November 27 - December 2, 2022
Boston, Massachusetts
December 6 - 8, 2022 (Virtual)
2022 MRS Fall Meeting

Symposium DS03-Artificial Intelligence Approaches for Energy Materials

The nexus of artificial intelligence (AI) and energy materials is crucial to meeting rising global energy demands and combating catastrophic climate change. Advanced AI, machine learning (ML) and data science approaches have revolutionized the design of new materials in recent decades, resulting in an explosion of promising materials for many applications and the development of frameworks to enable their continuous improvement. The benefit of methods rooted in AI, big data and automation has been clearly felt in energy applications, manifesting every day in the form of new calls for funding, publications, and patents on materials for solar cells, thermoelectrics, batteries, fuel cells and other applications. Specific improvements that have led to the accelerated design of energy materials include, but are not limited to, deployment of computations, synthesis and characterization efforts in an automated, high-throughput and large-scale manner, development of ML-based functionals with better accuracies, easy accessibility of frameworks for deep learning and other regression and classification algorithms, the use of convolutional neural networks and advanced computer vision techniques for quick identification of microstructural features, optimization techniques for rational synthesis and testing, and text mining based approaches for scouring the internet to expand existing databases for learning and screening.

This symposium aims to bring together researchers applying AI-based methodologies for all kinds of energy applications, such as inorganic/hybrid/organic photovoltaics, thermoelectrics, photocatalysts and electrocatalysts, batteries, water splitting and hydrogen generation and storage. There will be special focus on studies that involve discovery of new functionalities in metals, semiconductors and insulators, prediction of material synthesizability/feasibility and closing the discovery loop via rational experiments, and creation of online knowledgebases for energy materials prediction and design. Abstracts from across the world on any of the topics listed below will be welcome, and some of the leading researchers in these areas will be invited for longer talks.

Topics will include:

  • Materials screening based on autonomous simulations or experiments combined with ML.
  • AI-simulation-experiment synergy for energy materials.
  • Computer vision for extracting structure-property relationships for energy materials.
  • Deep learning for accelerated structural characterizations such as microscopy and spectroscopy.
  • Optimization of energy materials through AI-guided composition and defect engineering.
  • Natural language processing (NLP) for the energy materials literature.
  • Multi-fidelity machine learning approaches for energy applications.
  • Bayesian optimization and design of experiment approaches.
  • Predicting the synthesizability or synthetic routes of materials.

Invited Speakers:

  • Jakoah Brgoch (University of Houston, USA)
  • Maria K. Chan (Argonne National Laboratory, USA)
  • William Chueh (Stanford University, USA)
  • Samuel Cooper (Imperial College London, United Kingdom)
  • Alejandro Franco (Université de Picardie Jules Verne, France)
  • Grace Gu (University of California, Berkeley, USA)
  • Anubhav Jain (Lawrence Berkeley National Laboratory, USA)
  • Sergei Kalinin (The University of Tennessee, Knoxville, USA)
  • Noa Marom (Carnegie Mellon University, USA)
  • Dane Morgan (University of Wisconsin–Madison, USA)
  • Elsa Olivetti (Massachusetts Institute of Technology, USA)
  • Kristin Persson (University of California, Berkeley, USA)
  • Shyue Ping Ong (University of California, San Diego, USA)
  • Rampi Ramprasad (Georgia Institute of Technology, USA)
  • Kristofer Reyes (University at Buffalo, The State University of New York, USA)
  • Subramanian Sankaranarayanan (Argonne National Laboratory, USA)
  • Kandler Smith (National Renewable Energy Laboratory, USA)
  • Taylor Sparks (University of Utah, USA)
  • Alejandro Strachan (Purdue University, USA)
  • Venkat Viswanathan (Carnegie Mellon University, USA)
  • Chris Wolverton (Northwestern University, USA)

Symposium Organizers

Arun Mannodi Kanakkithodi
Purdue University
Materials Engineering
USA

Sijia Dong
Northeastern University
Chemistry and Chemical Biology
USA

Noah Harris Paulson
Argonne National Laboratory
Applied Materials Division
USA

Logan Ward
The University of Chicago, USA
Computation Institute
USA

Topics

artificial intelligence autonomous research combinatorial energy generation energy storage machine learning materials genome