SKM 2023 – wissenschaftliches Programm
Bereiche | Tage | Auswahl | Suche | Aktualisierungen | Downloads | Hilfe
O: Fachverband Oberflächenphysik
O 73: Metal Substrates: Adsorption and Reaction of Small Molecules II
O 73.1: Vortrag
Donnerstag, 30. März 2023, 10:30–10:45, CHE 91
Benchmarking machine-learned interatomic potentials for reactive surface dynamics at metal surfaces: accuracy vs speed — •Wojciech Stark1, Julia Westermayr1, Cas van der Oord2, Lingjun Zhu3, Bin Jiang3, Gabor Csanyi2, and Reinhard Maurer1 — 1University of Warwick, UK — 2University of Cambridge, UK — 3University of Science and Technology of China, China
Machine-learned interatomic potentials (MLIP) have become widely used tools to accelerate ab initio molecular dynamics simulations in materials science. Many promising MLIPs emerged recently, ranging from simple linear models to deep neural networks (DNN), differing in stability, accuracy, and inference time. Reactive scattering dynamics are highly sensitive to potential corrugation and low reaction probabilities require extensive ensemble averaging. Therefore, MLIPs need to combine smooth and accurate landscapes with extremely efficient inference. In this study, we compare different families of MLIPs, from atomic cluster expansion (ACE), message-passing based Neural Network SchNet and embedded atom neural networks (EANN), to equivariant neural networks such as PaiNN and MACE on the example of reactive molecular hydrogen scattering on copper. We compare these diverse methods by measuring accuracy and inference performance directly on dynamical observables. This provides a detailed picture of MLIP accuracy, speed, and learning rate that goes beyond simple train/test error analysis.