Coupling Electronic Structure Theory with Machine Learning for Chemical Applications
Abstract: Our recent efforts on the development of new computational methods that couple quantum chemistry with machine learning will be discussed. First, a novel molecular fingerprinting method based on persistent homology, an applied branch of topology, that can encode the geometric and electronic structure of molecules for chemical applications will be presented. We have demonstrated its applicability on studies on non-covalent interactions between functional groups of materials and small molecules. The functional groups with enhanced CO2-philic groups can be introduced in the next generation of polymeric membranes with enhanced CO2/N2 separation performance. A short discussion on the applicability of the novel molecular fingerprinting method in catalysis and lanthanide separation will be given.
Second, we have developed a novel approach based on machine-learning algorithms and data that accelerates the convergence of computational chemistry methods. Our method uses quantum chemical data in order to learn correlated wave functions and provide highly accurate electronic energies with less computational effort. We have tested our data-driven method on the coupled-cluster singles-and-doubles (CCSD) level of theory. The data-driven CCSD (DDCCSD) is not an alchemical method since the actual iterative coupled-cluster equations are solved. DDCC provides a remarkable speed-up while it offers transferability from small molecules to larger molecular clusters.
Konstantinos "Kostas" Vogiatzis graduated from the Hellenic-American Educational Foundation and completed his B.S. in chemistry at the University of Athens, Greece, in 2006. He obtained his MSc in Applied Molecular Spectroscopy from the University of Crete, Greece, in 2008, where he worked on theoretical studies of interactions of CO2 with nanomaterials. He received his Ph.D. in 2012 from the Karlsruhe Institute of Technology, Germany, where he worked on explicitly-correlated coupled-cluster in the group of Prof. Wim Klopper. After an eight-month post-doctoral appointment at the Institute of Nanotechnology at the Karlsruhe Institute of Technology, he moved in 2014 at the University of Minnesota (UMN), where he performed post-doctoral research at the group of Prof. Laura Gagliardi. In 2016, Dr. Kostas Vogiatzis joined the University of Tennessee, Knoxville, as an assistant professor of theoretical and computational chemistry. His research group is currently developing new computational methods based on electronic structure theory and machine learning for the theoretical examination of reactivity, catalysis and separation processes. Kostas is the recipient of the 2020 Ffrancon Williams Endowed Faculty Award in Chemistry and the ACS OpenEye Outstanding Junior Faculty Award for Spring 2021.
Location and Address
See CMU Chemistry departmental email or contact the host, Olexandr Isayev, at email@example.com