Please contact the symposium organizers with questions.

This symposium will cover new advances in data-driven workflows for the development and discovery of energy conversion and storage materials. The first part of the symposium will focus on experimental work including automated and high-throughput synthesis and characterization. The second part of the symposium will focus on computational work including high-throughput computational screening and active learning workflows.

The experimentally focused portion of the symposium will highlight efforts towards data-driven discovery of materials for energy conversion and storage including photovoltaics, electrocatalysts, and electrochemical energy storage devices. To leverage computational advances and new machine learning approaches, it is vital to generate large, high-quality experimental data sets. To this end, automated and high-throughput laboratory equipment can be used to dramatically accelerate data generation in a well structured format. Symposium contributions should address the use of automated or high-throughput approaches to address basic science questions in materials for energy conversion and storage or address applications of data-driven workflows to quickly discover new materials.

The second part of this symposium will highlight computationally focused efforts towards data-driven discovery of materials for energy conversion and storage. Using data-driven approaches for materials design and discovery presents unique challenges and requires innovation in the application of existing computational tools or the development of completely new tools and workflows. Symposium contributions should address the implementation of machine learning approaches to generate or analyze computational data or address the use of high throughput workflows for energy materials screening using computational techniques such as density functional theory (DFT) calculations and molecular dynamics (MD) simulations.

Topics will include:

• Automated laboratories for energy conversion and storage materials discovery
• High-throughput materials characterization
• Active learning in materials discovery
• High-throughput data processing
• Machine learning to predict performance
• Machine learning assisted molecular simulations
• Natural language processing (NLP) for materials discovery
• Physics-based machine learning
• Visualization and interpretation of materials data
• Workflows that combines experiment and simulation

Invited Speakers:

• Alán Aspuru-Guzik (University of Toronto, Canada)
• William Chueh (Stanford University, USA)
• Jacqueline Cole (University of Cambridge, United Kingdom)
• Andy Cooper (University of Liverpool, United Kingdom)
• Abigail Doyle (Princeton University, USA)
• Rafael Gomez-Bombarelli (Massachusetts Institute of Technology, USA)
• John Gregoire (California Institute of Technology, USA)
• Jennifer Lewis (Harvard University, USA)
• Elsa Olivetti (Massachusetts Institute of Technology, USA)
• Kenichi Oyaizu (Waseda University, Japan)
• Kristin Persson (Lawrence Berkeley National Laboratory, USA)
• Charles M. Schroeder (University of Illinois at Urbana-Champaign, USA)
• Taylor Sparks (University of Utah, USA)
• Dee Strand (Wildcat Discovery Technologies, USA)
• Zachary W. Ulissi (Carnegie Mellon University, USA)
• Venkat Viswanathan (Carnegie Mellon University, USA)
• Hongliang Xin (Virginia Tech, USA)

Symposium Organizers