Symposium MT02-Accelerated Material Discovery—Data-Driven Discovery, High-Throughput Experimentation and Autonomous Laboratories

The exploration and creation of materials have ushered in a new era dominated by big data. Achieving accelerated material discovery necessitates urgent contributions from experiments, theory, simulation, and data science. This symposium is dedicated to integrating these emerging efforts to pave the way for accelerated, or eventually autonomous material discovery. Its particular focus is to foster dialogue on recent advancements in areas such as high-throughput experimentation, database development both from simulation and experiments, and the acceleration of material design through artificial intelligence (AI) and machine learning (ML), in addition to exploring closed-loop experimental architectures and more. The event will feature a diverse array of world-leading experts at the forefront of material discovery. These specialists range from those in lab automation and high-throughput material synthesis to experts in automated characterization and materials testing, as well as in AI/ML, and theory-driven computational methods.

This symposium is designed to present a varied array of perspectives that will guide the future milestones of material discovery. Topics will include, but are not limited to, 1) Progresses of automation in materials synthesis, characterization, and testing; 2) Innovative methods for integrating AI/ML with various experimental approaches; 3) Strategies for utilizing big data to enhance our understanding of different material design spaces; 4) Approaches for closing the feedback loop or enabling rapid iteration across theory, computation, AI/ML, synthesis, and characterization; 5) Opportunities and approaches to incorporate generative AI and large langrage models in materials discovery. We welcome submissions that align with any of the themes or other novel research within the realm of accelerating material discovery.

Topics will include:

Progresses of automation in materials synthesis, characterization, and testing
Innovative methods for improving the throughput of various experimental approaches
Strategies for utilizing big data to enhance our understanding of different material design spaces
New approaches for data harvesting, data fusion and data interpretation across experiment and theory
Opportunities and approaches to incorporate generative AI in materials discovery.
Application of large language models in materials design and discovery
Protocols and platform development for promoting the share of data
Integrating theory driving approaches with AI/ML algorithm

Invited Speakers:

Chibueze Amanchukwu (The University of Chicago, USA)
Ryoji Asahi (Nagoya University, Japan)
Tonio Buonassisi (Massachusetts Institute of Technology, USA)
Gerbrand Ceder (University of California, Berkeley, USA)
Emory Chan (Lawrence Berkeley National Laboratory, USA)
Maria Chan (Argonne National Laboratory, USA)
Ekin Dogus Cubuk (Google DeepMind, USA)
Elif Ertekin (University of Illinois at Urbana-Champaign, USA)
Sheng Gong (ByteDance Inc, USA)
Jason Hattrick-Simpers (University of Toronto, USA)
Sergei Kalinin (University of Tennessee, Knoxville, USA)
Miao Liu (Institute of Physics, Chinese Academy of Science, China)
Shyue Ping Ong (University of California, San Diego, USA)
Kristin Persson (University of California, Berkeley, USA)
Dong-Hwa Seo (Korea Advanced Institute of Science and Technology, Republic of Korea)
Shijing Sun (University of Washington, USA)
Carolin Sutter-Fella (Lawrence Berkeley National Laboratory, USA)
Kazuo Tanaka (Kyoto University, Japan)
Jiayu Wan (Shanghai Jiao Tong University, China)
Yan (Eric) Wang (Samsung Semiconductor US, USA)
Chris Wolverton (Northwestern University, USA)
Tian Xie (Microsoft Research, USA)
Jie Xu (Argonne National Laboratory, USA)
Yan Zeng (Florida State University, USA)