Digital twins and deep learning segmentation of defects in monolayer MX2 phases

Fuhr, Addis S.; Ganesh, Panchapakesan; Vasudevan, Rama K.; Roccapriore, Kevin M.; Sumpter, Bobby G.

doi:10.1063/5.0181080

Digital twins and deep learning segmentation of defects in monolayer MX₂ phases

Journal Article · Wed Jan 17 00:00:00 EST 2024 · Applied Physics Letters

DOI:https://doi.org/10.1063/5.0181080· OSTI ID:2283874

^[1]; ^[1]; ^[1]; ^[1]; ^[1]

Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States). Center for Nanophase Materials Sciences (CNMS)

Developing methods to understand and control defect formation in nanomaterials offers a promising route for materials discovery. Monolayer MX₂ phases represent a particularly compelling case for defect engineering of nanomaterials due to the large variability in their physical properties as different defects are introduced into their structure. However, effective identification and quantification of defects remain a challenge even as high-throughput scanning transmission electron microscopy methods improve. This study highlights the benefits of employing first principles calculations to produce digital twins for training deep learning segmentation models for defect identification in monolayer MX₂ phases. Around 600 defect structures were obtained using density functional theory calculations, with each monolayer MX₂ structure being subjected to multislice simulations for the purpose of generating the digital twins. Several deep learning segmentation architectures were trained on this dataset, and their performances evaluated under a variety of conditions such as recognizing defects in the presence of unidentified impurities, beam damage, grain boundaries, and with reduced image quality from low electron doses. Further, this digital twin approach allows benchmarking different deep learning architectures on a theory dataset, which enables the study of defect classification under a broad array of finely controlled conditions. It thus opens the door to resolving the underpinning physical reasons for model shortcomings and potentially chart paths forward for automated discovery of materials defect phases in experiments.

View Accepted Manuscript (DOE)

Research Organization:: Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States). Center for Nanophase Materials Sciences (CNMS); Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States). Compute and Data Environment for Science (CADES)

Sponsoring Organization:: USDOE

Grant/Contract Number:: AC05-00OR22725

OSTI ID:: 2283874

Journal Information:: Applied Physics Letters, Journal Name: Applied Physics Letters Journal Issue: 3 Vol. 124; ISSN 0003-6951

Publisher:: American Institute of Physics (AIP)Copyright Statement

Country of Publication:: United States

Language:: English

References (69)

