Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
167 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
42 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

Gaussian Plane-Wave Neural Operator for Electron Density Estimation (2402.04278v2)

Published 5 Feb 2024 in physics.chem-ph and cs.LG

Abstract: This work studies machine learning for electron density prediction, which is fundamental for understanding chemical systems and density functional theory (DFT) simulations. To this end, we introduce the Gaussian plane-wave neural operator (GPWNO), which operates in the infinite-dimensional functional space using the plane-wave and Gaussian-type orbital bases, widely recognized in the context of DFT. In particular, both high- and low-frequency components of the density can be effectively represented due to the complementary nature of the two bases. Extensive experiments on QM9, MD, and material project datasets demonstrate GPWNO's superior performance over ten baselines.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (52)
  1. Application of dft calculations in designing polymer-based drug delivery systems: An overview. Pharmaceutics, 14(9):1972, 2022.
  2. Pseudopotentials that work: From h to pu. Physical Review B, 26(8):4199, 1982.
  3. Blöchl, P. Electrostatic decoupling of periodic images of plane-wave-expanded densities and derived atomic point charges. The Journal of chemical physics, 103(17):7422–7428, 1995.
  4. Blöchl, P. E. Projector augmented-wave method. Physical review B, 50(24):17953, 1994.
  5. Efficient prediction of 3d electron densities using machine learning. arXiv preprint arXiv:1811.06255, 2018.
  6. Quantum chemical accuracy from density functional approximations via machine learning. Nature communications, 11(1):5223, 2020.
  7. Bypassing the kohn-sham equations with machine learning. Nature communications, 8(1):872, 2017.
  8. Lead-free perovskite compounds cssn 1- x ge x i 3- y br y explored for superior visible-light absorption. Physical Chemistry Chemical Physics, 23(26):14449–14456, 2021.
  9. Equivariant neural operator learning with graphon convolution. arXiv preprint arXiv:2311.10908, 2023.
  10. 3d u-net: learning dense volumetric segmentation from sparse annotation. In Medical Image Computing and Computer-Assisted Intervention–MICCAI 2016: 19th International Conference, Athens, Greece, October 17-21, 2016, Proceedings, Part II 19, pp.  424–432. Springer, 2016.
  11. Electron density learning of non-covalent systems. Chemical science, 10(41):9424–9432, 2019.
  12. Fast and uncertainty-aware directional message passing for non-equilibrium molecules. arXiv preprint arXiv:2011.14115, 2020a.
  13. Directional message passing for molecular graphs. arXiv preprint arXiv:2003.03123, 2020b.
  14. e3nn: Euclidean neural networks, 2022.
  15. Advanced capabilities for materials modelling with quantum espresso. Journal of physics: Condensed matter, 29(46):465901, 2017.
  16. Gill, P. M. Molecular integrals over gaussian basis functions. In Advances in quantum chemistry, volume 25, pp.  141–205. Elsevier, 1994.
  17. Abinit: First-principles approach to material and nanosystem properties. Computer Physics Communications, 180(12):2582–2615, 2009.
  18. Transferable machine-learning model of the electron density. ACS central science, 5(1):57–64, 2018.
  19. Hafner, J. Ab-initio simulations of materials using vasp: Density-functional theory and beyond. Journal of computational chemistry, 29(13):2044–2078, 2008.
  20. Harrison, W. A. Pseudopotentials in the theory of metals. (No Title), 1966.
  21. Self—consistent molecular orbital methods. xii. further extensions of gaussian—type basis sets for use in molecular orbital studies of organic molecules. The Journal of Chemical Physics, 56(5):2257–2261, 1972.
  22. Gaussian error linear units (gelus). arXiv preprint arXiv:1606.08415, 2016.
  23. Commentary: The materials project: A materials genome approach to accelerating materials innovation. APL materials, 1(1), 2013.
