Deep machine learning interatomic potential for liquid silica

Balyakin, I. A.; Rempel, S. V.; Ryltsev, R. E.; Rempel, А. А.

doi:10.1103/physreve.102.052125

“…A DP was developed to simulate liquid and glassy silica which proved to have satisfactory accuracy based upon a relatively small training dataset [143]. Other DPs were developed to calculate transport properties of silicate in the mantle [144][145][146].…”

Section: Multi-element Bulk Systemsmentioning

confidence: 99%

Deep potentials for materials science

Wen

¹

,

Zhang²,

Wang

³

et al. 2022

View full text Add to dashboard Cite

To fill the gap between accurate (and expensive) ab initio calculations and efficient atomistic simulations based on empirical interatomic potentials, a new class of descriptions of atomic interactions has emerged and been widely applied; i.e., machine learning potentials (MLPs). One recently developed type of MLP is the Deep Potential (DP) method. In this review, we provide an introduction to DP methods in computational materials science. The theory underlying the DP method is presented along with a step-by-step introduction to their development and use. We also review materials applications of DPs in a wide range of materials systems. The DP Library provides a platform for the development of DPs and a database of extant DPs. We discuss the accuracy and efficiency of DPs compared with ab initio methods and empirical potentials.

show abstract

“…A DP was developed to simulate liquid and glassy silica which proved to have satisfactory accuracy based upon a relatively small training dataset [150]. Other DPs were developed to calculate transport properties of silicate in the mantle [151][152][153].…”

Section: B Multi-element Bulk Systemsmentioning

confidence: 99%

Deep Potentials for Materials Science

Wen¹,

Zhang²,

Wang³

et al. 2022

Preprint

0

View full text Add to dashboard Cite

To fill the gap between accurate (and expensive) ab initio calculations and efficient atomistic simulations based on empirical interatomic potentials, a new class of descriptions of atomic interactions has emerged and been widely applied; i.e., machine learning potentials (MLPs). One recently developed type of MLP is the Deep Potential (DP) method. In this review, we provide an introduction to DP methods in computational materials science. The theory underlying the DP method is presented along with a step-by-step introduction to their development and use. We also review materials applications of DPs in a wide range of materials systems. The DP Library provides a platform for the development of DPs and a database of extant DPs. We discuss the accuracy and efficiency of DPs compared with ab initio methods and empirical potentials.

show abstract

“…With the rapid development of machine learning (ML), the combination of ML and MD simulations has emerged as a solution to the above challenges [25,26] . This is an advanced approach to develop ML‐based atomic interaction potentials based upon DFT data, with low computational cost and high accuracy [27–33] . Several fitting methods of ML potentials have been developed during the past decades, such as the Behler‐Parrinello neural network potentials (BPNNPs), [34] spectral neighbor analysis potentials (SNAPs), [35] Gauss approximate potentials (GAPs), [36] and the emerging deep neural potentials (DNPs) [37,38] .…”

Section: Introductionmentioning

confidence: 99%

Exploring the Effects of Ionic Defects on the Stability of CsPbI₃ with a Deep Learning Potential

Yang

¹

,

Li

²

,

Chen

³

et al. 2022

View full text Add to dashboard Cite

defects. With regards to surface defects, Cs defects have the largest impact on the stability of CsPbI 3 when the defect concentration is less than 15 %, whereas Pb defects act play a dominant role for defect concentrations exceeding 20 %. Most importantly, this machine-learning-based MD simulation strategy provides a new avenue to explore the ionic defect effects on the stability of perovskite-like materials, laying a theoretical foundation for the design of stable perovskite materials.

show abstract

Deep machine learning interatomic potential for liquid silica

Cited by 42 publications

References 67 publications

Deep potentials for materials science

Deep potentials for materials science

Deep Potentials for Materials Science

Exploring the Effects of Ionic Defects on the Stability of CsPbI₃ with a Deep Learning Potential

Contact Info

Product

Resources

About

Deep machine learning interatomic potential for liquid silica

Cited by 42 publications

References 67 publications

Deep potentials for materials science

Deep potentials for materials science

Deep Potentials for Materials Science

Exploring the Effects of Ionic Defects on the Stability of CsPbI3 with a Deep Learning Potential

Contact Info

Product

Resources

About

Exploring the Effects of Ionic Defects on the Stability of CsPbI₃ with a Deep Learning Potential