journal article·2023-06Open access

Predicting mechanical properties of newly generated two-dimensional materials with minimum uncertainty

Inhyo Lee, Joonchul Kim, Taehyun Park, Kyoungmin Min

Abstract

Two-dimensional (2D) materials exhibit exceptional properties. Thus, many studies have been conducted to discover novel 2D materials with unique characteristics or to find new ways of utilizing existing 2D materials. However, the existing open databases of 2D materials are often inefficient for this purpose. In this study, a material discovery framework is developed to identify new 2D materials using a deep learning-based generative model. First, a previous 2D database is adopted as a training set to develop a machine learning-based surrogate model for predicting the mechanical properties. Next, 2D candidates are generated, and their structural validity is confirmed by employing a classification model and checking their similarities to existing 2D materials. The uncertainty in the predicted mechanical properties of the generated materials is measured and the actual values are verified using density functional theory calculations. A total of 360 structures are newly identified according to the exploration method and the mean absolute error is significantly reduced from 206.025 to 10.185 N/m. We believe that the developed framework is general and can be further modified to search for novel 2D materials satisfying target physicochemical properties.
Source: openalex_inverted_index · Quality: baseline

Research context

OpenAlex topics: Machine Learning in Materials Science · 2D Materials and Applications · Graphene research and applications

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

References (59)

Show source-provided references
1. Measurement of the elastic properties and intrinsic strength of monolayer graphene10.1126/science.1157996 ↗
2. Superior thermal conductivity of single-layer graphene10.1021/nl0731872 ↗
3. Graphene photonics, plasmonics, and broadband optoelectronic devices10.1021/nn300989g ↗
4. Synthesis of graphene aerogel with high electrical conductivity10.1021/ja1072299 ↗
5. Production of graphene layer by liquid-phase exfoliation with low sonication power and sonication time from synthesized expanded graphite10.1080/1536383X.2015.1114472 ↗
6. Two dimensional hexagonal boron nitride (2D-HBN): synthesis, properties and applications10.1039/C7TC04300G ↗
7. Graphene and its elemental analogue: a molecular dynamics view of fracture phenomenon10.1016/j.physb.2017.04.009 ↗
8. A comprehensive review on recent advances in two-dimensional (2D) hexagonal boron nitride10.1021/acsaelm.1c00720 ↗
9. 2D hexagonal boron nitride (2D-HBN) explored for the electrochemical sensing of dopamine10.1021/acs.analchem.6b02638 ↗
10. 2D hexagonal boron nitride (2D-HBN) explored as a potential electrocatalyst for the oxygen reduction reaction10.1002/elan.201600462 ↗
11. Sub-picosecond photo-induced displacive phase transition in two-dimensional MoTe210.1038/s41699-020-0147-x ↗
12. 2D materials for large-area flexible thermoelectric devices10.1002/aenm.201902842 ↗
13. Transfer of large-scale two-dimensional semiconductors: challenges and developments10.1088/2053-1583/abf234 ↗
14. Van der Waals epitaxy of III-nitride semiconductors based on 2D materials for flexible applications10.1002/adma.201903407 ↗
15. The role of graphene and other 2D materials in solar photovoltaics
16. Two-dimensional materials to address the lithium battery challenges10.1021/acsnano.9b08396 ↗
17. The high-throughput highway to computational materials design10.1038/nmat3568 ↗
18. Machine learning-driven new material discovery10.1039/D0NA00388C ↗
19. High-throughput discovery and investigation of auxetic two-dimensional crystals10.1021/acs.chemmater.1c04229 ↗
20. Designing two-dimensional halide perovskites based on high-throughput calculations and machine learning
21. Efficient prediction of structural and electronic properties of hybrid 2D materials using complementary DFT and machine learning approaches10.1002/adts.201800128 ↗
22. Lyngby
23. 2DMatPedia, an open computational database of two-dimensional materials from top-down and bottom-up approaches10.1038/s41597-019-0097-3 ↗
24. The joint automated repository for various integrated simulations (JARVIS) for data-driven materials design10.1038/s41524-020-00440-1 ↗
25. Two-dimensional materials from high-throughput computational exfoliation of experimentally known compounds10.1038/s41565-017-0035-5 ↗
26. An artificial intelligence-aided virtual screening recipe for two-dimensional materials discovery10.1038/s41524-020-00375-7 ↗
27. Generative adversarial networks (GAN) based efficient sampling of chemical composition space for inverse design of inorganic materials10.1038/s41524-020-00352-0 ↗
28. Generative adversarial network: an overview
29. Materials design and discovery with high-throughput density functional theory: the open Quantum materials database (OQMD)10.1007/s11837-013-0755-4 ↗
30. The inorganic crystal structure database (ICSD) - present and future10.1080/08893110410001664882 ↗
31. Commentary: the materials Project: a materials genome approach to accelerating materials innovation10.1063/1.4812323 ↗
32. Machine learning based prediction of noncentrosymmetric crystal materials
33. Computational discovery of new 2D materials using deep learning generative models10.1021/acsami.1c01044 ↗
34. Active-learning-based generative design for the discovery of wide-band-gap materials10.1021/acs.jpcc.1c02438 ↗
35. A general-purpose machine learning framework for predicting properties of inorganic materials
36. Including crystal structure attributes in machine learning models of formation energies via voronoi tessellations10.1103/PhysRevB.96.024104 ↗
37. Maximizing the energy density and stability of Ni-rich layered cathode materials with multivalent dopants via machine learning
38. Accelerated discovery of novel garnet-type solid-state electrolyte candidates via machine learning
39. Kang · 2022 · 1
40. Random forest in remote sensing: a review of applications and future directions10.1016/j.isprsjprs.2016.01.011 ↗
41. CRYSPNet: crystal structure predictions via neural networks
42. The earth mover's distance as a metric for the space of inorganic compositions10.1021/acs.chemmater.0c03381 ↗
43. Definition of a scoring parameter to identify low-dimensional materials components
44. Recent progress of the computational 2D materials database (C2DB)10.1088/2053-1583/ac1059 ↗
45. Low-code AutoML-augmented data pipeline – a review and experiments
46. Benchmarking graph neural networks for materials chemistry10.1038/s41524-021-00554-0 ↗
47. Crystal graph convolutional neural networks for an accurate and interpretable prediction of material properties10.1103/PhysRevLett.120.145301 ↗
48. Graph networks as a universal machine learning framework for molecules and crystals10.1021/acs.chemmater.9b01294 ↗
49. Neural message passing for Quantum chemistry
50. SchNet - a deep learning architecture for molecules and materials
51. Searching for mechanically superior solid-state electrolytes in Li-ion batteries via data-driven approaches10.1021/acsami.1c07999 ↗
52. A predictive machine learning approach for microstructure optimization and materials design
53. Deep learning framework for material design space exploration using active transfer learning and data augmentation10.1038/s41524-021-00609-2 ↗
54. Efficiency of ab-initio total energy calculations for metals and semiconductors using a plane-wave basis set10.1016/0927-0256(96)00008-0 ↗
55. Efficient iterative schemes for ab-initio total energy calculations using a plane-wave basis set10.1103/PhysRevB.54.11169 ↗
56. Generalized gradient approximation made simple10.1103/PhysRevLett.77.3865 ↗
57. High-precision sampling for brillouin-zone integration in metals10.1103/PhysRevB.40.3616 ↗
58. The inhibition of epidermal growth factor receptor signaling by hexagonal selenium nanoparticles modified by SiRNA10.1038/cgt.2016.38 ↗
59. Efficient creation and convergence of surface slabs10.1016/j.susc.2013.05.016 ↗