ENTEG guest seminar by Prof Alexander Shapeev entitled: "Machine-learning interatomic potentials as a reliable computational tool"
|When:||Fr 23-04-2021 14:30 - 16:00|
|Where:||online, link: http://meet.google.com/wfc-hkgi-jxr|
The Multi-Scale Mechanics (MSM) group (PI: Dr Francesco Maresca ) presents:
A guest seminar by Prof Alexander Shapeev entitled: "Machine-learning interatomic potentials as a reliable computational tool"
Over the past 15 years, machine-learning interatomic potentials have evolved from a promising idea to a wide field of materials modeling. The idea is that a true interatomic interaction energy (or an accurate quantum-mechanical model of it) can be approximated as a function of positions of neighbors of each atom with a flexible (systematically improvable) functional form. Making such potentials reliable is not an easy task: one must make sure that all relevant configurations, those that the potential must not fail, are added to the training set. In my talk I will show how using active learning algorithms ensures this automatically turning machine-learning potentials to a reliable computational tool of seamlessly accelerating quantum-mechanical calculations. Namely, I will present my version of machine-learning potentials, moment tensor potentials, and an active learning algorithm automating the procedure of assembling the dataset. I will show how the two algorithms combined allow for an automatic acceleration by orders of magnitude in such applications as constructing convex hulls of stable alloy structures or computing vibrational and configurational free energy of alloys. Moreover, machine-learning potentials can be used as a screening tool before the final quantum-mechanical calculation, offering a speedup of several orders of magnitude without committing any numerical error.
Alexander Shapeev has completed his PhD in Mathematics from National University of Singapore. After two postdoc projects on classical computational methods, he started developing new methodologies in computational materials science as he assumed an Assistant Professor position at Skolkovo Institute of Science and Technology (Moscow, Russia). He is now an Associate Professor at the same institution and author of more than 40 peer-review papers one of which was awarded the Outstanding Paper Prize of the Society of Industrial and Applied Mathematics (United States).