Electronically Nonadiabatic Structural Transformations Promoted by Electron Beams Lingerfelt, David B.; Ganesh, Panchapakesan; Jakowski, Jacek Advanced Functional Materials, Vol. 29, Issue 52 https://doi.org/10.1002/adfm.201901901	journal	June 2019
Chemically Exfoliated VSe ₂ Monolayers with Room‐Temperature Ferromagnetism Yu, Wei; Li, Jing; Herng, Tun Seng Advanced Materials, Vol. 31, Issue 40 https://doi.org/10.1002/adma.201903779	journal	August 2019
A Deep Learning Approach to Identify Local Structures in Atomic-Resolution Transmission Electron Microscopy Images Madsen, Jacob; Liu, Pei; Kling, Jens Advanced Theory and Simulations, Vol. 1, Issue 8 https://doi.org/10.1002/adts.201800037	journal	July 2018
Ferromagnetic Order at Room Temperature in Monolayer WSe ₂ Semiconductor via Vanadium Dopant Yun, Seok Joon; Duong, Dinh Loc; Ha, Doan Manh Advanced Science, Vol. 7, Issue 9 https://doi.org/10.1002/advs.201903076	journal	March 2020
Deep Learning‐Assisted Quantification of Atomic Dopants and Defects in 2D Materials Yang, Sang‐Hyeok; Choi, Wooseon; Cho, Byeong Wook Advanced Science, Vol. 8, Issue 16 https://doi.org/10.1002/advs.202101099	journal	June 2021
Direct Observation of Atomic Dynamics and Silicon Doping at a Topological Defect in Graphene Yang, Zhiqing; Yin, Lichang; Lee, Jaekwang Angewandte Chemie International Edition, Vol. 53, Issue 34 https://doi.org/10.1002/anie.201403382	journal	June 2014
Efficiency of ab-initio total energy calculations for metals and semiconductors using a plane-wave basis set Kresse, G.; Furthmüller, J. Computational Materials Science, Vol. 6, Issue 1, p. 15-50 https://doi.org/10.1016/0927-0256(96)00008-0	journal	July 1996
Optimal experimental design of STEM measurement of atom column positions Van Aert, S.; den Dekker, A. J.; Van Dyck, D. Ultramicroscopy, Vol. 90, Issue 4 https://doi.org/10.1016/S0304-3991(01)00152-8	journal	April 2002
Column-by-column compositional mapping by Z-contrast imaging Molina, S. I.; Sales, D. L.; Galindo, P. L. Ultramicroscopy, Vol. 109, Issue 2 https://doi.org/10.1016/j.ultramic.2008.10.008	journal	January 2009
Scanning distortion correction in STEM images Ning, Shoucong; Fujita, Takeshi; Nie, Anmin Ultramicroscopy, Vol. 184 https://doi.org/10.1016/j.ultramic.2017.09.003	journal	January 2018
High-Throughput Screening of Extrinsic Point Defect Properties in Si and Ge: Database and Applications Sluydts, Michael; Pieters, Michael; Vanhellemont, Jan Chemistry of Materials, Vol. 29, Issue 3 https://doi.org/10.1021/acs.chemmater.6b03368	journal	December 2016
Atomic Structure of Intrinsic and Electron-Irradiation-Induced Defects in MoTe ₂ Elibol, Kenan; Susi, Toma; Argentero, Giacomo Chemistry of Materials, Vol. 30, Issue 4 https://doi.org/10.1021/acs.chemmater.7b03760	journal	February 2018
Understanding Beam-Induced Electronic Excitations in Materials Lingerfelt, David B.; Ganesh, Panchapakesan; Jakowski, Jacek Journal of Chemical Theory and Computation, Vol. 16, Issue 2 https://doi.org/10.1021/acs.jctc.9b00792	journal	January 2020
Defect Genome of Cubic Perovskites for Fuel Cell Applications Balachandran, Janakiraman; Lin, Lianshan; Anchell, Jonathan S. The Journal of Physical Chemistry C, Vol. 121, Issue 48 https://doi.org/10.1021/acs.jpcc.7b08716	journal	November 2017