  24. Deepdft: Neural message passing network for accurate charge density prediction. arXiv preprint arXiv:2011.03346, 2020.
  25. Equivariant graph neural networks for fast electron density estimation of molecules, liquids, and solids. npj Computational Materials, 8(1):183, 2022.
  26. Equivariant graph neural networks for fast electron density estimation of molecules, liquids, and solids. npj Computational Materials, 8(1), 2022. doi: 10.1038/s41524-022-00863-y.
  27. Kittel, C. Introduction to solid state physics. John Wiley & sons, inc, 2005.
  28. Use of energy derivative of the radial solution in an augmented plane wave method: application to copper. Journal of Physics F: Metal Physics, 5(11):2041, 1975.
  29. Self-consistent equations including exchange and correlation effects. Physical review, 140(4A):A1133, 1965.
  30. Charge-transfer-induced lattice collapse in ni-rich ncm cathode materials during delithiation. The journal of physical chemistry C, 121(44):24381–24388, 2017.
  31. Ewald-based long-range message passing for molecular graphs, 2023.
  32. Neural operator: Learning maps between function spaces, 2023.
  33. A guide to Monte Carlo simulations in statistical physics. Cambridge university press, 2021.
  34. Fourier neural operator for parametric partial differential equations. arXiv preprint arXiv:2010.08895, 2020a.
  35. Neural operator: Graph kernel network for partial differential equations. arXiv preprint arXiv:2003.03485, 2020b.
  36. Geometry-informed neural operator for large-scale 3d pdes. In Thirty-seventh Conference on Neural Information Processing Systems, 2023.
  37. A hybrid gaussian and plane wave density functional scheme. Molecular Physics, 92(3):477–488, 1997.
  38. Deeponet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operators. arXiv preprint arXiv:1910.03193, 2019.
  39. Martin, R. M. Electronic Structure: Basic Theory and Practical Methods. Cambridge University Press, 2004. doi: 10.1017/CBO9780511805769.
  40. Quantum chemistry structures and properties of 134 kilo molecules. Scientific data, 1(1):1–7, 2014.
  41. Enumeration of 166 billion organic small molecules in the chemical universe database gdb-17. Journal of chemical information and modeling, 52(11):2864–2875, 2012.
  42. E (n) equivariant graph neural networks. In International conference on machine learning, pp.  9323–9332. PMLR, 2021.
  43. Equivariant message passing for the prediction of tensorial properties and molecular spectra. In International Conference on Machine Learning, pp.  9377–9388. PMLR, 2021.
  44. A representation-independent electronic charge density database for crystalline materials, 2021.
  45. Deep neural network computes electron densities and energies of a large set of organic molecules faster than density functional theory (dft). arXiv preprint arXiv:1809.02723, 2018.
  46. Phase neural operator for multi-station picking of seismic arrivals. Geophysical Research Letters, 50(24):e2023GL106434, 2023.
  47. Gaussian and plane-wave mixed density fitting for periodic systems. The Journal of chemical physics, 147(16), 2017.
  48. Tensor field networks: Rotation-and translation-equivariant neural networks for 3d point clouds. arXiv preprint arXiv:1802.08219, 2018.
  49. Factorized fourier neural operators. In The Eleventh International Conference on Learning Representations, 2023. URL https://openreview.net/forum?id=tmIiMPl4IPa.
  50. Comparison between gaussian-type orbitals and plane wave ab initio density functional theory modeling of layer silicates: Talc [mg3si4o10 (oh) 2] as model system. The Journal of chemical physics, 139(20), 2013.
  51. Large scale dataset of real space electronic charge density of cubic inorganic materials from density functional theory (dft) calculations. Scientific Data, 9(1):59, 2022.
  52. Crystal graph convolutional neural networks for an accurate and interpretable prediction of material properties. Phys. Rev. Lett., 120:145301, Apr 2018. doi: 10.1103/PhysRevLett.120.145301. URL https://link.aps.org/doi/10.1103/PhysRevLett.120.145301.
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