Machine learning for deep elastic strain engineering of semiconductor electronic band structure and effective mass
Abstract
Abstract The controlled introduction of elastic strains is an appealing strategy for modulating the physical properties of semiconductor materials. With the recent discovery of large elastic deformation in nanoscale specimens as diverse as silicon and diamond, employing this strategy to improve device performance necessitates first-principles computations of the fundamental electronic band structure and target figures-of-merit, through the design of an optimal straining pathway. Such simulations, however, call for approaches that combine deep learning algorithms and physics of deformation with band structure calculations to custom-design electronic and optical properties. Motivated by this challenge, we present here details of a machine learning framework involving convolutional neural networks to represent the topology and curvature of band structures in k -space. These calculations enable us to identify ways in which the physical properties can be altered through “deep” elastic strain engineering up to a large fraction of the ideal strain. Algorithms capable of active learning and informed by the underlying physics were presented here for predicting the bandgap and the band structure. By training a surrogate model with ab initio computational data, our method can identify the most efficient strain energy pathway to realize physical property changes. The power of this method is furthermore »
- Authors:
- Publication Date:
- Sponsoring Org.:
- USDOE
- OSTI Identifier:
- 1785138
- Resource Type:
- Published Article
- Journal Name:
- npj Computational Materials
- Additional Journal Information:
- Journal Name: npj Computational Materials Journal Volume: 7 Journal Issue: 1; Journal ID: ISSN 2057-3960
- Publisher:
- Nature Publishing Group
- Country of Publication:
- United Kingdom
- Language:
- English
Citation Formats
Tsymbalov, Evgenii, Shi, Zhe, Dao, Ming, Suresh, Subra, Li, Ju, and Shapeev, Alexander. Machine learning for deep elastic strain engineering of semiconductor electronic band structure and effective mass. United Kingdom: N. p., 2021.
Web. doi:10.1038/s41524-021-00538-0.
Tsymbalov, Evgenii, Shi, Zhe, Dao, Ming, Suresh, Subra, Li, Ju, & Shapeev, Alexander. Machine learning for deep elastic strain engineering of semiconductor electronic band structure and effective mass. United Kingdom. https://doi.org/10.1038/s41524-021-00538-0
Tsymbalov, Evgenii, Shi, Zhe, Dao, Ming, Suresh, Subra, Li, Ju, and Shapeev, Alexander. Fri .
"Machine learning for deep elastic strain engineering of semiconductor electronic band structure and effective mass". United Kingdom. https://doi.org/10.1038/s41524-021-00538-0.
@article{osti_1785138,
title = {Machine learning for deep elastic strain engineering of semiconductor electronic band structure and effective mass},
author = {Tsymbalov, Evgenii and Shi, Zhe and Dao, Ming and Suresh, Subra and Li, Ju and Shapeev, Alexander},
abstractNote = {Abstract The controlled introduction of elastic strains is an appealing strategy for modulating the physical properties of semiconductor materials. With the recent discovery of large elastic deformation in nanoscale specimens as diverse as silicon and diamond, employing this strategy to improve device performance necessitates first-principles computations of the fundamental electronic band structure and target figures-of-merit, through the design of an optimal straining pathway. Such simulations, however, call for approaches that combine deep learning algorithms and physics of deformation with band structure calculations to custom-design electronic and optical properties. Motivated by this challenge, we present here details of a machine learning framework involving convolutional neural networks to represent the topology and curvature of band structures in k -space. These calculations enable us to identify ways in which the physical properties can be altered through “deep” elastic strain engineering up to a large fraction of the ideal strain. Algorithms capable of active learning and informed by the underlying physics were presented here for predicting the bandgap and the band structure. By training a surrogate model with ab initio computational data, our method can identify the most efficient strain energy pathway to realize physical property changes. The power of this method is further demonstrated with results from the prediction of strain states that influence the effective electron mass. We illustrate the applications of the method with specific results for diamonds, although the general deep learning technique presented here is potentially useful for optimizing the physical properties of a wide variety of semiconductor materials.},
doi = {10.1038/s41524-021-00538-0},
journal = {npj Computational Materials},
number = 1,
volume = 7,
place = {United Kingdom},
year = {Fri May 28 00:00:00 EDT 2021},
month = {Fri May 28 00:00:00 EDT 2021}
}
https://doi.org/10.1038/s41524-021-00538-0
Works referenced in this record:
Semiconductor strained layers
journal, December 1997
- Jain, Suresh C.; Maes, Herman E.; Van Overstraeten, Roger
- Current Opinion in Solid State and Materials Science, Vol. 2, Issue 6
Double-slit photoelectron interference in strong-field ionization of the neon dimer
journal, January 2019
- Kunitski, Maksim; Eicke, Nicolas; Huber, Pia
- Nature Communications, Vol. 10, Issue 1
Generalized Gradient Approximation Made Simple
journal, October 1996
- Perdew, John P.; Burke, Kieron; Ernzerhof, Matthias
- Physical Review Letters, Vol. 77, Issue 18, p. 3865-3868
Active Learning with Statistical Models
journal, January 1996
- Cohn, D. A.; Ghahramani, Z.; Jordan, M. I.
- Journal of Artificial Intelligence Research, Vol. 4
Effective masses and electronic structure of diamond including electron correlation effects in first principles calculations using the GW-approximation
journal, September 2011
- Löfås, Henrik; Grigoriev, Anton; Isberg, Jan
- AIP Advances, Vol. 1, Issue 3
Electronic Structure of Some Wurtzite Semiconductors: Hybrid Functionals vs. Ab Initio Many Body Calculations
journal, May 2012
- Kaczkowski, J.