Deep Learning Enabled Strain Mapping of Single-Atom Defects in Two-Dimensional Transition Metal Dichalcogenides with Sub-Picometer Precision Lee, Chia-Hao; Khan, Abid; Luo, Di Nano Letters, Vol. 20, Issue 5 https://doi.org/10.1021/acs.nanolett.0c00269	journal	April 2020
Nonadiabatic Effects on Defect Diffusion in Silicon-Doped Nanographenes Lingerfelt, David B.; Yu, Tao; Yoshimura, Anthony Nano Letters, Vol. 21, Issue 1 https://doi.org/10.1021/acs.nanolett.0c03587	journal	December 2020
Atomic-Level Structural Engineering of Graphene on a Mesoscopic Scale Trentino, Alberto; Madsen, Jacob; Mittelberger, Andreas Nano Letters, Vol. 21, Issue 12 https://doi.org/10.1021/acs.nanolett.1c01214	journal	June 2021
STEM Image Analysis Based on Deep Learning: Identification of Vacancy Defects and Polymorphs of MoS₂ Lee, Kihyun; Park, Jinsub; Choi, Soyeon Nano Letters, Vol. 22, Issue 12 https://doi.org/10.1021/acs.nanolett.2c00550	journal	June 2022
Engineering the Structural and Electronic Phases of MoTe ₂ through W Substitution Rhodes, D.; Chenet, D. A.; Janicek, B. E. Nano Letters, Vol. 17, Issue 3 https://doi.org/10.1021/acs.nanolett.6b04814	journal	February 2017
Opto-Valleytronic Spin Injection in Monolayer MoS ₂ /Few-Layer Graphene Hybrid Spin Valves Luo, Yunqiu Kelly; Xu, Jinsong; Zhu, Tiancong Nano Letters, Vol. 17, Issue 6 https://doi.org/10.1021/acs.nanolett.7b01393	journal	May 2017
Electronic Structure and Enhanced Charge-Density Wave Order of Monolayer VSe ₂ Feng, Jiagui; Biswas, Deepnarayan; Rajan, Akhil Nano Letters, Vol. 18, Issue 7 https://doi.org/10.1021/acs.nanolett.8b01649	journal	June 2018
Atomic Observation of Filling Vacancies in Monolayer Transition Metal Sulfides by Chemically Sourced Sulfur Atoms Roy, Shrawan; Choi, Wooseon; Jeon, Sera Nano Letters, Vol. 18, Issue 7 https://doi.org/10.1021/acs.nanolett.8b01714	journal	June 2018
High-Energy Gain Upconversion in Monolayer Tungsten Disulfide Photodetectors Wang, Qixing; Zhang, Qi; Zhao, Xiaoxu Nano Letters, Vol. 19, Issue 8 https://doi.org/10.1021/acs.nanolett.9b02136	journal	June 2019
Hierarchically Structured Core–Shell Design of a Lithium Transition-Metal Oxide Cathode Material for Excellent Electrochemical Performance Shim, Jae-Hyun; Kim, Young-Hoon; Yoon, Han-Sol ACS Applied Materials & Interfaces, Vol. 11, Issue 4 https://doi.org/10.1021/acsami.8b19902	journal	January 2019
Electron-Beam-Driven Structure Evolution of Single-Layer MoTe ₂ for Quantum Devices Lehnert, Tibor; Ghorbani-Asl, Mahdi; Köster, Janis ACS Applied Nano Materials, Vol. 2, Issue 5 https://doi.org/10.1021/acsanm.9b00616	journal	April 2019
Performance Improvement by Ozone Treatment of 2D PdSe ₂ Liang, Qijie; Zhang, Qian; Gou, Jian ACS Nano, Vol. 14, Issue 5 https://doi.org/10.1021/acsnano.0c00180	journal	April 2020
Impact of S-Vacancies on the Charge Injection Barrier at the Electrical Contact with the MoS₂ Monolayer Bussolotti, Fabio; Yang, Jing; Kawai, Hiroyo ACS Nano, Vol. 15, Issue 2 https://doi.org/10.1021/acsnano.0c07982	journal	January 2021
Probing Electron Beam Induced Transformations on a Single-Defect Level via Automated Scanning Transmission Electron Microscopy Roccapriore, Kevin M.; Boebinger, Matthew G.; Dyck, Ondrej ACS Nano, Vol. 16, Issue 10 https://doi.org/10.1021/acsnano.2c07451	journal	October 2022
Deep Learning of Atomically Resolved Scanning Transmission Electron Microscopy Images: Chemical Identification and Tracking Local Transformations Ziatdinov, Maxim; Dyck, Ondrej; Maksov, Artem ACS Nano, Vol. 11, Issue 12 https://doi.org/10.1021/acsnano.7b07504	journal	October 2016
