Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
173 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Dielectric Tensor Prediction for Inorganic Materials Using Latent Information from Preferred Potential (2405.09052v2)

Published 15 May 2024 in cond-mat.mtrl-sci and cs.LG

Abstract: Dielectrics are crucial for technologies like flash memory, CPUs, photovoltaics, and capacitors, but public data on these materials are scarce, restricting research and development. Existing machine learning models have focused on predicting scalar polycrystalline dielectric constants, neglecting the directional nature of dielectric tensors essential for material design. This study leverages multi-rank equivariant structural embeddings from a universal neural network potential to enhance predictions of dielectric tensors. We develop an equivariant readout decoder to predict total, electronic, and ionic dielectric tensors while preserving O(3) equivariance, and benchmark its performance against state-of-the-art algorithms. Virtual screening of thermodynamically stable materials from Materials Project for two discovery tasks, high-dielectric and highly anisotropic materials, identifies promising candidates including Cs2Ti(WO4)3 (band gap $E_g=2.93 \mathrm{eV}$, dielectric constant $\varepsilon=180.90$) and CsZrCuSe3 (anisotropic ratio $\alpha_r = 121.89$). The results demonstrate our model's accuracy in predicting dielectric tensors and its potential for discovering novel dielectric materials.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (60)
  1. High dielectric constant conjugated materials for organic photovoltaics. Journal of Materials Chemistry A, 5(46):24037–24050, 2017.
  2. Advanced dielectric polymers for energy storage. Energy Storage Materials, 44:29–47, 2022.
  3. Polymer-based dielectrics with high permittivity for electric energy storage: A review. Nano Energy, 89:106438, 2021.
  4. Perspective on ceramic materials for 5g wireless communication systems. Applied Physics Letters, 118(12), 2021.
  5. Recent progress in dielectric resonator antenna: Materials, designs, fabrications, and their performance. Applied Physics Reviews, 10(2), 2023.
  6. High-throughput screening of inorganic compounds for the discovery of novel dielectric and optical materials. Scientific data, 4(1):1–12, 2017.
  7. From the computer to the laboratory: materials discovery and design using first-principles calculations. Journal of Materials Science, 47:7317–7340, 2012.
  8. Inhomogeneous electron gas. Physical review, 136(3B):B864, 1964.
  9. Self-consistent equations including exchange and correlation effects. Physical review, 140(4A):A1133, 1965.
  10. High-throughput density functional perturbation theory and machine learning predictions of infrared, piezoelectric, and dielectric responses. npj computational materials, 6(1):64, 2020.
  11. Computational high-throughput screening of electrocatalytic materials for hydrogen evolution. Nature materials, 5(11):909–913, 2006.
  12. Benchmarking density functional perturbation theory to enable high-throughput screening of materials for dielectric constant and refractive index. Physical Review B, 93(11):115151, 2016.
  13. A critical review of machine learning of energy materials. Advanced Energy Materials, 10(8):1903242, 2020.
  14. De novo creation of a naked eye–detectable fluorescent molecule based on quantum chemical computation and machine learning. Science advances, 8(10):eabj3906, 2022.
  15. Ai-driven discovery of amorphous fluorinated polymer electret with improved charge stability for energy harvesting. Advanced Materials, page 2303827, 2023.
  16. Discovery of polymer electret material via de novo molecule generation and functional group enrichment analysis. Applied Physics Letters, 118(22), 2021.
  17. Deep learning enables rapid identification of potent ddr1 kinase inhibitors. Nature biotechnology, 37(9):1038–1040, 2019.
  18. Discovery of intermetallic compounds from traditional to machine-learning approaches. Accounts of chemical research, 51(1):59–68, 2018.
  19. Prediction of dielectric constants using a combination of first principles calculations and machine learning. Japanese Journal of Applied Physics, 58(SL):SLLC01, 2019.
  20. Accelerated search for abo3-type the electronic contribution of polycrystalline dielectric constants by machine learning. Computational Materials Science, 193:110404, 2021.
  21. Prediction of dielectric constants of abo 3-type perovskites using machine learning and first-principles calculations. Physical Chemistry Chemical Physics, 24(11):7050–7059, 2022.
  22. Dielectric tensor of monoclinic ga2o3 single crystals in the spectral range 0.5–8.5 ev. APL Materials, 3(10), 2015.
  23. Relational inductive biases, deep learning, and graph networks. arXiv preprint arXiv:1806.01261, 2018.
  24. Neural message passing for quantum chemistry. In International conference on machine learning, pages 1263–1272. PMLR, 2017.
