This symposium will highlight advances in computational modeling, big data, and AI/ML approaches for accelerating the discovery, design, and understanding of structural and functional ceramics. Topics will include multiscale computational modeling, data-driven materials discovery, property prediction, digital materials design, and the integration of AI/ML with computational modeling across different length and time scales. While experimental validation and autonomous experimentation are within the scope, the primary emphasis of this symposium is on theory and computational methods rather than AI-enabled manufacturing or experimental workflows. A joint session on closed-loop autonomous ceramic discovery integrating AI/ML, computational modeling, and self-driving laboratories may also be organized if there is sufficient interest.
Session Topics:
Innovations in theoretical methods for structural and functional materials
High throughput and AI/ML aided ceramic materials discovery
Advances in multiscale modeling and the expansion of modeling limits across length and time scales.
Close-loop design of ceramic discovery and understanding
Integration of artificial intelligence (AI), machine learning (ML), large language models (LLM), and laboratory automation to accelerate ceramic design
Development of validated physical and digital twins that integrate predictive modeling with experimental workflows
Symposium Organizer(s):
Bin Ouyang, Vanderbilt University, USA
Jiayu Peng, University at Buffalo, USA
Maria Chan, Argonne National Laboratory, USA
Mina Yoon, Oak Ridge National Laboratory, USA
Daniele Vivona, University of Connecticut, USA
Robert B. Wexler, Washington University in St. Louis, USA
Aiping Chen, Los Alamos National Laboratory, USA
Bai Cui, University of Nebraska-Lincoln, USA
Point(s) of Contact:
Bin Ouyang; bin.ouyang@vanderbilt.edu
Division Sponsor(s):
Basic Science Division
Electronics Division
Energy Materials and Systems Division
Manufacturing Division
ACerS Spring Meeting 2027
May 23 • 28, 2027