Linking atomic structural defects to mesoscale properties in crystalline solids using graph neural networks
Source abstract
Abstract
Abstract Structural defects are abundant in solids, and vital to the macroscopic materials properties. However, a defect-property linkage typically requires significant efforts from experiments or simulations, and often contains limited information due to the breadth of nanoscopic design space. Here we report a graph neural network (GNN)-based approach to achieve direct translation between mesoscale crystalline structures and atom-level properties, emphasizing the effects of structural defects. Our end-to-end method offers great performance and generality in predicting both atomic stress and potential energy of multiple systems with different defects. Furthermore, the approach also precisely captures derivative properties which strictly observe physical laws and reproduces evolution of properties with varying boundary conditions. By incorporating a genetic algorithm, we then design de novo atomic structures with optimum global properties and target local patterns. The method would significantly enhance the efficiency of evaluating atomic behaviors given structural imperfections and accelerates the design process at the meso-level.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Machine Learning in Materials Science · Graphene research and applications · Ferroelectric and Negative Capacitance Devices
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (70)
Show source-provided references
1. Fang, T.-T. Elements of Structures and Defects of Crystalline Materials (Elsevier, 2018).10.1016/B978-0-12-814268-4.00024-2 ↗
2. Tilley, R. J. D. Defects in Solids (John Wiley & Sons, Ltd, 2008).10.1002/9780470380758 ↗
3. Xu, T. & Sun, L. Structural defects in graphene. Defects Adv. Electron. Mater. Nov. Low. Dimens. Struct. 5, 137–160 (2018).10.1016/B978-0-08-102053-1.00005-3 ↗
4. Cohen-Tanugi, D. & Grossman, J. C. Water desalination across nanoporous graphene. Nano Lett. 12, 3602–3608 (2012).10.1021/nl3012853 ↗
5. Jung, G., Qin, Z. & Buehler, M. J. Molecular mechanics of polycrystalline graphene with enhanced fracture toughness. Extrem. Mech. Lett. 2, 52–59 (2015).10.1016/j.eml.2015.01.007 ↗
6. Cheng, Z., Zhou, H., Lu, Q., Gao, H. & Lu, L. Extra strengthening and work hardening in gradient nanotwinned metals. Science 362, eaau1925 (2018).10.1126/science.aau1925 ↗
7. Shimura, F. Springer Handbook of Electronic and Photonic Materials (Springer International Publishing, 2017).
8. Robertson, A. W. et al. Spatial control of defect creation in graphene at the nanoscale. Nat. Commun. 3, 1144 (2012).10.1038/ncomms2141 ↗
9. Cui, Y. et al. Metallic bond-enabled wetting behavior at the liquid Ga/CuGa2 interfaces. ACS Appl. Mater. Interfaces 10, 9203–9210 (2018).10.1021/acsami.8b00009 ↗
10. Yeo, J. et al. Multiscale design of graphyne-based materials for high-performance separation membranes. Adv. Mater. 31, 1–24 (2019).10.1002/adma.201805665 ↗
11. Wang, S. et al. Atomically sharp crack tips in monolayer MoS2 and their enhanced toughness by vacancy defects. ACS Nano 10, 9831–9839 (2016).10.1021/acsnano.6b05435 ↗
12. Qin, Z., Jung, G. S., Kang, M. J. & Buehler, M. J. The mechanics and design of a lightweight three-dimensional graphene assembly. Sci. Adv. 3, 1–9 (2017).10.1126/sciadv.1601536 ↗
