Skip to main content
Search

# Machine Learning Interatomic Potential

3 related articles

Subscribe to updates
  1. arXiv

    Fine-tuning a MACE foundation model fixes sodium clustering in hard carbon, cutting formation-energy error from 32.43 to 1.65 meV/atom

    Pretrained MACE atomistic foundation models describe sodium intercalation in graphite-like domains but treat the metallic attraction between sodium atoms on graphene as repulsion, so they miss the clustering and pore filling that shape hard-carbon storage. Targeted fine-tuning on 1,985 sodium-cluster configurations plus 300 expanded graphite and sodium reference configurations lowers the formation-energy mean absolute error on the sodium-cluster data from 32.43 to 1.65 meV/atom and raises R² from -36.32 to 0.87. After fine-tuning on a broader sodium-carbon set, the model still gives a 2.03 meV/atom formation-energy error on sodium-filled carbon nanotubes excluded from training, and it links closed-pore radius to plateau voltage.

  2. arXiv

    Magnetic neuroevolution potential puts spins into the energy surface, running two-million-atom spin-lattice dynamics on one consumer GPU

    A magnetic neuroevolution potential takes magnetic moments as inputs alongside atomic positions, so different magnetic orders of the same atomic structure no longer share one energy surface. Trained on the same datasets for the same number of iterations as a standard neuroevolution potential without magnetic descriptors, it cuts energy root-mean-square error by up to about one order of magnitude on CrN, Fe and FeGe. Spin-lattice simulations of Fe give a magnetic transition temperature near 1000 K, close to the experimental Curie temperature of 1043 K, and one consumer-grade GPU handles coupled dynamics of more than two million atoms.

  3. arXiv

    Multi-fidelity Machine Learning Interatomic Potentials for Charged Point Defects

    Using vacancies in the semiconductor Sb2Se3 as a case study, this work finds that current foundation machine learning interatomic potentials trained on bulk data do not reliably identify defect ground states, and introduces global defect charge embeddings in the MACE architecture together with a multi-fidelity training strategy combining low-cost PBE data with high-quality HSE06 data, achieving ground-state identification within 0.05 Å and defect formation energies and thermodynamic transition levels within 0.02 eV of hybrid-functional DFT at a fixed defect supercell size, while uncovering global minima missed by standard defect search workflows.

You’re all caught up