SG-NNP: Species-separated Gaussian Neural Network Potential with Linear Elemental Scaling and Optimized Dimensions for Multi-component Materials

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Yoon, Ji Wei, Zhou, Bangjian, Senthilnath, J
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866929415029522432
author Yoon, Ji Wei
Zhou, Bangjian
Senthilnath, J
author_facet Yoon, Ji Wei
Zhou, Bangjian
Senthilnath, J
contents Accurate simulations of materials at long-time and large-length scales have increasingly been enabled by Machine-learned Interatomic Potentials (MLIPs). There have been increasing interest on improving the robustness of such models. To this end, we engineer a novel set of Gaussian-type descriptors that scale linearly with the number of atoms, reduce informational degeneracy for multi-component atomic environments and apply them in Species-separated Gaussian Neural Network Potentials (SG-NNPs). The robustness of our method was tested by analyzing the impact of various design choices and hyperparameters on Molybdenum (Mo) SG-NNP performance during training and inference/simulation. With less dimensions, SG-NNPs are shown to have superior atomic forces and total energy predictions than other traditional and ML descriptor-based interatomic potentials on diverse set of materials - Ni, Cu, Li, Mo, Si, Ge, NiMo, Li3N and NbMoTaW. From the obtained results we can observe that the proposed method improves the performance of atomic descriptors of complex environments with multiple species.
format Preprint
id arxiv_https___arxiv_org_abs_2407_06615
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SG-NNP: Species-separated Gaussian Neural Network Potential with Linear Elemental Scaling and Optimized Dimensions for Multi-component Materials
Yoon, Ji Wei
Zhou, Bangjian
Senthilnath, J
Materials Science
Accurate simulations of materials at long-time and large-length scales have increasingly been enabled by Machine-learned Interatomic Potentials (MLIPs). There have been increasing interest on improving the robustness of such models. To this end, we engineer a novel set of Gaussian-type descriptors that scale linearly with the number of atoms, reduce informational degeneracy for multi-component atomic environments and apply them in Species-separated Gaussian Neural Network Potentials (SG-NNPs). The robustness of our method was tested by analyzing the impact of various design choices and hyperparameters on Molybdenum (Mo) SG-NNP performance during training and inference/simulation. With less dimensions, SG-NNPs are shown to have superior atomic forces and total energy predictions than other traditional and ML descriptor-based interatomic potentials on diverse set of materials - Ni, Cu, Li, Mo, Si, Ge, NiMo, Li3N and NbMoTaW. From the obtained results we can observe that the proposed method improves the performance of atomic descriptors of complex environments with multiple species.
title SG-NNP: Species-separated Gaussian Neural Network Potential with Linear Elemental Scaling and Optimized Dimensions for Multi-component Materials
topic Materials Science
url https://arxiv.org/abs/2407.06615