First-principles informed supervised machine learning models for ferroic materials discovery
Dr. Joseph Bennett, Department of Biology & Chemistry (2025)
Abstract: The search for new ferroic materials to advance tomorrow’s generation of materials that are capable of storing energy in a very efficient way is more profound now than ever before. Experimental and computational approaches have helped in accelerating the discovery of these materials, but they have not come far enough. In this work, we plan to incorporate first principle calculations with supervised machine learning approaches to speed up the discovery of these materials. The study will further highlights the power of data-driven material exploration in uncovering the wealth of ferroic materials that lies within the periodic table.
New Examples of Functional Material
Joseph Bennett, Department of Chemistry & Biochemistry, UMBC. (2019)
This project is an exploration of structure-property relationships for new and existing materials related by stoichiometries and symmetry operations; we focus on new examples of ferroelectric and antiferroelectric materials.