Organizers:
- Shengfeng Yang, Purdue University
- Ying Li, University of Wisconsin-Madison
- Steve Waiching Sun, Columbia University
- Emma Lejeune, Boston University
Description:
The integration of machine learning (ML) with multiscale modeling and simulation is transforming computational engineering, driving innovation across diverse engineering disciplines. Advances in artificial intelligence (AI) are not only enhancing the efficiency of traditional computational techniques but also enabling new insights into the behavior of complex materials and structures across scales. This mini-symposium aims to provide a platform for exploring the latest developments in ML-driven modeling and simulation methodologies, focusing on their applications to diverse material systems and multiscale phenomena. Contributions that demonstrate the integration of ML with modeling and simulation at the atomic, mesoscale, and macroscopic levels are encouraged.
Topics of interest:
We welcome submissions in, but not limited to, the following topics.
- Applications of ML integrated with multiscale modeling methods, including but not limited to molecular dynamics, phase-field modeling, and finite element analysis.
- Applications of data-driven approaches for designing materials at micro and meso scales.
- AI-driven methods for additive manufacturing and 3D printing of complex materials.
- Data-centric approaches for the design, synthesis, and characterization of polymers and composite materials.
- ML-assisted approaches for exploring deformation mechanisms in complex materials.