Juner Zhu, Massachusetts Institute of Technology
Hongyi Xu, University of Connecticut
Sulin Zhang, Penn State
Christos E. Athanasiou, Brown
Wei Li, MIT
Advanced engineered systems are usually complex. The complexity mainly comes from two aspects: i) multiple length- and time-scales and ii) multiple physical effects, such as mechanics, chemical reactions, mass and heat transfer, etc. Physics-based or first-principle-based theories have achieved great successes but gradually suffer from the “curse of dimensionality” as the number of variables and degrees of freedom increases. Recently, many data-driven approaches particularly machine learning have shown prominent advantages of dealing with high-dimensional problems, but they are usually agnostic and prone to unphysical failure. This symposium will not only welcome applications of data-driven approaches to discover, characterize and design a wide variety of multiscale and/or multiphysics systems but also dive deep into the issue of combining data-driven approaches with physics-based theories.