skip to main content
DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Active learning for accelerated design of layered materials

Abstract

Hetero-structures made from vertically stacked monolayers of transition metal dichalcogenides hold great potential for optoelectronic and thermoelectric devices. Discovery of the optimal layered material for specific applications necessitates the estimation of key material properties, such as electronic band structure and thermal transport coefficients. However, screening of material properties via brute force ab initio calculations of the entire material structure space exceeds the limits of current computing resources. Moreover, the functional dependence of material properties on the structures is often complicated, making simplistic statistical procedures for prediction difficult to employ without large amounts of data collection. Here, we present a Gaussian process regression model, which predicts material properties of an input hetero-structure, as well as an active learning model based on Bayesian optimization, which can efficiently discover the optimal hetero-structure using a minimal number of ab initio calculations. The electronic band gap, conduction/valence band dispersions, and thermoelectric performance are used as representative material properties for prediction and optimization. The Materials Project platform is used for electronic structure computation, while the BoltzTraP code is used to compute thermoelectric properties. Bayesian optimization is shown to significantly reduce the computational cost of discovering the optimal structure when compared with finding an optimal structure bymore » building a regression model to predict material properties. The models can be used for predictions with respect to any material property and our software, including data preparation code based on the Python Materials Genomics (PyMatGen) library as well as python-based machine learning code, is available open source.« less

Authors:
 [1]; ORCiD logo [2];  [3]; ORCiD logo [3];  [4];  [5]; ORCiD logo [5];  [6];  [6];  [6];  [3]
  1. Univ. of Southern California, Los Angeles, CA (United States). Collaboratory for Advanced Computing and Simulations, Dept. of Physics and Astronomy
  2. Univ. of Southern California, Los Angeles, CA (United States). Collaboratory for Advanced Computing and Simulations, and Dept. of Computer Science
  3. Univ. of Southern California, Los Angeles, CA (United States). Collaboratory for Advanced Computing and Simulations, Dept. of Physics and Astronomy, and Dept. of Chemical Engineering and Material Science, and Dept. of Computer Science
  4. Univ. of Southern California, Los Angeles, CA (United States). Dept. of Chemical Engineering and Material Science, and Dept. of Computer Science
  5. Univ. of Missouri, Columbia, MO (United States). Dept. of Physics and Astronomy
  6. Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)
Publication Date:
Research Org.:
Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)
Sponsoring Org.:
USDOE Office of Science (SC), Basic Energy Sciences (BES) (SC-22)
OSTI Identifier:
1494091
Grant/Contract Number:  
AC02-05CH11231
Resource Type:
Accepted Manuscript
Journal Name:
npj Computational Materials
Additional Journal Information:
Journal Volume: 4; Journal Issue: 1; Journal ID: ISSN 2057-3960
Publisher:
Nature Publishing Group
Country of Publication:
United States
Language:
English
Subject:
36 MATERIALS SCIENCE

Citation Formats

Bassman, Lindsay, Rajak, Pankaj, Kalia, Rajiv K., Nakano, Aiichiro, Sha, Fei, Sun, Jifeng, Singh, David J., Aykol, Muratahan, Huck, Patrick, Persson, Kristin, and Vashishta, Priya. Active learning for accelerated design of layered materials. United States: N. p., 2018. Web. doi:10.1038/s41524-018-0129-0.
Bassman, Lindsay, Rajak, Pankaj, Kalia, Rajiv K., Nakano, Aiichiro, Sha, Fei, Sun, Jifeng, Singh, David J., Aykol, Muratahan, Huck, Patrick, Persson, Kristin, & Vashishta, Priya. Active learning for accelerated design of layered materials. United States. doi:10.1038/s41524-018-0129-0.
Bassman, Lindsay, Rajak, Pankaj, Kalia, Rajiv K., Nakano, Aiichiro, Sha, Fei, Sun, Jifeng, Singh, David J., Aykol, Muratahan, Huck, Patrick, Persson, Kristin, and Vashishta, Priya. Mon . "Active learning for accelerated design of layered materials". United States. doi:10.1038/s41524-018-0129-0. https://www.osti.gov/servlets/purl/1494091.
@article{osti_1494091,
title = {Active learning for accelerated design of layered materials},
author = {Bassman, Lindsay and Rajak, Pankaj and Kalia, Rajiv K. and Nakano, Aiichiro and Sha, Fei and Sun, Jifeng and Singh, David J. and Aykol, Muratahan and Huck, Patrick and Persson, Kristin and Vashishta, Priya},
abstractNote = {Hetero-structures made from vertically stacked monolayers of transition metal dichalcogenides hold great potential for optoelectronic and thermoelectric devices. Discovery of the optimal layered material for specific applications necessitates the estimation of key material properties, such as electronic band structure and thermal transport coefficients. However, screening of material properties via brute force ab initio calculations of the entire material structure space exceeds the limits of current computing resources. Moreover, the functional dependence of material properties on the structures is often complicated, making simplistic statistical procedures for prediction difficult to employ without large amounts of data collection. Here, we present a Gaussian process regression model, which predicts material properties of an input hetero-structure, as well as an active learning model based on Bayesian optimization, which can efficiently discover the optimal hetero-structure using a minimal number of ab initio calculations. The electronic band gap, conduction/valence band dispersions, and thermoelectric performance are used as representative material properties for prediction and optimization. The Materials Project platform is used for electronic structure computation, while the BoltzTraP code is used to compute thermoelectric properties. Bayesian optimization is shown to significantly reduce the computational cost of discovering the optimal structure when compared with finding an optimal structure by building a regression model to predict material properties. The models can be used for predictions with respect to any material property and our software, including data preparation code based on the Python Materials Genomics (PyMatGen) library as well as python-based machine learning code, is available open source.},
doi = {10.1038/s41524-018-0129-0},
journal = {npj Computational Materials},
number = 1,
volume = 4,
place = {United States},
year = {2018},
month = {12}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record

