Neural network potential for dislocation plasticity in ceramics

npj Computational Materials, Journal Year: 2024, Volume and Issue: 10(1)

Published: Nov. 22, 2024

Abstract Dislocations in ceramics are increasingly recognized for their promising potential applications such as toughening intrinsically brittle and tailoring functional properties. However, the atomistic simulation of dislocation plasticity remains challenging due to complex interatomic interactions characteristic ceramics, which include a mix ionic covalent bonds, highly distorted extensive core structures within crystal structures. These complexities exceed capabilities empirical potentials. Therefore, constructing neural network potentials (NNPs) emerges optimal solution. Yet, creating training dataset that includes proves difficult complexity configurations computational demands density theory large atomic models containing cores. In this work, we propose from properties easier compute via high-throughput calculation. Using dataset, have successfully developed NNPs specifically three typical ceramics: ZnO, GaN, SrTiO 3 . effectively capture nonstoichiometric charged slip barriers dislocations, well long-range electrostatic between dislocations. The effectiveness was further validated by measuring similarity uncertainty across snapshots derived large-scale simulations, alongside validation various Utilizing constructed NNPs, examined through nanopillar compression nanoindentation, demonstrated excellent agreement with experimental observations. This study provides an effective framework enable detailed modeling plasticity, opening new avenues exploring plastic behavior ceramics.

Language: Английский

---

Applications and training sets of machine learning potentials

Science and Technology of Advanced Materials Methods, Journal Year: 2023, Volume and Issue: 3(1)

Published: Oct. 12, 2023

Recently, machine learning potentials (MLPs) have been attracting interest as an alternative to the computationally expensive density-functional theory (DFT) calculations. The data-driven approach in MLPs requires carefully curated training datasets, which define valid domain of simulations. Therefore, acquiring datasets that comprehensively span desired simulations is important. In this review, we attempt set guidelines for systematic construction according target To end, extensively analyze sets previous literature four application types: thermal properties, diffusion structure prediction, and chemical reactions. each application, summarize characteristic reference structures discuss specific parameters DFT calculations such MD conditions. We hope review serves a comprehensive guide researchers practitioners aiming harness capabilities material

Language: Английский

---

CURATOR: Building Robust Machine Learning Potentials for Atomistic Simulations Autonomously with Batch Active Learning

Published: Feb. 16, 2024

To enable fast, resource efficient development and broad scale deployment of high accuracy Machine-Learned Interatomic Potentials (MLIPs) with minimum expert involvement, we introduce CURATOR, an autonomous batch active learning workflow for constructing MLIPs. CURATOR integrates state the art models, uncertainty quantification techniques, selection algorithms user defined labeling chemical-structure space exploration methods data compute learning. We also developed a novel gradient computation method that calculates forces stress based on energy derivative respect to accelerate CURATOR. Our evaluation across different chemical systems demonstrates considerably reduces computational resources time required develop reliable In practical applications in complex materials interfaces, shows promising results, underscoring its potential accelerating discovery. The flexibility efficiency mark significant advancement field science, paving way more larger time-length atomistic simulations.

Language: Английский

---

Development and Validation of Neural Network Potentials for Multicomponent Oxide Glasses

The Journal of Physical Chemistry C, Journal Year: 2024, Volume and Issue: unknown

Published: Oct. 2, 2024

Language: Английский

---

Exploring model complexity in machine learned potentials for simulated properties

Journal of materials research/Pratt's guide to venture capital sources, Journal Year: 2023, Volume and Issue: 38(24), P. 5136 - 5150

Published: Sept. 18, 2023

Abstract Machine learning (ML) enables the development of interatomic potentials with accuracy first principles methods while retaining speed and parallel efficiency empirical potentials. While ML traditionally use atom-centered descriptors as inputs, different models such linear regression neural networks map to atomic energies forces. This begs question: what is improvement in due model complexity irrespective descriptors? We curate three datasets investigate this question terms ab initio energy force errors: (1) solid liquid silicon, (2) gallium nitride, (3) superionic conductor Li $$_{10}$$ 10 Ge(PS $$_{6}$$ 6 ) $$_{2}$$ 2 (LGPS). further how these errors affect simulated properties verify if fitting corresponds measurable property prediction. By assessing models, we observe correlations between quantity (e.g. force) error respect values. Graphical abstract

Language: Английский

---