Harnessing graph convolutional neural networks for identification of glassy states in metallic glasses

Gurniak, Emily J.; Yuan, Suyue; Ren, Xuezhen; Branicio, Paulo S.

doi:10.1016/j.commatsci.2024.113257

Harnessing graph convolutional neural networks for identification of glassy states in metallic glasses

Journal Article · Mon Jul 29 04:00:00 EDT 2024 · Computational Materials Science

DOI:https://doi.org/10.1016/j.commatsci.2024.113257· OSTI ID:2406993

^[1]; ^[2]; Ren, Xuezhen ^[3]; ^[3]

University of Southern California, Los Angeles, CA (United States); University of Southern California
University of Southern California, Los Angeles, CA (United States); Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)
University of Southern California, Los Angeles, CA (United States)

Graph Convolutional Neural Networks (GCNNs) have emerged as powerful tools for analyzing materials. In this study, we employ GCNNs to examine structural characteristics of CuZr metallic glasses (MGs) and identify their states. We use molecular dynamics to simulate the quenching process of CuZr, using cooling rates ranging from 10⁹ to 10¹⁵ K/s, to produce six unique glassy states. For each state, we create a dataset comprising 1,800 distinct samples. We evaluate the effectiveness of various GCNNs, including Graph Attention Neural Network (GANN), Graph Sample and AggreGatE (GraphSAGE), Graph Isomorphism Network (GIN), and Relational Graph Convolutional Neural Network (RGCN). GANN and GraphSAGE demonstrate comparable performance, achieving an overall accuracy of 81% in classifying the MG states. Furthermore, these results underscore the potential of GCNNs to detect subtle structural variances in disordered materials and point to broader application of deep learning in the analysis of MGs and other amorphous substances.

View Accepted Manuscript (DOE)

Research Organization:: University of Southern California, Los Angeles, CA (United States)

Sponsoring Organization:: USDOE Office of Science (SC), Basic Energy Sciences (BES). Materials Sciences & Engineering Division (MSE); National Science Foundation (NSF)

Grant/Contract Number:: SC0020295; AC52-07NA27344

OSTI ID:: 2406993

Alternate ID(s):: OSTI ID: 2407145
OSTI ID: 2429365

Journal Information:: Computational Materials Science, Journal Name: Computational Materials Science Vol. 244; ISSN 0927-0256

Publisher:: ElsevierCopyright Statement

Country of Publication:: United States

Language:: English

References (42)