Electron-Driven In Situ Transmission Electron Microscopy of 2D Transition Metal Dichalcogenides and Their 2D Heterostructures Mendes, Rafael G.; Pang, Jinbo; Bachmatiuk, Alicja ACS Nano https://doi.org/10.1021/acsnano.8b08079	journal	January 2019
Atomic-scale imaging of individual dopant atoms and clusters in highly n-type bulk Si Voyles, P. M.; Muller, D. A.; Grazul, J. L. Nature, Vol. 416, Issue 6883 https://doi.org/10.1038/416826a	journal	April 2002
Valleytronics in 2D materials Schaibley, John R.; Yu, Hongyi; Clark, Genevieve Nature Reviews Materials, Vol. 1, Issue 11 https://doi.org/10.1038/natrevmats.2016.55	journal	August 2016
2D transition metal dichalcogenides Manzeli, Sajedeh; Ovchinnikov, Dmitry; Pasquier, Diego Nature Reviews Materials, Vol. 2, Issue 8 https://doi.org/10.1038/natrevmats.2017.33	journal	June 2017
Topological superconductivity in monolayer transition metal dichalcogenides Hsu, Yi-Ting; Vaezi, Abolhassan; Fischer, Mark H. Nature Communications, Vol. 8, Issue 1 https://doi.org/10.1038/ncomms14985	journal	April 2017
Imaging atomic-level random walk of a point defect in graphene Kotakoski, Jani; Mangler, Clemens; Meyer, Jannik C. Nature Communications, Vol. 5, Issue 1 https://doi.org/10.1038/ncomms4991	journal	May 2014
Picometre-precision analysis of scanning transmission electron microscopy images of platinum nanocatalysts Yankovich, Andrew B.; Berkels, Benjamin; Dahmen, W. Nature Communications, Vol. 5, Issue 1 https://doi.org/10.1038/ncomms5155	journal	June 2014
Imaging quantum materials Moler, Kathryn Ann Nature Materials, Vol. 16, Issue 11 https://doi.org/10.1038/nmat5018	journal	October 2017
How the doors to the nanoworld were opened Gerber, Christoph; Lang, Hans Peter Nature Nanotechnology, Vol. 1, Issue 1 https://doi.org/10.1038/nnano.2006.70	journal	October 2006
Enhanced performance of in-plane transition metal dichalcogenides monolayers by configuring local atomic structures Zhou, Yao; Zhang, Jing; Song, Erhong Nature Communications, Vol. 11, Issue 1 https://doi.org/10.1038/s41467-020-16111-0	journal	May 2020
Antisite defect qubits in monolayer transition metal dichalcogenides Tsai, Jeng-Yuan; Pan, Jinbo; Lin, Hsin Nature Communications, Vol. 13, Issue 1 https://doi.org/10.1038/s41467-022-28133-x	journal	January 2022
Automated defect analysis in electron microscopic images Li, Wei; Field, Kevin G.; Morgan, Dane npj Computational Materials, Vol. 4, Issue 1 https://doi.org/10.1038/s41524-018-0093-8	journal	July 2018
Deep learning analysis of defect and phase evolution during electron beam-induced transformations in WS2 Maksov, Artem; Dyck, Ondrej; Wang, Kai npj Computational Materials, Vol. 5, Issue 1 https://doi.org/10.1038/s41524-019-0152-9	journal	February 2019
Defect detection in atomic-resolution images via unsupervised learning with translational invariance Guo, Yueming; Kalinin, Sergei V.; Cai, Hui npj Computational Materials, Vol. 7, Issue 1 https://doi.org/10.1038/s41524-021-00642-1	journal	November 2021
Quantum point defects in 2D materials - the QPOD database Bertoldo, Fabian; Ali, Sajid; Manti, Simone npj Computational Materials, Vol. 8, Issue 1 https://doi.org/10.1038/s41524-022-00730-w	journal	April 2022
