journal article·2021-12

Artificial intelligence model for efficient simulation of monatomic phase change material antimony

Mengchao Shi, Junhua Li, Ming Tao, Xin Zhang, Jie Liu

Publisher page

Abstract

Abstract This paper presents an efficient and accurate artificial intelligence (AI) model, to calculate the emerging monatomic phase change material antimony, by leveraging the cutting-edge AI technologies like active learning (AL) and deep learning (DL). The required dataset size of the AI model training is reduced by about one order of magnitude, by using the state-of-the-art AL technology, leading to efficient AI model training. It is shown that the potential energy surface, phonon dispersion, coordination number, radial distribution function, angular distribution function, and phase transition processes calculated by using the proposed AI model could agree well with those calculated by using DFT and DFT-based MD, indicating decent accuracy of the proposed AI model. It is well known that the simulation time of the proposed AI model scales as O(n), which is much more favorable than the O(n3) scaling scenario of the widely-used DFT and DFT-based MD, paving a way to future-generation fully-atomistic device simulations free of finite-size effects.
Source: openaire · Quality: candidate unverified · Source record ↗

Research context

OpenAlex topics: Phase-change materials and chalcogenides · Machine Learning in Materials Science · Advanced Memory and Neural Computing

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

References (53)

Show source-provided references
1. Designing crystallization in phase-change materials for universal memory and neuro-inspired computing10.1038/s41578-018-0076-x ↗
2. In-memory computing with resistive switching devices10.1038/s41928-018-0092-2 ↗
3. Accurate deep neural network inference using computational phase-change memory10.1038/s41467-020-16108-9 ↗
4. One-dimensional thickness scaling study of phase change material Ge2Sb2Te5 using a pseudo 3-terminal device10.1109/TED.2011.2121911 ↗
5. Low-power switching of phase-change materials with carbon nanotube electrodes10.1126/science.1201938 ↗
6. Reducing the stochasticity of crystal nucleation to enable subnanosecond memory writing10.1126/science.aao3212 ↗
7. Rapid‐phase transitions of GeTe‐Sb2Te3 pseudobinary amorphous thin films for an optical disk memory10.1063/1.348620 ↗
8. Phase-change heterostructure enables ultralow noise and drift for memory operation10.1126/science.aay0291 ↗
9. Breaking the speed limits of phase-change memory10.1126/science.1221561 ↗
10. From local structure to nanosecond recrystallization dynamics in AgInSbTe phase-change materials10.1038/nmat2931 ↗
11. Monatomic phase change memory10.1038/s41563-018-0110-9 ↗
12. Direct evidence of phase separation in Ge2Sb2Te5 in phase change memory devices
13. Crystallization properties of ultrathin phase change films10.1063/1.2938076 ↗
14. Influence of interfaces and doping on the crystallization temperature of Ge–Sb10.1063/1.3133344 ↗
15. Toward the ultimate limit of phase change in Ge2Sb2Te510.1021/nl902777z ↗
16. Formation of monatomic metallic glasses through ultrafast liquid quenching10.1038/nature13617 ↗
17. Glasses made from pure metals10.1038/nature13653 ↗
18. New horizons for glass formation and stability10.1038/nmat4292 ↗
19. Insights into antimony adsorption on {001} TiO2: XAFS and DFT study10.1021/acs.est.7b00807 ↗
20. Unraveling the stacking effect and stability in nanocrystalline antimony through DFT10.1016/j.jpcs.2019.109156 ↗
21. Density functional study of structure and dynamics in liquid antimony and Sbn clusters10.1063/1.4983219 ↗
22. DFT study of Sb(III) and Sb(V) adsorption and heterogeneous oxidation on hydrated oxide surfaces10.1016/j.comptc.2011.11.031 ↗
23. Crystallization of supercooled liquid antimony: a density functional study10.1103/PhysRevB.96.184102 ↗
24. Local structural origin of the crystallization tendency of pure and alloyed Sb10.1002/pssr.201800552 ↗
25. Chalcogenides by design: functionality through metavalent bonding and confinement10.1002/adma.201908302 ↗
26. Thermal transport in phase-change materials from atomistic simulations10.1103/PhysRevB.86.104301 ↗
27. Neural network interatomic potential for the phase change material GeTe10.1103/PhysRevB.85.174103 ↗
28. End-to-end symmetry preserving inter-atomic potential energy model for finite and extended systems
29. Deep potential molecular dynamics: a scalable model with the accuracy of quantum mechanics10.1103/PhysRevLett.120.143001 ↗
30. Generalized neural-network representation of high-dimensional potential-energy surfaces10.1103/PhysRevLett.98.146401 ↗
31. Multilayer feedforward networks are universal approximators10.1016/0893-6080(89)90020-8 ↗
32. DeePMD-kit: a deep learning package for many-body potential energy representation and molecular dynamics10.1016/j.cpc.2018.03.016 ↗
33. Active learning of uniformly accurate interatomic potentials for materials simulation
34. DP-GEN: a concurrent learning platform for the generation of reliable deep learning based potential energy models10.1016/j.cpc.2020.107206 ↗
35. Deep potential molecular dynamics: a scalable model with the accuracy of quantum mechanics10.1103/PhysRevLett.120.143001 ↗
36. Quickstep: fast and accurate density functional calculations using a mixed Gaussian and plane waves approach10.1016/j.cpc.2004.12.014 ↗
37. Generalized gradient approximation made simple10.1103/PhysRevLett.77.3865 ↗
38. Canonical dynamics: equilibrium phase-space distributions10.1103/PhysRevA.31.1695 ↗
39. A unified formulation of the constant temperature molecular dynamics methods10.1063/1.447334 ↗
40. Local structural origin of the crystallization tendency of pure and alloyed Sb10.1002/pssr.201800552 ↗
41. Phase relations in the Nb-Cr-Sb and Nb-Mn-Sb systems10.1134/S0020168511100141 ↗
42. Chemical understanding of resistance drift suppression in Ge–Sn–Te phase-change memory materials10.1039/C9TC04810C ↗
43. Reversing the resistivity contrast in the phase‐change memory material GeSb2Te4 using high pressure10.1002/aelm.201500240 ↗
44. Aging mechanisms in amorphous phase-change materials10.1038/ncomms8467 ↗
45. Cooling rate and stress relaxation in silica melts and glasses via microsecond molecular dynamics10.1103/PhysRevE.92.012320 ↗
46. Effects of system size and cooling rate on the structure and properties of sodium borosilicate glasses from molecular dynamics simulations10.1063/1.5007083 ↗
47. Quench-rate and size-dependent behaviour in glassy Ge2Sb2Te5 models simulated with a machine-learned Gaussian approximation potential10.1088/1361-6463/ab77de ↗
48. Molecular-dynamics simulation of Ge rapidly cooled from the molten state into the amorphous state10.1103/PhysRevB.62.7103 ↗
49. A multi-scale analysis of the crystallization of amorphous germanium telluride using ab initio simulations and classical crystallization theory10.1063/1.4861721 ↗
50. Crystallization properties of the Ge2Sb2Te5 phase-change compound from advanced simulations10.1002/adfm.201500849 ↗
51. PLUMED: a portable plugin for free-energy calculations with molecular dynamics10.1016/j.cpc.2009.05.011 ↗
52. Fast crystallization of the phase change compound GeTe by large-scale molecular dynamics simulations10.1021/jz402268v ↗
53. Effect of pressure on nucleation and growth in the Zr46.75Ti8.25Cu7.5Ni10Be27.5 bulk glass-forming alloy investigated usingin situx-ray diffraction10.1103/PhysRevB.68.184105 ↗