Predicting CASSCF-Derived Magnetic Anisotropy from DFT: A Metal-Centred Model for Co(II)

- 344849
Lecture
Favorite this paper
How to cite this paper?
Abstract

This lecture presents an ExtraTrees model that uses compact Co-centred DFT descriptors to predict five CASSCF-derived spin-Hamiltonian quantities for Co(II): D, E/D, gx, gy, and gz. Trained on 33,731 audited DFT/CASSCF geometry pairs, the model achieved R² values of 0.967–0.983 for coordination numbers 4–6, without encoding the full ligand molecular graph.

Share your ideas or questions with the authors!

Did you know that the greatest stimulus in scientific and cultural development is curiosity? Leave your questions or suggestions to the author!

Sign in to interact

Have a question or suggestion? Share your feedback with the authors!

Institutions
  • 1 Federal Rural University of Rio de Janeiro
  • 2 Department of Inorganic Chemistry, Institute of Chemistry, Fluminense Federal University (UFF), Niterói, RJ, Brazil
Track
  • Lecture
Keywords
Magnetic anisotropy
machine learning
multireference electronic structure