  25. Graph networks as a universal machine learning framework for molecules and crystals. Chemistry of Materials, 31(9):3564–3572, 2019.
  26. Schnet–a deep learning architecture for molecules and materials. The Journal of Chemical Physics, 148(24), 2018.
  27. Directional message passing for molecular graphs. arXiv preprint arXiv:2003.03123, 2020.
  28. Equiformer: Equivariant graph attention transformer for 3d atomistic graphs. arXiv preprint arXiv:2206.11990, 2022.
  29. E (3)-equivariant graph neural networks for data-efficient and accurate interatomic potentials. Nature communications, 13(1):2453, 2022.
  30. Equivariant message passing for the prediction of tensorial properties and molecular spectra. In International Conference on Machine Learning, pages 9377–9388. PMLR, 2021.
  31. Teanet: Universal neural network interatomic potential inspired by iterative electronic relaxations. Computational Materials Science, 207:111280, 2022.
  32. Towards universal neural network potential for material discovery applicable to arbitrary combination of 45 elements. Nature Communications, 13(1):2991, 2022.
  33. Towards universal neural network interatomic potential. Journal of Materiomics, 9(3):447–454, 2023.
  34. A universal graph deep learning interatomic potential for the periodic table. Nature Computational Science, 2(11):718–728, 2022.
  35. A universal equivariant graph neural network for the elasticity tensors of any crystal system. arXiv preprint arXiv:2307.15242, 2023.
  36. Commentary: The materials project: A materials genome approach to accelerating materials innovation. APL materials, 1(1), 2013.
  37. Optuna: A next-generation hyperparameter optimization framework. In Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining, pages 2623–2631, 2019.
  38. Tensor field networks: Rotation-and translation-equivariant neural networks for 3d point clouds. arXiv preprint arXiv:1802.08219, 2018.
  39. High dielectric ternary oxides from crystal structure prediction and high-throughput screening. Scientific Data, 7(1):81, 2020.
  40. Machine learning models for predicting the dielectric constants of oxides based on high-throughput first-principles calculations. Physical Review Materials, 4(10):103801, 2020.
  41. Accelerating materials property predictions using machine learning. Scientific reports, 3(1):2810, 2013.
  42. High-throughput ab initio calculations on dielectric constant and band gap of non-oxide dielectrics. Scientific reports, 8(1):14794, 2018.
  43. Novel high-κ𝜅\kappaitalic_κ dielectrics for next-generation electronic devices screened by automated ab initio calculations. NPG Asia Materials, 7(6):e190–e190, 2015.
  44. Enhancing materials property prediction by leveraging computational and experimental data using deep transfer learning. Nature communications, 10(1):5316, 2019.
  45. Overcoming data scarcity with transfer learning. arXiv preprint arXiv:1711.05099, 2017.
  46. Atomsets as a hierarchical transfer learning framework for small and large materials datasets. npj Computational Materials, 7(1):173, 2021.
  47. Accurate molecular polarizabilities with coupled cluster theory and machine learning. Proceedings of the National Academy of Sciences, 116(9):3401–3406, 2019.
  48. Learning atomic multipoles: prediction of the electrostatic potential with equivariant graph neural networks. Journal of Chemical Theory and Computation, 18(3):1701–1710, 2022.
  49. Vysetti Balaram. Rare earth elements: A review of applications, occurrence, exploration, analysis, recycling, and environmental impact. Geoscience Frontiers, 10(4):1285–1303, 2019.
  50. Generalized gradient approximation made simple. Physical review letters, 77(18):3865, 1996.
  51. Electron-energy-loss spectra and the structural stability of nickel oxide: An lsda+ u study. Physical Review B, 57(3):1505, 1998.
  52. A high-throughput infrastructure for density functional theory calculations. Computational Materials Science, 50(8):2295–2310, 2011.
  53. Peter E Blöchl. Projector augmented-wave method. Physical review B, 50(24):17953, 1994.
  54. From ultrasoft pseudopotentials to the projector augmented-wave method. Physical review b, 59(3):1758, 1999.
  55. Gaussian error linear units (gelus). arXiv preprint arXiv:1606.08415, 2016.
  56. Sigmoid-weighted linear units for neural network function approximation in reinforcement learning. Neural networks, 107:3–11, 2018.
  57. Swish: a self-gated activation function. arXiv preprint arXiv:1710.05941, 7(1):5, 2017.
  58. Pay attention to mlps. Advances in Neural Information Processing Systems, 34:9204–9215, 2021.
  59. 3d steerable cnns: Learning rotationally equivariant features in volumetric data. Advances in Neural Information Processing Systems, 31, 2018.
  60. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101, 2017.
Citations (2)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets