Joshi
ABSTRACT:
Machine learning (ML) techniques are gearing up to play a significant role in the
field of computational solid mechanics and multiphysics, enabling the integration
of experimental data and physical constraints towards data-driven constitutive
laws, acceleration of computational techniques for multi-scale modeling, and new
paradigms for the solution of forward and inverse problems, to name a few. This
talk will cover three main focus areas surrounding computational solid mechanics,
starting from i) automated and trustworthy constitutive modeling enabled by a
fusion of data-driven and physics-augmented approaches including new results
towards uncertainty quantification, to ii) enabling fast approaches for constitutive
modeling from full-field data using extreme sparsification and transfer learning and
finally, a transition to non-local models for advanced phenomena in solid
mechanics (from fracture to multiscale cascades of instabilities).
BIOGRAPHY:
Dr. Bouklas is an Associate Professor at the Sibley School of Mechanical and
Aerospace Engineering at Cornell University and Director for Research in CAD/CAE
and ML at Pasteur Labs. He received his PhD from the Aerospace Engineering and
Engineering Mechanics department at the University of Texas at Austin and
obtained his Diploma in Mechanical Engineering from the Aristotle University of
Thessaloniki, Greece. Dr. Bouklas' research focuses in the field of computational
solid mechanics and scientific machine learning. Developing theoretical frameworks
and advanced computational methods, he aims to improve the fundamental
understanding of materials and structures, and enhance the predictive capabilities
in relevant engineering applications. He is the recipient of the Young Investigator
Program award from the Air Force Office of Scientific Research, and served in the
leadership of the Cornell SciAI Center funded by ONR.