Abstract: Selected problems in structural materials informatics
In this talk, I will present a few materials research projects that may be of interest to applied math students. I will first give a brief overview of my research field -- structural alloys -- and then present project ideas. Projects typically involve the development and application of machine learning models for materials problems. The projects cover such topics as Bayesian modeling of damage in aluminum alloys; equivariant and symmetry-preserving neural networks for tensorial properties of materials; generative modeling of microstructure of 3D printed metals. The projects are designed to be manageable over the course of one MATH586 semester by an applied math student with good coding skills but without requiring prior experience or knowledge of materials science.