- Acta Physica Polonica A, Vol. 121, Issue 5-6
Strain scaling for CMOS
journal, February 2014
- Bedell, S. W.; Khakifirooz, A.; Sadana, D. K.
- MRS Bulletin, Vol. 39, Issue 2
Projector augmented-wave method
journal, December 1994
- Blöchl, P. E.
- Physical Review B, Vol. 50, Issue 24, p. 17953-17979
Plastic Deformation of Single‐Crystal Diamond Nanopillars
journal, January 2020
- Regan, Blake; Aghajamali, Alireza; Froech, Johannes
- Advanced Materials, Vol. 32, Issue 9
Deeper Connections between Neural Networks and Gaussian Processes Speed-up Active Learning
conference, August 2019
- Tsymbalov, Evgenii; Makarychev, Sergei; Shapeev, Alexander
- Twenty-Eighth International Joint Conference on Artificial Intelligence {IJCAI-19}, Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence
Electron effective masses and lattice scattering in natural diamond
journal, January 1980
- Nava, F.; Canali, C.; Jacoboni, C.
- Solid State Communications, Vol. 33, Issue 4
Efficiency of ab-initio total energy calculations for metals and semiconductors using a plane-wave basis set
journal, July 1996
- Kresse, G.; Furthmüller, J.
- Computational Materials Science, Vol. 6, Issue 1, p. 15-50
Non-linear behavior of flexoelectricity
journal, December 2019
- Wang, Zhiguo; Song, Ruobing; Shen, Zhenjiang
- Applied Physics Letters, Vol. 115, Issue 25
Mechanical Writing of Ferroelectric Polarization
journal, April 2012
- Lu, H.; Bark, C. -W.; Esque de los Ojos, D.
- Science, Vol. 336, Issue 6077
Deep elastic strain engineering of bandgap through machine learning
journal, February 2019
- Shi, Zhe; Tsymbalov, Evgenii; Dao, Ming
- Proceedings of the National Academy of Sciences, Vol. 116, Issue 10
Elastic strain engineering for unprecedented materials properties
journal, February 2014
- Li, Ju; Shan, Zhiwei; Ma, Evan
- MRS Bulletin, Vol. 39, Issue 2
Special points for Brillouin-zone integrations
journal, June 1976
- Monkhorst, Hendrik J.; Pack, James D.
- Physical Review B, Vol. 13, Issue 12, p. 5188-5192
Ultralarge elastic deformation of nanoscale diamond
journal, April 2018
- Banerjee, Amit; Bernoulli, Daniel; Zhang, Hongti
- Science, Vol. 360, Issue 6386
Physics of strain effects in semiconductors and metal-oxide-semiconductor field-effect transistors
journal, May 2007
- Sun, Y.; Thompson, S. E.; Nishida, T.
- Journal of Applied Physics, Vol. 101, Issue 10
First principles phonon calculations in materials science
journal, November 2015
- Togo, Atsushi; Tanaka, Isao
- Scripta Materialia, Vol. 108
The GW method
journal, March 1998
- Aryasetiawan, F.; Gunnarsson, O.
- Reports on Progress in Physics, Vol. 61, Issue 3
Deformation Potentials and Mobilities in Non-Polar Crystals
journal, October 1950
- Bardeen, J.; Shockley, W.
- Physical Review, Vol. 80, Issue 1
Multi-column deep neural networks for image classification
conference, June 2012
- Ciresan, D.; Meier, U.; Schmidhuber, J.
- 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Commentary: The Materials Project: A materials genome approach to accelerating materials innovation
journal, July 2013
- Jain, Anubhav; Ong, Shyue Ping; Hautier, Geoffroy
- APL Materials, Vol. 1, Issue 1
Electron correlation in semiconductors and insulators: Band gaps and quasiparticle energies
journal, October 1986
- Hybertsen, Mark S.; Louie, Steven G.
- Physical Review B, Vol. 34, Issue 8, p. 5390-5413
Achieving large uniform tensile elasticity in microfabricated diamond
journal, December 2020
- Dang, Chaoqun; Chou, Jyh-Pin; Dai, Bing
- Science, Vol. 371, Issue 6524
DeepInsight: A methodology to transform a non-image data to an image for convolution neural network architecture
journal, August 2019
- Sharma, Alok; Vans, Edwin; Shigemizu, Daichi
- Scientific Reports, Vol. 9, Issue 1
Metallization of diamond
journal, October 2020
- Shi, Zhe; Dao, Ming; Tsymbalov, Evgenii
- Proceedings of the National Academy of Sciences, Vol. 117, Issue 40
Linear muffin-tin-orbital and k ⋅ p calculations of effective masses and band structure of semiconducting diamond
journal, December 1994
- Willatzen, M.; Cardona, M.; Christensen, N. E.
- Physical Review B, Vol. 50, Issue 24
Active Learning and Uncertainty Estimation
book, June 2020
- Shapeev, Alexander; Gubaev, Konstantin; Tsymbalov, Evgenii
- Machine Learning Meets Quantum Physics, p. 309-329
Approaching the ideal elastic strain limit in silicon nanowires
journal, August 2016
- Zhang, Hongti; Tersoff, Jerry; Xu, Shang
- Science Advances, Vol. 2, Issue 8