You are here

Physics-Informed Learning and Data-Enabled Predictive Modeling and Discovery of Complex Systems

[Note: Minisymposium #315 merged with this minisymposium]

Danial Faghihi, University of Buffalo

Jian-xun Wang, University of Notre Dame

Kathryn Maupin, Sandia National Laboratories

Alireza Tabarraei, University of North Carolina at Charlotte

Hao Sun, Northeastern University

Recent advances in computational science have resulted in the ability to perform large-scale simulations and processing massive amounts of data obtained from measurements, images, or high-fidelity simulations of complex physical systems.  Harnessing such large and heterogeneous observational data and integrating those with physics-based models have enabled the scientific community to advance computational models' prediction capabilities.
This symposium aims to highlight novel efforts to develop predictive computational models.  Enhancing the predictive power of models requires novel computational frameworks to systematically use all relevant observational data and quantify the uncertainty in predictions delivered by these models.  This minisymposium provides a forum for advancing scientific knowledge of data-driven complex system modeling/discovery and discussing recent developments in physics-informed machine learning and data interpretation algorithms.  Potential topics may include but are not limited to efforts on:
  • Bayesian validation and selection of multi-scale/multi-physics models
  • UQ analyses of high-fidelity discrete (molecular dynamics, agent-based) models
  • Physics-informed machine/deep learning
  • Data-driven discovery of physical laws
  • The interface of UQ and AI
  • Design, control, and decision making under uncertainty
  • Integrated multi-scale modeling and image analyses
  • Computational imaging
  • Operator inference for model reduction and surrogate modeling
  • Learning from high-dimensional and uncertain data
  • Multi-level, multi-fidelity, and dimension reduction methods
  • Learning the structure of the high-fidelity physics-based model from data
  • UQ methods for stochastic, time-dependent models with high-dimensional parameter space
  • Scalable, adaptive, and efficient UQ algorithms
  • Extensible software framework for large-scale inference and UQ