Bridging microscopy with molecular dynamics and quantum simulations: an atomAI based pipeline Ghosh, Ayana; Ziatdinov, Maxim; Dyck, Ondrej npj Computational Materials, Vol. 8, Issue 1 https://doi.org/10.1038/s41524-022-00733-7	journal	April 2022
Anisotropic band splitting in monolayer NbSe2: implications for superconductivity and charge density wave Nakata, Yuki; Sugawara, Katsuaki; Ichinokura, Satoru npj 2D Materials and Applications, Vol. 2, Issue 1 https://doi.org/10.1038/s41699-018-0057-3	journal	May 2018
Unveiling the complex structure-property correlation of defects in 2D materials based on high throughput datasets Huang, Pengru; Lukin, Ruslan; Faleev, Maxim npj 2D Materials and Applications, Vol. 7, Issue 1 https://doi.org/10.1038/s41699-023-00369-1	journal	February 2023
Atomic structure of defects and dopants in 2D layered transition metal dichalcogenides Wang, Shanshan; Robertson, Alex; Warner, Jamie H. Chemical Society Reviews, Vol. 47, Issue 17 https://doi.org/10.1039/C8CS00236C	journal	January 2018
Utilization of electron-beam irradiation under atomic-scale chemical mapping for evaluating the cycling performance of lithium transition metal oxide cathodes Shim, Jae-Hyun; Kang, Hyosik; Lee, Sanghun Journal of Materials Chemistry A, Vol. 9, Issue 4 https://doi.org/10.1039/D0TA10415A	journal	January 2021
The pristine atomic structure of MoS ₂ monolayer protected from electron radiation damage by graphene Algara-Siller, Gerardo; Kurasch, Simon; Sedighi, Mona Applied Physics Letters, Vol. 103, Issue 20 https://doi.org/10.1063/1.4830036	journal	November 2013
Atomic-level defect modulation and characterization methods in 2D materials Ngome Okello, Odongo Francis; Yang, Dong-Hwan; Chu, Yu-Seong APL Materials, Vol. 9, Issue 10 https://doi.org/10.1063/5.0062633	journal	October 2021
Defect engineering of two-dimensional transition metal dichalcogenides Lin, Zhong; Carvalho, Bruno R.; Kahn, Ethan 2D Materials, Vol. 3, Issue 2 https://doi.org/10.1088/2053-1583/3/2/022002	journal	April 2016
The Computational 2D Materials Database: high-throughput modeling and discovery of atomically thin crystals Haastrup, Sten; Strange, Mikkel; Pandey, Mohnish 2D Materials, Vol. 5, Issue 4 https://doi.org/10.1088/2053-1583/aacfc1	journal	September 2018
Recent progress of the Computational 2D Materials Database (C2DB) Gjerding, Morten Niklas; Taghizadeh, Alireza; Rasmussen, Asbjørn 2D Materials, Vol. 8, Issue 4 https://doi.org/10.1088/2053-1583/ac1059	journal	July 2021
AiiDA-defects: an automated and fully reproducible workflow for the complete characterization of defect chemistry in functional materials Muy, Sokseiha; Johnston, Conrad; Marzari, Nicola Electronic Structure, Vol. 5, Issue 2 https://doi.org/10.1088/2516-1075/ace014	journal	June 2023
Ab initiomolecular dynamics for liquid metals Kresse, G.; Hafner, J. Physical Review B, Vol. 47, Issue 1, p. 558-561 https://doi.org/10.1103/PhysRevB.47.558	journal	January 1993
Ab initio molecular-dynamics simulation of the liquid-metal–amorphous-semiconductor transition in germanium Kresse, G.; Hafner, J. Physical Review B, Vol. 49, Issue 20, p. 14251-14269 https://doi.org/10.1103/PhysRevB.49.14251	journal	May 1994
Efficient iterative schemes for ab initio total-energy calculations using a plane-wave basis set Kresse, G.; Furthmüller, J. Physical Review B, Vol. 54, Issue 16, p. 11169-11186 https://doi.org/10.1103/PhysRevB.54.11169	journal	October 1996
