Abstract: Machine-learned interatomic potentials (MLIPs) offer near-DFT accuracy at classical molecular dynamics computational cost, yet developing accurate, robust potentials for largescale ...

Abstract: This work investigates the thermal conductivity and elastic moduli of silicon nanosheets of varying thicknesses using machine learning interatomic potentials (MLIPs). The training dataset ...

ilearn is a benchmark suite for interatomic potentials in materials science, with a focus on radiation damage research. It provides tools to evaluate the performance of interatomic potentials based on ...

Machine learning is transforming many scientific fields, including computational materials science. For about two decades, scientists have been using it to make accurate yet inexpensive calculations ...

Machine learning is transforming many scientific fields, including computational materials science. For about two decades, scientists have been using it to make accurate yet inexpensive calculations ...

How many times a week do you introduce yourself? Whether it’s in person, virtually, one-on-one, in a large group, or formally or informally, you probably introduce yourself many times a week. Perhaps ...

Machine-Learned Interatomic Potentials for YBa₂Cu₃O₇₋ₓ (YBCO), trained using ACE and MACE. All potentials have been trained on the same DFT data from CP2K. The DFT input file used to collect the ...

illustrating the comprehensive zero-shot benchmark of 19 universal machine learning interatomic potentials and the dominant impact of training data composition for surface energy prediction. A ...

School of Mechanical Engineering, Yonsei University, 50 Yonsei-ro, Seodaemun-gu, Seoul 03722, Republic of Korea School of Mechanical Engineering, Soongsil University, 369 Sangdo-ro, Dongjak-gu, Seoul ...

Catalysts play an indispensable role in modern manufacturing. More than 80% of all manufactured products, from pharmaceuticals to plastics, rely on catalytic processes at some stage of production.