13. Xu, W. et al. Self-folding hybrid graphene skin for 3D biosensing. Nano Lett. 19, 1409–1417 (2019).10.1021/acs.nanolett.8b03461 ↗
14. Ma, A., Roters, F. & Raabe, D. A dislocation density based constitutive model for crystal plasticity FEM including geometrically necessary dislocations. Acta Mater. 54, 2169–2179 (2006).10.1016/j.actamat.2006.01.005 ↗
15. Butler, K. T., Davies, D. W., Cartwright, H., Isayev, O. & Walsh, A. Machine learning for molecular and materials science. Nature 559, 547–555 (2018).10.1038/s41586-018-0337-2 ↗
16. Lecun, Y., Bengio, Y. & Hinton, G. Deep learning. Nature 521, 436–444 (2015).10.1038/nature14539 ↗
17. Hughes, T. W., Williamson, I. A. D., Minkov, M. & Fan, S. Wave physics as an analog recurrent neural network. Sci. Adv. 5, eaay6946 (2019).10.1126/sciadv.aay6946 ↗
18. Qin, Z., Yu, Q. & Buehler, M. J. Machine learning model for fast prediction of the natural frequencies of protein molecules. Rsc. Adv. 10, 16607–16615 (2020).10.1039/C9RA04186A ↗
19. Jensen, Z. et al. A machine learning approach to zeolite synthesis enabled by automatic literature data extraction. ACS Cent. Sci. 5, 892–899 (2019).10.1021/acscentsci.9b00193 ↗
20. Aykol, M. et al. Network analysis of synthesizable materials discovery. Nat. Commun. 10, 2018 (2019).10.1038/s41467-019-10030-5 ↗
21. Karniadakis, G. E. et al. Physics-informed machine learning. Nat. Rev. Phys. 3, 422–440 (2021).10.1038/s42254-021-00314-5 ↗
22. Liu, Y. et al. Materials discovery and design using machine learning. J. Mater. 3, 159–177 (2017).
23. Libbrecht, M. W. & Noble, W. S. Machine learning applications in genetics and genomics. Nat. Rev. Genet. 16, 321–332 (2015).10.1038/nrg3920 ↗
24. Guo, K., Yang, Z., Yu, C. H. & Buehler, M. J. Artificial intelligence and machine learning in design of mechanical materials. Mater. Horiz. 8, 1153–1172 (2021).10.1039/D0MH01451F ↗
25. Xie, T. & Grossman, J. C. Crystal graph convolutional neural networks for an accurate and interpretable prediction of material properties. Phys. Rev. Lett. 120, 145301 (2018).10.1103/PhysRevLett.120.145301 ↗
26. Hsu, Y. C., Yu, C. H. & Buehler, M. J. Using deep learning to predict fracture patterns in crystalline solids. Matter 3, 197–211 (2020).10.1016/j.matt.2020.04.019 ↗
27. Rajak, P. et al. Autonomous reinforcement learning agent for stretchable kirigami design of 2D materials. npj Comput. Mater. 7, 102 (2021).10.1038/s41524-021-00572-y ↗
28. Hanakata, P. Z., Cubuk, E. D., Campbell, D. K. & Park, H. S. Accelerated search and design of stretchable graphene kirigami using machine learning. Phys. Rev. Lett. 121, 255304 (2018).10.1103/PhysRevLett.121.255304 ↗
29. Wan, J., Jiang, J.-W. & Park, H. S. Machine learning-based design of porous graphene with low thermal conductivity. Carbon 157, 262–269 (2020).10.1016/j.carbon.2019.10.037 ↗
30. Schütt, K. T., Arbabzadah, F., Chmiela, S., Müller, K. R. & Tkatchenko, A. Quantum-chemical insights from deep tensor neural networks. Nat. Commun. 8, 6–13 (2017).10.1038/ncomms13890 ↗
31. Schleder, G. R., Padilha, A. C. M., Acosta, C. M., Costa, M. & Fazzio, A. From DFT to machine learning: recent approaches to materials science–a review. J. Phys. Mater. 2, 032001 (2019).10.1088/2515-7639/ab084b ↗
32. Schütt, K. T. et al. SchNet: a continuous-filter convolutional neural network for modeling quantum interactions. Adv. Neural Inf. Process. Syst. 2017, 992–1002 (2017).
