USACM Thematic Conference on Uncertainty Quantification for Machine Learning Integrated Physics Modeling (UQ-MLIP)

Photos from the event

Computational models of real world systems are rapidly integrating data-driven models from the field of Machine Learning with first-principles based physics models. The uncertainty associated with each class of models needs careful characterization and the quantification of uncertainties in outcomes of the integrated models demands for novel approaches or extensions of existing methodologies. The scope also includes their applications or extensions to many related sub-topics including digital twinning, large scale integrated computations, active decision making in UQ frameworks, etc.

The objectives of the conference are to bring together leading experts, scientists, young researchers, in these domains of interest in order to exchange about the latest developments and identify challenges and opportunities to advance the field.

Sponsored by the Uncertainty Quantification and Probabilistic Modeling Technical Thrust Area of the U. S. Association for Computational Mechanics as well as NSF and Sandia National Laboratories.

Organizing Committee:

Abani Patra, Tufts University

Serge Prudhomme, Polytechnique Montréal

Johann Guilleminot, Duke University

Jian-Xun Wang, University of Notre Dame

Nathaniel Trask, Sandia National Laboratories

Krishna Garikipati, University of Michigan

Yue Yu, Lehigh University

James Stewart, Sandia National Laboratories

Scientific Committee:

Yuri Bazilevs, Brown University

Suvranu De, Rensselaer Polytechnic Institute

Charbel Farhat, Stanford University

Roger Ghanem, University of South California

Omar Ghattas, The University of Texas at Austin

Somnath Ghosh, Johns Hopkins University

Lori Graham-Brady, Johns Hopkins University

George Karniadakis, Brown University

Wing Kam Liu, Northwestern University

Youssef Marzouk, MIT

Habib Najm, Sandia National Laboratories

Michael Parks, Sandia National Laboratories