development in Wilmington, Delaware, and was the Senior Manager of Material Science Laboratories of Sony Europe from 2001-2004. In 2005, Nobu was named a Distinguished Engineer at Sony. Since 2016, he has been working for Panasonic, designing materials used in various electronic devices produced by Panasonic.

Nobuyuki N. Matsuzawa (Panasonic Corporation)

Michael Helander, PhD
OTI Lumionics

Michael is co-founder and CEO of OTI Lumionics, an advanced materials company he co-founded while pursuing his PhD at the University of Toronto in 2011. The company commercializes disruptive materials and process technology for OLED displays from headquarters in Toronto and offices in Asia. OLED is the leading display technology used in virtually all high-end consumer electronics and is the next generation of design-driven lighting. Dr. Helander received a BSc in Engineering Science and a PhD in Materials Science & Engineering from the University of Toronto. He has over 100 patents and peer-reviewed publications related to OLED materials, process, equipment, and displays.

Michael Helander (OTI Lumionics)

Phillip M. Maffettone, DPhil
Brookhaven National Laboratory

Phil is currently a Research Associate in Computational Science at Brookhaven National Laboratory, where he focuses on developing the laboratory of the future using artificial intelligence to combine simulation and autonomous experimentation. During his career, Phil has developed a healthy disregard for disciplinary boundaries by working at the intersection of physical and computational sciences. He earned a BS in Chemical Engineering at the University at Buffalo (2014), researching silicon nanoparticle synthesis and applications. After receiving a Marshall Scholarship, he completed his DPhil in Inorganic Chemistry at the University of Oxford (2018), focused on simulating disorder in diffraction where Bragg’s law breaks down in hard and soft matter. Phil recently returned home to New York from a role at the University of Liverpool, where he developed the AI for an autonomous mobile robotic scientist searching for new photocatalytic materials.

Phillip M. Maffettone (Brookhaven National Laboratory)

Further Readings

Matsuzawa

Maffettone

Burger B, Maffettone PM, Gusev VV, et al.

Nature. 2020 Jul 8;583:237-241.

Automating Production from Lab to Factory

Moderator/Panelists

Sam Samdani, PhD
McKinsey & Company

Sam is a senior industry expert in the Global Chemicals & Agriculture Practice at McKinsey & Company, a global management consulting firm. His responsibilities include providing thought leadership across a range of complex knowledge domains in advanced/engineered materials, pharmaceutical ingredients, and specialty chemicals for the top management of many multinational chemical, pharmaceutical, and petroleum companies as well as government agencies and NGOs worldwide.  Before joining McKinsey, Sam worked at McGraw-Hill as an Associate Editor with Chemical Engineering, a monthly technical publication. He received his BS in chemical engineering from Yale University and his PhD in chemical engineering from the University of Rochester.

 

Philipp Harbach, PhD
Merck KGaA

Philipp is the Head of In Silico Research in the Digital Organization of Merck KGaA. There he focuses on the digitalization of chemical and experimental processes in R&D, production, and analytics with the help of modern computational modeling and data analytics methods. He is specifically interested in applying quantum mechanical methods to industrial problems and is leading first initiatives to adapt these algorithms to noisy intermediate-scale quantum computers as part of the Merck Quantum Computing Task Force.

 

James Warren, PhD
National Institute of Standards and Technology

Since 2010,  Jim has been focusing his energies on the US Materials Genome Initiative, a multi-agency initiative designed to create a new era of policy, resources, and infrastructure that supports US institutions to discover, manufacture, and deploy advanced materials twice as fast a fraction of the cost. As Director of the NIST Materials Genome Program, he works with a government-wide team to build out the materials innovation infrastructure need to realize the initiative’s goals.   He is also one of the co-founders and the current Director of the NIST Center for Theoretical and Computational Materials Science. Jim has a PhD in physics from the University of California, Santa Barbara.

 

Greg Mulholland, Founder and CEO
Citrine Informatics

Greg is the co-founder and CEO of Citrine Informatics and a recognized leader in the use of digital tools and digitization practices in the development of next-generation materials and chemicals products and the creation of next-generation business models. Under his leadership, Citrine has been recognized as a WEF Technology Pioneer, a member of the Cleantech 100, the World Materials Forum Startup of the Year, and CB Insights AI 100 in 2017 and 2020. Greg holds a BS in Electrical Engineering and a BS in Computer Engineering from NC State University, an MPhil in Materials Science from Cambridge University, and an MBA from Stanford University.

 

Tim Robertson, PhD
Schrödinger, Inc.

Tim is a full-stack software engineer with a doctorate in computational biology and extensive experience in applied machine learning.  He worked as a data scientist for companies such as Twitch and Yelp and founded two YCombinator-funded startups. Currently, Tim is Principal Scientist at Schrödinger, where he works in a hybrid scientist/engineer role, developing and applying deep learning and other AI techniques to problems in rational drug design.  He has a PhD in Computational Biology (Biochemistry) from the University of Washington.

Panel Discussion


Samdani/Harbach/Warren/Mulholland/Robertson (McKinsey/Merck KGaA/NIST/Citrine Informatics/Schrödinger)