Symposium MT04-Next-Generation AI-Catalyzed Scientific Workflow for Digital Materials Discovery

Emerging data-driven techniques based on statistics, machine learning, and artificial intelligence (AI) have shown great potential for improving effectiveness of the scientific workflow in material discovery. To widen their application and speed up material innovation, this symposium aims to bring together researchers from interdisciplinary knowledge domains (materials, engineering, computer science, statistics, and robotics) to discuss the fundamental challenges and innovative methodologies of applying emerging AI algorithms to catalyze the scientific workflow in material discovery. The scope of the discussion includes integration of physics/chemistry laws, human intelligence within AI systems, how emerging AI algorithms can be applied to material design and computation, and how big material data can be visualized. The materials are defined in a wide sense, including the building blocks used to create, e.g., molecules, polymers, or metals, and semiconductors. The broad implications resulting from the fruitful discussions will inspire researchers working across research fields to move forward and promote the basic knowledge development and technology deployment.

Topics will include:

  • Physics- and chemistry-informed, explainable machine learning for material development
  • High throughput material simulation enabled by machine learning algorithms
  • Large language models for materials development
  • Generative models for materials design
  • Fuzzy AI and AI with human reasoning for materials development
  • Human-machine interactions, human-machine hybridized intelligence in materials development
  • Data generation & curation
  • Data tools (visualization, dimension reduction) and software
  • AI ethics

Invited Speakers:

  • Raymundo Arroyave (Texas A&M University, USA)
  • Alan Aspuru-Guzik (University of Toronto, Canada)
  • Samuel Blau (Lawrence Berkeley National Laboratory, USA)
  • Gerbrand Ceder (University of California, Berkeley, USA)
  • Michele Ceriotti (École Polytechnique Fédérale de Lausanne, Switzerland)
  • Stefano Curtarolo (Duke University, USA)
  • Pascal Friederich (Karlsruhe Institute of Technology, Germany)
  • Janine George (Federal Institute for Materials Research and Testing, Germany)
  • Renana Gershoni-Poranne (Technion–Israel Institute of Technology, Israel)
  • Brian Giera (Lawrence Livermore National Laboratory, USA)
  • Richard Gottscho (Lam Research Corporation, USA)
  • Ganna Gryn’ova (Heidelberg Institute for Theoretical Studies, Germany)
  • Boris Kozinsky (Harvard University, USA)
  • Heather Kulik (Massachusetts Institute of Technology, USA)
  • Ying Li (University of Wisconsin–Madison, USA)
  • Kohei Nakajima (The University of Tokyo, Japan)
  • Kristin Persson (Lawrence Berkeley National Laboratory, USA)
  • Rampi Ramprasad (Georgia Institute of Technology, USA)
  • Semion Saikin (Kebotix, USA)
  • Aron Walsh (Imperial College London, United Kingdom)
  • Tian Xie (Microsoft, United Kingdom)

Symposium Organizers

Jian Lin
University of Missouri
Department of Mechanical and Aerospace Engineering

Kjell Jorner
ETH Zürich
No Phone for Symposium Organizer Provided , [email protected]

Daniel Tabor
Texas A&M University
No Phone for Symposium Organizer Provided , [email protected]

Dmitry Zubarev
IBM Almaden Research Center
No Phone for Symposium Organizer Provided , [email protected]

Publishing Alliance

MRS publishes with Springer Nature