33. Wang, J. et al. Machine learning of coarse-grained molecular dynamics force fields. ACS Cent. Sci. 5, 755–767 (2019).10.1021/acscentsci.8b00913 ↗
34. Behler, J. & Parrinello, M. Generalized neural-network representation of high-dimensional potential-energy surfaces. Phys. Rev. Lett. 98, 1–4 (2007).10.1103/PhysRevLett.98.146401 ↗
35. Noé, F., Tkatchenko, A., Müller, K.-R. & Clementi, C. Machine learning for molecular simulation. Annu. Rev. Phys. Chem. 71, 361–390 (2020).10.1146/annurev-physchem-042018-052331 ↗
36. Gu, G. X., Chen, C.-T. & Buehler, M. J. De novo composite design based on machine learning algorithm. Extrem. Mech. Lett. 18, 19–28 (2018).10.1016/j.eml.2017.10.001 ↗
37. Yang, Z., Yu, C.-H., Guo, K. & Buehler, M. J. End-to-end deep learning method to predict complete strain and stress tensors for complex hierarchical composite microstructures. J. Mech. Phys. Solids 154, 104506 (2021).10.1016/j.jmps.2021.104506 ↗
38. Yang, Z., Yu, C.-H. & Buehler, M. J. Deep learning model to predict complex stress and strain fields in hierarchical composites. Sci. Adv. 7, eabd7416 (2021).10.1126/sciadv.abd7416 ↗
39. Zhou, J. et al. Graph neural networks: a review of methods and applications. AI Open 1, 57–81 (2020).10.1016/j.aiopen.2021.01.001 ↗
40. Corso, G., Cavalleri, L., Beaini, D., Liò, P. & Veličković, P. Principal Neighbourhood Aggregation for Graph Nets. In Advances in Neural Information Processing Systems (eds. Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M. F. & Lin, H.) 33, 13260–13271 (Curran Associates, Inc., 2020).
41. Shekhawat, A. & Ritchie, R. O. Toughness and strength of nanocrystalline graphene. Nat. Commun. 7, 1–8 (2016).10.1038/ncomms10546 ↗
42. Chen, M. Q. et al. Effects of grain size, temperature and strain rate on the mechanical properties of polycrystalline graphene – A molecular dynamics study. Carbon 85, 135–146 (2015).10.1016/j.carbon.2014.12.092 ↗
43. Hao, F., Fang, D. & Xu, Z. Mechanical and thermal transport properties of graphene with defects. Appl. Phys. Lett. 99, 2009–2012 (2011).10.1063/1.3615290 ↗
44. Jing, N. et al. Effect of defects on Young’s modulus of graphene sheets: a molecular dynamics simulation. RSC Adv. 2, 9124–9129 (2012).10.1039/c2ra21228e ↗
45. Mortazavi, B. & Ahzi, S. Thermal conductivity and tensile response of defective graphene: a molecular dynamics study. Carbon 63, 460–470 (2013).10.1016/j.carbon.2013.07.017 ↗
46. Yamakov, V., Wolf, D., Phillpot, S. R., Mukherjee, A. K. & Gleiter, H. Dislocation processes in the deformation of nanocrystalline aluminium by molecular-dynamics simulation. Nat. Mater. 1, 45–48 (2002).10.1038/nmat700 ↗
47. Alavi, S. & Thompson, D. L. Molecular dynamics simulations of the melting of aluminum nanoparticles. J. Phys. Chem. A 110, 1518–1523 (2006).10.1021/jp053318s ↗
48. Yang, G., Li, L., Lee, W. B. & Ng, M. C. Structure of graphene and its disorders: a review. Sci. Technol. Adv. Mater. 19, 613–648 (2018).10.1080/14686996.2018.1494493 ↗
49. Stukowski, A. Visualization and analysis of atomistic simulation data with OVITO-the open visualization tool. Model. Simul. Mater. Sci. Eng. 18, 15012 (2009).10.1088/0965-0393/18/1/015012 ↗
50. Larsen, P. M., Schmidt, S. Ø. & SchiØtz, J. Robust structural identification via polyhedral template matching. Model. Simul. Mater. Sci. Eng. 24, 55007 (2016).10.1088/0965-0393/24/5/055007 ↗
51. Hao, F., Fang, D. & Xu, Z. Mechanical and thermal transport properties of graphene with defects. Appl. Phys. Lett. 99, 41901 (2011).10.1063/1.3615290 ↗
52. Lee, C., Wei, X., Kysar, J. W. & Hone, J. Measurement of the elastic properties and intrinsic strength of monolayer graphene. Science 321, 385–388 (2008).10.1126/science.1157996 ↗