Stone-Wales-type transformations in carbon nanostructures driven by electron irradiation Kotakoski, J.; Meyer, J. C.; Kurasch, S. Physical Review B, Vol. 83, Issue 24 https://doi.org/10.1103/PhysRevB.83.245420	journal	June 2011
From point to extended defects in two-dimensional MoS 2 : Evolution of atomic structure under electron irradiation Komsa, Hannu-Pekka; Kurasch, Simon; Lehtinen, Ossi Physical Review B, Vol. 88, Issue 3 https://doi.org/10.1103/PhysRevB.88.035301	journal	July 2013
Understanding topological phase transition in monolayer transition metal dichalcogenides Choe, Duk-Hyun; Sung, Ha-Jun; Chang, K. J. Physical Review B, Vol. 93, Issue 12 https://doi.org/10.1103/PhysRevB.93.125109	journal	March 2016
Monolayer VTe 2 : Incommensurate Fermi surface nesting and suppression of charge density waves Sugawara, Katsuaki; Nakata, Yuki; Fujii, Kazuki Physical Review B, Vol. 99, Issue 24 https://doi.org/10.1103/PhysRevB.99.241404	journal	June 2019
Direct Observation of Dopant Atom Diffusion in a Bulk Semiconductor Crystal Enhanced by a Large Size Mismatch Ishikawa, Ryo; Mishra, Rohan; Lupini, Andrew R. Physical Review Letters, Vol. 113, Issue 15 https://doi.org/10.1103/PhysRevLett.113.155501	journal	October 2014
Generalized Gradient Approximation Made Simple Perdew, John P.; Burke, Kieron; Ernzerhof, Matthias Physical Review Letters, Vol. 77, Issue 18, p. 3865-3868 https://doi.org/10.1103/PhysRevLett.77.3865	journal	October 1996
Deep Residual Learning for Image Recognition He, Kaiming; Zhang, Xiangyu; Ren, Shaoqing 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) https://doi.org/10.1109/cvpr.2016.90	conference	June 2016
Magnetism in semiconducting molybdenum dichalcogenides Guguchia, Z.; Kerelsky, A.; Edelberg, D. Science Advances, Vol. 4, Issue 12 https://doi.org/10.1126/sciadv.aat3672	journal	December 2018
Building and exploring libraries of atomic defects in graphene: Scanning transmission electron and scanning tunneling microscopy study Ziatdinov, Maxim; Dyck, Ondrej; Li, Xin Science Advances, Vol. 5, Issue 9 https://doi.org/10.1126/sciadv.aaw8989	journal	September 2019
Exploring order parameters and dynamic processes in disordered systems via variational autoencoders Kalinin, Sergei V.; Dyck, Ondrej; Jesse, Stephen Science Advances, Vol. 7, Issue 17 https://doi.org/10.1126/sciadv.abd5084	journal	April 2021
The abTEM code: transmission electron microscopy from first principles Madsen, Jacob; Susi, Toma Open Research Europe, Vol. 1 https://doi.org/10.12688/openreseurope.13015.1	journal	January 2021

Similar Records

Defects in MX2 (DMX) 2.0: STEM Digital Twins

Dataset · Sun Nov 19 23:00:00 EST 2023 · OSTI ID:2203442

Defects in MX2 Phases (DMX) Dataset: STEM Digital Twins

Dataset · Sun Nov 19 23:00:00 EST 2023 · OSTI ID:1991531

Reinforcement Learning as a Parsimonious Alternative to Prediction Cascades: A Case Study on Image Segmentation

Conference · Thu Feb 29 23:00:00 EST 2024 · OSTI ID:2438975

Related Subjects

36 MATERIALS SCIENCE
Crystallographic defects
Deep learning
Density functional theory
Electron scattering
First-principle calculations
Nanomaterials
Phonons
Transmission electron microscopy

Digital twins and deep learning segmentation of defects in monolayer MX2 phases

Citation Formats

References (69)

Similar Records

Related Subjects

Digital twins and deep learning segmentation of defects in monolayer MX₂ phases