Aubrey Toland

I am a driven materials scientist with an innate talent for leveraging cutting-edge computational tools to expedite materials research and discovery. Currently my research in my PhD program revolves around utilizing density functional theory, classical molecular dynamics, and machine learning to unravel the mysteries of polymer properties and advance sustainable solutions. I have experience in using scikit-learning to train quick and ready models as well as packages like pytorch, tensorflow, and gpflow to train more advanced and problem tailored models. Currently my interest is in leveraging data generated by both density functional theory and classical molecular dynamics to help close the small data gap that tends to inhibit robust machine learning solutions for many materials science problems. In this vein, I am particularly interested in using deep learning to emulate density functional theory and allow for calculations on length and timescales orders of magnitude larger than currently possible with ab-initio methods. Join me in exploring the limitless possibilities at the intersection of materials science, machine learning, and computational methodologies. Together, let's pioneer solutions that redefine the landscape of sustainable materials and propel us towards a brighter, technologically enriched future.