S23 Landing Banner

Symposium MT03-Machine Learning Methods, Data and Automation for Sustainable Electronics

The need for optimized design, synthesis, and processing conditions is ubiquitous in materials science and technology, impacting fields as diverse as solar energy conversion, electronics, medicine, metallurgy, and energy storage. However, obtaining a target material with desired properties is time-intensive because of the high-dimensional and complex synthetic and processing parameters space. The sampling of the large synthetic and processing landscape is generally done through human intuition, based on the knowledge of physical chemistry principles, and trial-and-error approaches, leading to clustered, sparse and incomplete datasets. In the past decade, automated robotic technologies have been shown to markedly increase productivity in medicine, synthetic biology, chemistry/physics and materials science research fields by offloading repetitive works from human scientists and performing experiments at a faster speed, with greater precision, and better accuracy. With the aid of high-performance computing in recent years, artificial intelligence (AI) has been successfully applied to inorganic materials and small molecule discovery and engineering. Physics-informed machine learning approaches applied to clustering, regression, and Bayesian methods, as well as artificial neural networks, have emerged, and have used and contributed to publicly accessible databases producing new insights. This new integrated experimental and computational paradigm has enormous potential benefits, as the robotic hardware and AI software technologies required to realize this goal are just reaching maturity. The proposed symposium will address the main progress and challenges in the research of AI-guided sustainable (e.g., energy conversion and storage, climate, plastic upcycling) and electronic materials synthesis and processing, and cover the entire life cycle of these studies, from computational design, physically-guided AI, experimental automation, to control methods, synthetic databases, and robotic integration.

Topics will include:

  • ML-assisted computational designs of sustainable and electronic materials
  • Experimental automation for energy and electronic materials discovery
  • High-throughput characterization, laboratory and synchrotron data analytics
  • Autonomous systems for materials research with humans in/out-of-the loop
  • Data standardization, management, graphical database and ontology
  • Workflow design and process engineering for accelerated materials development
  • Self-driving laboratories for organic and inorganic materials discovery
  • AI-assisted microstructure, interface, and device optimization
  • Robotics and control theory to guide scientific experiments
  • Materials informatics for batteries, catalysts, optoelectronics, solar cells, and fuel cells, and quantum devices, etc.
  • Explainable, physics-informed and small dataset machine learning

Invited Speakers (tentative):

  • Chibueze Amanchukwu (The University of Chicago, USA)
  • Nong Arthrith (University of Utrecht, Netherlands)
  • Simon Billinge (Columbia University, USA)
  • Christoph J. Brabec (Friedrich-Alexander-Universität Erlangen-Nürnberg, Germany)
  • Maria Chan (Argonne National Laboratory, USA)
  • Janine George (Federal Institute for Materials Research and Testing, Germany)
  • Rafael Gomez-Bombarelli (Massachusetts Institute of Technology, USA)
  • Jason Hattrick-Simpers (University of Toronto, Canada)
  • Arun Mannodi Kanakkithodi (Purdue University, USA)
  • Rachel Kurchin (Carnegie Mellon University, USA)
  • Benji Maruyama (Air Force Research Laboratory, USA)
  • Reinhard Maurer (University of Warwick, United Kingdom)
  • Austin Mroz (Imperial College London, USA)
  • Lilo Pozzo (University of Washington, USA)
  • Brett Savoie (Purdue Univeristy, USA)
  • Junichiro Shiomi (The University of Tokyo, Japan)
  • Steven Torrisi (Toyota Research Institute, USA)
  • Tejs Vegge (Technical University of Denmark, Denmark)
  • Aron Walsh (Imperial College London, United Kingdom)
  • Martijn Zwijnenburg (University College London, United Kingdom)

Symposium Organizers

Jie Xu
Argonne National Laboratory
USA
No Phone for Symposium Organizer Provided , xuj@anl.gov

Keith Butler
University College London
Department of Chemistry
United Kingdom
No Phone for Symposium Organizer Provided , k.t.butler@ucl.ac.uk

Kedar Hippalgaonkar
Nanyang Technological University
Singapore

Shijing Sun
University of Washington
USA
No Phone for Symposium Organizer Provided , shijing@uw.edu

Publishing Alliance

MRS publishes with Springer Nature