Roland St. Michel

Roland St. Michel

Graduate Student

Massachusetts Institute of Technology

Roland joined the group in November 2022 as a Ph.D. student in materials science and engineering. He graduated from Cornell University with a Bachelors of Engineering in Materials Science and Engineering. During his undergradatuate education, he worked for the Wolverton group at Northwestern, on a project to machine learn the difference of formation energy between SCAN and PBE functionals. This is where he became interested in using machine learning.

Interests
  • machine learning
  • density functional theory
  • materials discovery
Education

  • BE in Materials Science and Engineering, 2022

    Cornell University

Publications

  1. The BOS-TMC Dataset: DFT Properties of 159k Experimentally Characterized Transition Metal Complexes Spanning Multiple Charge and Spin States (2026)
  2. The BOS-Lig Dataset: Accurate Ligand Charges from a Consensus Approach for 66,810 Experimentally Synthesized Ligands (2026)
  3. High-Throughput Discovery of Conformation-Switching Mechanophores with Novel Response and Enhanced Reactivity (2026)
  4. molSimplify 2.0: Improved Structure Generation for Automating Discovery in Inorganic Molecular and Reticular Chemistry (2026)
  5. Identifying Dynamic Metal–Ligand Coordination Modes with Ensemble Learning (2025)
  6. Exploring Transition Metal Complexes with Large Language Models (2025)
  7. Graph neural networks for predicting metal–ligand coordination of transition metal complexes (2025)
  8. Exploring beyond experiment: generating high-quality datasets of transition metal complexes with quantum chemistry and machine learning (2025)
  9. Leveraging natural language processing to curate the tmCAT, tmPHOTO, tmBIO, and tmSCO datasets of functional transition metal complexes (2025)

Posts