1307 Machine Learning and Uncertainty Quantification for Materials Design

  • Vahid Keshavarzzadeh, University Of Utah
  • Arash Noshadravan, Texas A&M
  • Johann Guilleminot, Duke University

Research in computational mechanics will continue to rely on advances in scientific computation. The aim of this mini-symposium is to provide a platform to discuss recent developments in advanced computational and machine learning techniques as these pertain to design optimization and uncertainty quantification in the context of mechanics and materials.

Topics include but are not limited to:
• Inverse materials design and discovery
• Physics-based and simulation-based deep learning
• Multiscale topology optimization
• Bio-inspired materials design
• Damage-based design optimization
• Variational inference and Bayesian neural networks for uncertainty analysis and design
• Multilevel and multifidelity approaches for uncertainty quantification and Stochastic PDEs
• Provably scalable regression and UQ techniques

This mini-symposium provides a forum that encourages the interaction of interdisciplinary researchers in various fields, including civil, mechanical, aerospace engineering, and computer science.

© WCCM-APCOM 2022. All Rights Reserved.