Processing of Bulk Metallic Glass Schroers, Jan Advanced Materials, Vol. 22, Issue 14 https://doi.org/10.1002/adma.200902776	journal	December 2009
The case for bulk metallic glass Telford, Mark Materials Today, Vol. 7, Issue 3 https://doi.org/10.1016/S1369-7021(04)00124-5	journal	March 2004
Bulk metallic glass formation in binary Cu-rich alloy series – Cu100−xZrx (x=34, 36, 38.2, 40 at.%) and mechanical properties of bulk Cu64Zr36 glass Xu, Donghua; Lohwongwatana, Boonrat; Duan, Gang Acta Materialia, Vol. 52, Issue 9 https://doi.org/10.1016/j.actamat.2004.02.009	journal	May 2004
Atomic structural evolution during glass formation of a Cu–Zr binary metallic glass Li, F.; Liu, X. J.; Lu, Z. P. Computational Materials Science, Vol. 85 https://doi.org/10.1016/j.commatsci.2013.12.058	journal	April 2014
Graph isomorphism network for materials property prediction along with explainability analysis Xiao, Jianping; Yang, Li; Wang, Shuqun Computational Materials Science, Vol. 233 https://doi.org/10.1016/j.commatsci.2023.112619	journal	January 2024
Predicting melting temperature of inorganic crystals via crystal graph neural network enhanced by transfer learning Kim, Jaesun; Jung, Jisu; Kim, Sookyung Computational Materials Science, Vol. 234 https://doi.org/10.1016/j.commatsci.2024.112783	journal	February 2024
LAMMPS - a flexible simulation tool for particle-based materials modeling at the atomic, meso, and continuum scales Thompson, Aidan P.; Aktulga, H. Metin; Berger, Richard Computer Physics Communications, Vol. 271 https://doi.org/10.1016/j.cpc.2021.108171	journal	February 2022
Gradient microstructure induced shear band constraint, delocalization, and delayed failure in CuZr nanoglasses Yuan, Suyue; Branicio, Paulo S. International Journal of Plasticity, Vol. 134 https://doi.org/10.1016/j.ijplas.2020.102845	journal	November 2020
Atomistic simulations of nanoindentation on nanoglasses: Effects of grain size and gradient microstructure on the mechanical properties Yuan, Suyue; Branicio, Paulo S. Intermetallics, Vol. 153 https://doi.org/10.1016/j.intermet.2022.107782	journal	February 2023
Improving Abusive Language Detection with online interaction network Song, Rui; Giunchiglia, Fausto; Shen, Qiang Information Processing & Management, Vol. 59, Issue 5 https://doi.org/10.1016/j.ipm.2022.103009	journal	September 2022
Uncovering metallic glasses hidden vacancy-like motifs using machine learning Yuan, Suyue; Liang, Aoyan; Liu, Chang Materials & Design, Vol. 233 https://doi.org/10.1016/j.matdes.2023.112185	journal	September 2023
Bulk metallic glasses Wang, W. H.; Dong, C.; Shek, C. H. Materials Science and Engineering: R: Reports, Vol. 44, Issue 2-3 https://doi.org/10.1016/j.mser.2004.03.001	journal	June 2004
Dynamic relaxations and relaxation-property relationships in metallic glasses Wang, Wei Hua Progress in Materials Science, Vol. 106 https://doi.org/10.1016/j.pmatsci.2019.03.006	journal	December 2019
Processing effects on fracture toughness of metallic glasses Chen, Wen; Zhou, Haofei; Liu, Ze Scripta Materialia, Vol. 130 https://doi.org/10.1016/j.scriptamat.2016.11.011	journal	March 2017
Tuning the mechanical properties of nanoglass-metallic glass composites with brick and mortar designs Yuan, Suyue; Branicio, Paulo S. Scripta Materialia, Vol. 194 https://doi.org/10.1016/j.scriptamat.2020.113639	journal	March 2021
Graph Networks as a Universal Machine Learning Framework for Molecules and Crystals Chen, Chi; Ye, Weike; Zuo, Yunxing Chemistry of Materials, Vol. 31, Issue 9 https://doi.org/10.1021/acs.chemmater.9b01294	journal	April 2019
Temperature-Dependent Properties of Molten Li₂BeF₄ Salt Using Ab Initio Molecular Dynamics Baral, Khagendra; San, Saro; Sakidja, Ridwan ACS Omega, Vol. 6, Issue 30 https://doi.org/10.1021/acsomega.1c02528	journal	July 2021
Thermomechanical processing of metallic glasses: extending the range of the glassy state Sun, Yonghao; Concustell, Amadeu; Greer, A. Lindsay Nature Reviews Materials, Vol. 1, Issue 9 https://doi.org/10.1038/natrevmats.2016.39	journal	June 2016
Formation of monatomic metallic glasses through ultrafast liquid quenching Zhong, Li; Wang, Jiangwei; Sheng, Hongwei Nature, Vol. 512, Issue 7513 https://doi.org/10.1038/nature13617	journal	August 2014
Rejuvenation engineering in metallic glasses by complementary stress and structure modulation Şopu, Daniel; Spieckermann, Florian; Bian, Xilei NPG Asia Materials, Vol. 15, Issue 1 https://doi.org/10.1038/s41427-023-00509-5	journal	November 2023
A transferable machine-learning framework linking interstice distribution and plastic heterogeneity in metallic glasses Wang, Qi; Jain, Anubhav Nature Communications, Vol. 10, Issue 1 https://doi.org/10.1038/s41467-019-13511-9	journal	December 2019
Inverse design of glass structure with deep graph neural networks Wang, Qi; Zhang, Longfei Nature Communications, Vol. 12, Issue 1 https://doi.org/10.1038/s41467-021-25490-x	journal	September 2021
Recent advances and applications of deep learning methods in materials science Choudhary, Kamal; DeCost, Brian; Chen, Chi npj Computational Materials, Vol. 8, Issue 1 https://doi.org/10.1038/s41524-022-00734-6	journal	April 2022
