Materials Cartography: The Role of Materials Representation

Within materials science, practitioners are concerned with modeling time and length scales that span many orders of magnitude, presenting differing challenges across the atomistic, mesoscale, and device levels. Moreover, problems where data are scarce pose challenges for applying machine learning in many scientific fields. When designing, training, and applying a model, the representation of input features can be just as important as the target and architecture of the model itself. Finding the appropriate way to represent a material of interest is not always straightforward and remains an active area of research. In this talk, I will highlight recent work which explores the concept of materials representation in applications ranging from materials and device-level informatics to molecular dynamics, highlighting intruiging results as well as lessons learned that may be useful for practitioners in diverse subfields of materials science.