Machine-Learned Interatomic Potentials in Practice
An online seminar on machine-learned interatomic potentials will be organized by EuroCC National Competence Center Sweden (ENCCS) on 30 September 2026.
Quantum-mechanical methods such as density functional theory (DFT) are accurate but limited to small systems and short timescales. Classical force fields are fast but often not accurate or transferable enough. Machine-learned interatomic potentials (MLIPs) could break this trade-off between accuracy and scale, and the field is now moving at remarkable speed. So-called universal or "foundation" models (e.g. MACE-MP, UMA, MatterSim, Orb, the DPA/OpenLAM series) are pre-trained on tens to hundreds of millions of DFT calculations spanning the periodic table. These models approach DFT-level accuracy at a small fraction of the cost. They can be applied out of the box ("zero-sho"”) to almost any chemistry. Afterward, they can be fine-tuned to a specific system with a small amount of targeted data. This shortens the path from question to result for both academic and industrial users.
This webinar is intended for researchers and students in computational materials science, chemistry, and condensed-matter physics, users of classical molecular dynamics (LAMMPS, GROMACS, ASE workflows), HPC support staff and research software engineers, and anyone curious about how the foundation-model paradigm from language and vision AI is reshaping simulation in the natural sciences.