Citation Metrics:
Cited by: 10 works
Citation information provided by
Web of Science

Figures / Tables:

Figure 1 Figure 1: Workflow for optimal structure and property prediction. First, structure files for a family of N-layered materials are created and uploaded to the Materials Project (MP) database. Second, the MP infrastructure performs all DFT calculations, and subsequently, transport calculations using BoltzTraP code are performed. A snapshot of the materialmore » property data computed by MP database is pictured, along with the thermoelectric parameters computed by BoltzTraP. Third, a numerical feature vector is assigned to uniquely represent each structure. Fourth, and finally, machine learning techniques are applied to the data to make predictions for either a material property or an optimal structure« less

Save / Share:

Works referenced in this record:

From Organized High-Throughput Data to Phenomenological Theory using Machine Learning: The Example of Dielectric Breakdown
journal, February 2016


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
  • DOI: 10.1103/PhysRevLett.77.3865

Effect of quantum-well structures on the thermoelectric figure of merit
journal, May 1993


Projector augmented-wave method
journal, December 1994


Efficiency of ab-initio total energy calculations for metals and semiconductors using a plane-wave basis set
journal, July 1996


The inorganic crystal structure data base
journal, May 1983

  • Bergerhoff, G.; Hundt, R.; Sievers, R.
  • Journal of Chemical Information and Modeling, Vol. 23, Issue 2
  • DOI: 10.1021/ci00038a003

Machine learning bandgaps of double perovskites
journal, January 2016

  • Pilania, G.; Mannodi-Kanakkithodi, A.; Uberuaga, B. P.
  • Scientific Reports, Vol. 6, Issue 1
  • DOI: 10.1038/srep19375

Accelerated materials property predictions and design using motif-based fingerprints
journal, July 2015

  • Huan, Tran Doan; Mannodi-Kanakkithodi, Arun; Ramprasad, Rampi
  • Physical Review B, Vol. 92, Issue 1
  • DOI: 10.1103/PhysRevB.92.014106

Strong interlayer coupling in van der Waals heterostructures built from single-layer chalcogenides
journal, April 2014

  • Fang, H.; Battaglia, C.; Carraro, C.
  • Proceedings of the National Academy of Sciences, Vol. 111, Issue 17
  • DOI: 10.1073/pnas.1405435111

Identifying Structural Flow Defects in Disordered Solids Using Machine-Learning Methods
journal, March 2015


Van der Waals heterostructures
journal, July 2013

  • Geim, A. K.; Grigorieva, I. V.
  • Nature, Vol. 499, Issue 7459, p. 419-425
  • DOI: 10.1038/nature12385

Taking the Human Out of the Loop: A Review of Bayesian Optimization
journal, January 2016


A New Method of Locating the Maximum Point of an Arbitrary Multipeak Curve in the Presence of Noise
journal, March 1964

  • Kushner, H. J.
  • Journal of Basic Engineering, Vol. 86, Issue 1
  • DOI: 10.1115/1.3653121

Electronics and optoelectronics of two-dimensional transition metal dichalcogenides
journal, November 2012

