Amir Natan
Talk: Machine Learning Models in Atomistic Simulations: When Can We Trust Their Predictions?
Accurate interatomic forces and total energies are essential for atomistic simulations such as molecular dynamics (MD) and Monte Carlo (MC) for the correct prediction of materials properties and processes. First-principles methods such as density-functional theory (DFT) and other quantum methods provide reliable forces and energies but are often prohibitively expensive. In the last two decades, machine-learning (ML) interatomic models have demonstrated close to first-principles accuracy while remaining several orders of magnitude faster than DFT (but still slower than classical force fields). This raises two important questions: How trustworthy are simulations driven by ML models, and how can we quantify their predictive uncertainty? I examine those questions in three different projects: (1) deep-learning simulations of interlayer sliding in defective graphene and the role of chemical bond formation and rapture in controlling friction; (2) evaluation of the performance of uncertainty-quantification (UQ) signals for direct DL force/energy models; and (3) analysis of how ML errors can affect the inference of materials properties such as the melting temperature at various pressures.
BIO:
Amir Natan is an associate professor in the department of Physical Electronics, school of ECE, Tel Aviv University, Israel. He received his B.Sc. in Physics and Mathematics from the Hebrew University, Israel, his M.Sc. in Electrical Engineering from Tel-Aviv University, Israel, and his PhD in chemistry from the Weizmann Institute of Science, Israel.
The group of Prof. Natan develops and uses quantum and classical methods for multi-scale characterization of materials with a focus on energy applications.
His research includes: the development of highly efficient methods for real-space density functional theory (DFT) and time dependent density functional theory (TDDFT) calculations, the development of deep learning (DL) methods for accurate and efficient force-fields for molecular dynamics (MD) calculations, DFT calculations of materials and specifically materials surfaces and interfaces, and classical MD simulations for the understanding of processes in battery solvent materials. In recent years, his group has specialized in simulations of oxygen reduction reaction (ORR) and additional reactions at surfaces for metal-air batteries and fuel cells.