Skip to content
6CCVD Research

Screening outstanding mechanical properties and low lattice thermal conductivity using global attention graph neural network

At a Glance

Section titled “At a Glance”
MetadataDetails
Publication Date2023-06-26
JournalEnergy and AI
AuthorsJoshua Ojih, Alejandro Rodriguez, Jianjun Hu, Ming Hu
InstitutionsUniversity of South Carolina
Citations19

Abstract

Section titled “Abstract”

Mechanical and thermal properties of materials are extremely important for various engineering and scientific fields such as energy conversion and energy storage. However, the characterization of these properties via high throughput screening at the quantum level, although highly accurate, is inefficient and very time- and resource-consuming. In contrast, prediction at the classical level is highly efficient but less accurate. We deploy scalable global attention graph neural network for accurate prediction of mechanical properties which bridge the gap between the accuracy at the quantum level and efficiency at the classical level. Using 10,158 elastic constants as training data, we trained the models on 5 mechanical properties, namely bulk modulus, shear modulus, Young’s modulus, Poisson’s ratio, and hardness. With the trained model, we predicted 775,947 data in search of materials with ultrahigh hardness. We further verify the recommended ultrahigh hardness materials by high precision first principles calculations, and we finally identify 20 structures with extreme hardness close to diamond, the hardest material in nature. Among those, two super hard materials are completely new and have not been reported in literature so far. We further recommend potential materials from bulk modulus prediction to search low lattice thermal conductivity, and we verify the thermal conductivity of 338 structures with first principles. Our results demonstrate that one can find materials with extreme mechanical properties recommended by graph neural network and low thermal conductivity material from bulk modulus prediction with minimal first principles calculations of the structures (only 0.04%) in the large-scale materials pool.

Tech Support

Section titled “Tech Support”

Original Source

Section titled “Original Source”

References

Section titled “References”
  1. 2021 - Machine learning for material characterization with an application for predicting mechanical properties [Crossref]
  2. 2015 - Charting the complete elastic properties of inorganic crystalline compounds [Crossref]
  3. 2012 - Extra-electron induced covalent strengthening and generalization of intrinsic ductile-to-brittle criterion [Crossref]
  4. 2020 - Thermal conductivity enhancement on phase change materials for thermal energy storage: a review [Crossref]
  5. 2011 - Thermal impacts on the performance of nanoscale-gap thermophotovoltaic power generators [Crossref]
  6. 2018 - Thermal transport crossover from crystalline to partial-crystalline partial-liquid state
  7. 2019 - First-principles study of electronic, optical and thermal transport properties of group III-VI monolayer MX (M = Ga, In; X = S, Se)
  8. 2017 - Low thermal conductivity of monolayer ZnO and its anomalous temperature dependence [Crossref]
  9. 2020 - Thermal transport properties of GaN with biaxial strain and electron-phonon coupling [Crossref]
  10. 2018 - Accelerating evaluation of converged lattice thermal conductivity [Crossref]

Reads Similar to This

Local density of electromagnetic states in plasmonic nanotapers - spatial resolution limits with nitrogen-vacancy centers in diamond nanospheres Thermal transport in a silicon/diamond micro-flake with quantum dots inserts Formation of perfectly aligned high-density NV centers in (111) CVD-grown diamonds for magnetic field imaging of magnetic particles