53. Davis, J. R. Aluminum and Aluminum Alloys (ASM International, 1993).
54. Noori, Z., Panjepour, M. & Ahmadian, M. Study of the effect of grain size on melting temperature of Al nanocrystals by molecular dynamics simulation. J. Mater. Res. 30, 1648–1660 (2015).10.1557/jmr.2015.109 ↗
55. Papanikolaou, M., Salonitis, K., Jolly, M. & Frank, M. Large-scale molecular dynamics simulations of homogeneous nucleation of pure aluminium. Metals 9, 1–17 (2019).10.3390/met9111217 ↗
56. Hirel, P. Atomsk: a tool for manipulating and converting atomic data files. Comput. Phys. Commun. 197, 212–219 (2015).10.1016/j.cpc.2015.07.012 ↗
57. Jiang, D. E., Cooper, V. R. & Dai, S. Porous graphene as the ultimate membrane for gas separation. Nano Lett. 9, 4019–4024 (2009).10.1021/nl9021946 ↗
58. Garaj, S. et al. Graphene as a subnanometre trans-electrode membrane. Nature 467, 190–193 (2010).10.1038/nature09379 ↗
59. Yu, C.-H., Qin, Z. & Buehler, M. J. Artificial intelligence design algorithm for nanocomposites optimized for shear crack resistance. Nano Futures 3, 035001 (2019).10.1088/2399-1984/ab36f0 ↗
60. Chawla, K. K. Composite Materials: Science and Engineering (Springer Science & Business Media, 2012).
61. Plimpton, S. Fast parallel algorithms for short-range molecular dynamics. J. Comput. Phys. 117, 1–19 (1995).10.1006/jcph.1995.1039 ↗
62. Brenner, D. W. et al. A second-generation reactive empirical bond order ({REBO}) potential energy expression for hydrocarbons. J. Phys. Condens. Matter 14, 783–802 (2002).10.1088/0953-8984/14/4/312 ↗
63. Stuart, S. J., Tutein, A. B. & Harrison, J. A. A reactive potential for hydrocarbons with intermolecular interactions. J. Chem. Phys. 112, 6472–6486 (2000).10.1063/1.481208 ↗
64. Mendelev, M. I., Kramer, M. J., Becker, C. A. & Asta, M. Analysis of semi-empirical interatomic potentials appropriate for simulation of crystalline and liquid Al and Cu. Philos. Mag. 88, 1723–1750 (2008).10.1080/14786430802206482 ↗
65. Paszke, A. et al. PyTorch: an imperative style, high-performance deep learning library. In Advances in Neural Information Processing Systems 32 (eds. Wallach, H. et al.) 8024–8035 (Curran Associates, Inc., 2019).
66. Fey, M. & Lenssen, J. E. Fast graph representation learning with PyTorch geometric. Preprint at https://arxiv.org/abs/1903.02428 (2019).
67. Kipf, T. N. & Welling, M. Semi-supervised classification with graph convolutional networks. Preprint at https://arxiv.org/abs/1609.02907 (2016).
68. Veličković, P. et al. Graph attention networks. Preprint at https://arxiv.org/abs/1710.10903 (2017).
69. Gilmer, J., Schoenholz, S. S., Riley, P. F., Vinyals, O. & Dahl, G. E. Neural message passing for quantum chemistry. In Proc. 34th International Conference on Machine Learning (eds. Precup, D. & Teh, Y. W.) 1263–1272 (PMLR, 2017).
70. Blank, J. & Deb, K. pymoo: multi-objective optimization in Python. IEEE Access 8, 89497–89509 (2020).10.1109/ACCESS.2020.2990567 ↗