Symposium MT02-Battery Manufacturing—Emerging Opportunities in Data-Driven Experimentation, Analysis and Modeling

Rechargeable batteries are among the key technologies for decarbonization, with expanding applications in electronics, transportation and power grids. The demand for lighter devices and safer, longer-duration energy storage continues to fuel the need for battery innovation. This need, in turn, requires designing new materials, understanding how they function and, ultimately, developing scalable processes to manufacture them. However, moving from early discovery to commercial deployment may take a decade or longer due to multifaceted requirements related to lifetime, safety, cost, and environmental impact. With the advances in artificial intelligence (AI) and machine learning (ML), in silico tools and workflows for automated characterization and data analysis are emerging. These data-driven approaches show great promise in high-throughput autonomous experimentation and in silico design pipelines. When combined, data-driven characterization, analysis and modeling can greatly accelerate the otherwise ultra-long process from battery materials discovery to commercial deployment and the impact can be transformative.

This symposium highlights the crucial roles of data-driven experimentation, analysis and modeling in accelerating the process of moving from lab-scale battery research and development to large-scale battery manufacturing. This symposium aims to advocate the emerging opportunities in using AI/ML to close the loop from early discovery to commercial deployment and to gather insights from the battery community regarding research needs. It will serve as a platform for developing collaborations among AI/ML developers, data scientists, theorists, and battery researchers broadly from industry, academia and national laboratories.

Topics will include:

Advanced artificial intelligence and machine learning (AI/ML) techniques for battery materials development and manufacturing
Ontologies for the adoption of AI/ML in battery sciences
AI/ML for battery informatics
AI/ML for data analytics and high-throughput experimentation
AL/ML for automated high-throughput modeling
Al/ML for supply-chain analysis and management
Data-driven process design for materials synthesis, processing, and surface/interface engineering
Digital twins applied to optimization of materials synthesis, electrode/cell fabrication, and recyclability

Invited Speakers:

Abraham Anapolsky (Toyota Research Institute, USA)
Mark Bailey (Wildcat Discovery Technologies, USA)
Piero Canepa (National University of Singapore, Singapore)
Maria Chan (Argonne National Laboratory, USA)
Simon Clark (Stiftelsen for industriell og teknisk forskning, Norway)
Eric Dufek (Idaho National Laboratory, USA)
David Howey (University of Oxford, United Kingdom)
Weihan Li (RWTH Aachen University, Germany)
Elsa Olivetti (Massachusetts Institute of Technology, USA)
Noah Paulson (Argonne National Laboratory, USA)
Krishna Rajan (University at Buffalo, The State University of New York, USA)
Venkat Srinivasan (Argonne National Laboratory, USA)
Changwon Suh (U.S. Department of Energy—Office of Energy Efficiency and Renewable Energy, USA)
Shailesh Upreti (Charge CCCV (C4V), USA)
Venkat Viswanathan (Carnegie Mellon University, USA)
Wei Wang (Pacific Northwest National Laboratory, USA)
Karim Zaghib (Concordia University, Canada)
Yuepeng Zhang (Argonne National Laboratory, USA)