AI-MI Seminar Series: Adrian Del Maestro (University of Tennessee)

Join us for the next AI-MI Seminar Series talk as we explore how machine learning can push interaction potentials to the accuracy quantum many-body predictions actually require.

Helium adsorbed on atomically thin substrates hosts some of the most interesting quantum many-body physics available in the lab — but what you predict depends sensitively on the adsorption potential you start from. This talk combines actively selected coupled-cluster calculations, multi-fidelity Gaussian process regression and knowledge distillation from universal interatomic potentials to reach single-wavenumber accuracy, a level at which the physics itself changes.

Watch live at youtube.com/@AIMaterialsInstitute

Topic: Helium on atomically thin substrates enables exotic quantum many-body physics, but predictions depend sensitively on the adsorption potential. For benzene and larger polycyclic aromatic hydrocarbons, we combine actively selected coupled-cluster calculations, multi-fidelity Gaussian process regression, and knowledge distillation from universal interatomic potentials to achieve single-wavenumber accuracy. Quantum Monte Carlo reveals qualitative changes in solvation relative to existing models.

Speaker: Adrian Del Maestro is Professor and Head of Physics & Astronomy at the University of Tennessee, Knoxville, with an additional appointment in Electrical Engineering and Computer Science. He leads an interdisciplinary AI-for-quantum-materials group in UT’s NSF-funded MRSEC, using high-performance computing and AI to study collective quantum phenomena. He earned his Ph.D. from Harvard and previously held appointments at UBC, Johns Hopkins, and the University of Vermont.