  • Wang, Qing Hua; Kalantar-Zadeh, Kourosh; Kis, Andras
  • Nature Nanotechnology, Vol. 7, Issue 11, p. 699-712
  • DOI: 10.1038/nnano.2012.193

Toward Effective Utilization of Methane: Machine Learning Prediction of Adsorption Energies on Metal Alloys
journal, March 2018

  • Toyao, Takashi; Suzuki, Keisuke; Kikuchi, Shoma
  • The Journal of Physical Chemistry C, Vol. 122, Issue 15
  • DOI: 10.1021/acs.jpcc.7b12670

Materials informatics: An emerging technology for materials development
journal, June 2009

  • LeSar, Richard
  • Statistical Analysis and Data Mining, Vol. 1, Issue 6
  • DOI: 10.1002/sam.10034

Recent advances in optoelectronic properties and applications of two-dimensional metal chalcogenides
journal, May 2016


Efficient iterative schemes for ab initio total-energy calculations using a plane-wave basis set
journal, October 1996


From ultrasoft pseudopotentials to the projector augmented-wave method
journal, January 1999


Multi-fidelity machine learning models for accurate bandgap predictions of solids
journal, March 2017


Modulating Optoelectronic Properties of Two-Dimensional Transition Metal Dichalcogenide Semiconductors by Photoinduced Charge Transfer
journal, December 2015


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
  • DOI: 10.1063/1.4812323

Inhomogeneous Electron Gas
journal, November 1964


Informatics-aided bandgap engineering for solar materials
journal, February 2014


Machine Learning Strategy for Accelerated Design of Polymer Dielectrics
journal, February 2016

  • Mannodi-Kanakkithodi, Arun; Pilania, Ghanshyam; Huan, Tran Doan
  • Scientific Reports, Vol. 6, Issue 1
  • DOI: 10.1038/srep20952

Physical and chemical tuning of two-dimensional transition metal dichalcogenides
journal, January 2015

  • Wang, Haotian; Yuan, Hongtao; Sae Hong, Seung
  • Chemical Society Reviews, Vol. 44, Issue 9
  • DOI: 10.1039/C4CS00287C

Representations in neural network based empirical potentials
journal, July 2017

  • Cubuk, Ekin D.; Malone, Brad D.; Onat, Berk
  • The Journal of Chemical Physics, Vol. 147, Issue 2
  • DOI: 10.1063/1.4990503

Ab initiomolecular dynamics for liquid metals
journal, January 1993


Recent development in 2D materials beyond graphene
journal, August 2015


Machine Learning Assisted Predictions of Intrinsic Dielectric Breakdown Strength of ABX 3 Perovskites
journal, June 2016

  • Kim, Chiho; Pilania, Ghanshyam; Ramprasad, Rampi
  • The Journal of Physical Chemistry C, Vol. 120, Issue 27
  • DOI: 10.1021/acs.jpcc.6b05068

Detailed Balance Limit of Efficiency of p‐n Junction Solar Cells
journal, March 1961

  • Shockley, William; Queisser, Hans J.
  • Journal of Applied Physics, Vol. 32, Issue 3, p. 510-519
  • DOI: 10.1063/1.1736034

BoltzTraP. A code for calculating band-structure dependent quantities
journal, July 2006


Photovoltaic Effect in an Electrically Tunable van der Waals Heterojunction
journal, July 2014

  • Furchi, Marco M.; Pospischil, Andreas; Libisch, Florian
  • Nano Letters, Vol. 14, Issue 8
  • DOI: 10.1021/nl501962c

The chemistry of two-dimensional layered transition metal dichalcogenide nanosheets
journal, April 2013

  • Chhowalla, Manish; Shin, Hyeon Suk; Eda, Goki
  • Nature Chemistry, Vol. 5, Issue 4, p. 263-275
  • DOI: 10.1038/nchem.1589

A general-purpose machine learning framework for predicting properties of inorganic materials
journal, August 2016


On the tuning of electrical and thermal transport in thermoelectrics: an integrated theory–experiment perspective
journal, February 2016


Artificial neural network prediction of the band gap and melting point of binary and ternary compound semiconductors
journal, June 1998


Atomically-thin layered films for device applications based upon 2D TMDC materials
journal, October 2016


Materials informatics
journal, October 2005


Electronic fitness function for screening semiconductors as thermoelectric materials
journal, November 2017


Python Materials Genomics (pymatgen): A robust, open-source python library for materials analysis
journal, February 2013


Self-Consistent Equations Including Exchange and Correlation Effects
journal, November 1965


    Figures/Tables have been extracted from DOE-funded journal article accepted manuscripts.