Linking atomic structural defects to mesoscale properties in crystalline solids using graph neural networks Yang, Zhenze; Buehler, Markus J. npj Computational Materials, Vol. 8, Issue 1 https://doi.org/10.1038/s41524-022-00879-4	journal	September 2022
CEGANN: Crystal Edge Graph Attention Neural Network for multiscale classification of materials environment Banik, Suvo; Dhabal, Debdas; Chan, Henry npj Computational Materials, Vol. 9, Issue 1 https://doi.org/10.1038/s41524-023-00975-z	journal	February 2023
Unveiling the predictive power of static structure in glassy systems Bapst, V.; Keck, T.; Grabska-Barwińska, A. Nature Physics, Vol. 16, Issue 4 https://doi.org/10.1038/s41567-020-0842-8	journal	April 2020
Excess free volume and structural properties of inert gas condensation synthesized nanoparticles based CuZr nanoglasses Zheng, Kaifeng; Yuan, Suyue; Hahn, Horst Scientific Reports, Vol. 11, Issue 1 https://doi.org/10.1038/s41598-021-98494-8	journal	September 2021
Drug discovery with explainable artificial intelligence Jiménez-Luna, José; Grisoni, Francesca; Schneider, Gisbert Nature Machine Intelligence, Vol. 2, Issue 10 https://doi.org/10.1038/s42256-020-00236-4	journal	October 2020
Graph neural networks for materials science and chemistry Reiser, Patrick; Neubert, Marlen; Eberhard, André Communications Materials, Vol. 3, Issue 1 https://doi.org/10.1038/s43246-022-00315-6	journal	November 2022
Deep learning for automated classification and characterization of amorphous materials Swanson, Kirk; Trivedi, Shubhendu; Lequieu, Joshua Soft Matter, Vol. 16, Issue 2 https://doi.org/10.1039/C9SM01903K	journal	January 2020
Composition and grain size effects on the structural and mechanical properties of CuZr nanoglasses Adibi, Sara; Branicio, Paulo S.; Zhang, Yong-Wei Journal of Applied Physics, Vol. 116, Issue 4 https://doi.org/10.1063/1.4891450	journal	July 2014
Development of a semi-empirical potential suitable for molecular dynamics simulation of vitrification in Cu-Zr alloys Mendelev, M. I.; Sun, Y.; Zhang, F. The Journal of Chemical Physics, Vol. 151, Issue 21 https://doi.org/10.1063/1.5131500	journal	December 2019
Annealing metallic glasses above Tg in order to accelerate the relaxation process in molecular dynamics simulations Şopu, D.; Yuan, X.; Eckert, J. Applied Physics Letters, Vol. 120, Issue 1 https://doi.org/10.1063/5.0073204	journal	January 2022
Atomic structure insight into crystallization of undercooled liquid metal Zr during isothermal relaxation processes Wen, Dadong; Deng, Yonghe; Dai, Xiongying Philosophical Magazine, Vol. 99, Issue 23 https://doi.org/10.1080/14786435.2019.1644464	journal	July 2019
Visualization and analysis of atomistic simulation data with OVITO–the Open Visualization Tool Stukowski, Alexander Modelling and Simulation in Materials Science and Engineering, Vol. 18, Issue 1 https://doi.org/10.1088/0965-0393/18/1/015012	journal	December 2009
Relaxation processes and physical aging in metallic glasses Ruta, B.; Pineda, E.; Evenson, Z. Journal of Physics: Condensed Matter, Vol. 29, Issue 50 https://doi.org/10.1088/1361-648X/aa9964	journal	November 2017
Topology of SiO_x-units and glassy network of magnesium silicate glass under densification: correlation between radial distribution function and bond angle distribution Son, Nguyen Hung; Anh, Nguyen Hoang; Kien, Pham Huu Modelling and Simulation in Materials Science and Engineering, Vol. 28, Issue 6 https://doi.org/10.1088/1361-651X/ab9bb4	journal	July 2020
Relational graph convolutional networks for predicting blood–brain barrier penetration of drug molecules Ding, Yan; Jiang, Xiaoqian; Kim, Yejin Bioinformatics, Vol. 38, Issue 10 https://doi.org/10.1093/bioinformatics/btac211	journal	April 2022
Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties Xie, Tian; Grossman, Jeffrey C. Physical Review Letters, Vol. 120, Issue 14 https://doi.org/10.1103/PhysRevLett.120.145301	journal	April 2018
Graph convolutional networks: a comprehensive review Zhang, Si; Tong, Hanghang; Xu, Jiejun Computational Social Networks, Vol. 6, Issue 1 https://doi.org/10.1186/s40649-019-0069-y	journal	November 2019
From patterning heterogeneity to nanoglass: A new approach to harden and toughen metallic glasses Wang, Yongwei; Gleiter, Herbert; Li, Mo MRS Bulletin, Vol. 48, Issue 1 https://doi.org/10.1557/s43577-022-00347-w	journal	September 2022
Investigating Transfer Learning in Graph Neural Networks Kooverjee, Nishai; James, Steven; van Zyl, Terence Electronics, Vol. 11, Issue 8 https://doi.org/10.3390/electronics11081202	journal	April 2022

Similar Records

GRAPH CONVOLUTIONAL NEURAL NETWORK (GCNN)FOR POLYMER PROPERTY PREDICTION

Software · Mon Mar 13 20:00:00 EDT 2023 · OSTI ID:code-102626

Fast and Accurate Predictions of Total Energy for Solid Solution Alloys with Graph Convolutional Neural Networks

Conference · Mon Feb 28 23:00:00 EST 2022 · OSTI ID:1855626

Related Subjects

36 MATERIALS SCIENCE
Graph attention neural networks
Graph convolutional neural networks
Graph isomorphism networks
GraphSAGE
Machine learning
Metallic glass
Molecular dynamics

Harnessing graph convolutional neural networks for identification of glassy states in metallic glasses

Citation Formats

References (42)

Similar Records

Related Subjects