Machine-learning potentials for nanoscale simulations of tensile deformation and fracture in ceramics

S Lin, L Casillas-Trujillo, F Tasnádi, L Hultman… - npj Computational …, 2024 - nature.com
Abstract Machine-learning interatomic potentials (MLIPs) offer a powerful avenue for
simulations beyond length and timescales of ab initio methods. Their development for …

Automated ab initio-accurate atomistic simulations of dissociated dislocations

L Mismetti, M Hodapp - arxiv preprint arxiv:2311.01830, 2023 - arxiv.org
In (M Hodapp and A Shapeev 2020 Mach. Learn.: Sci. Technol. 1 045005), we have
proposed an algorithm that fully automatically trains machine-learning interatomic potentials …

Automated atomistic simulations of dissociated dislocations with ab initio accuracy

L Mismetti, M Hodapp - Physical Review B, 2024 - APS
In a previous work [M. Hodapp and A. Shapeev, Mach. Learn.: Sci. Technol. 1, 045005
(2020) 2632-2153 10.1088/2632-2153/aba373], we proposed an algorithm that fully …

Machine-learning potentials for nanoscale simulations of deformation and fracture: example of TiB ceramic

S Lin, L Casillas-Trujillo, F Tasnádi, L Hultman… - arxiv preprint arxiv …, 2023 - arxiv.org
Machine-learning interatomic potentials (MLIPs) offer a powerful avenue for simulations
beyond length and timescales of ab initio methods. Their development for investigation of …

Physics-Transfer Learning for Material Strength Screening

Y Zhao, Z Zhang, Z Xu - arxiv preprint arxiv:2403.07526, 2024 - arxiv.org
The strength of materials, like many problems in the natural sciences, spans multiple length
and time scales, and the solution has to balance accuracy and performance. Peierls stress is …