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

Title: Optimisation of GaN LEDs and the reduction of efficiency droop using active machine learning

Abstract

A fundamental challenge in the design of LEDs is to maximise electro-luminescence efficiency at high current densities. We simulate GaN-based LED structures that delay the onset of efficiency droop by spreading carrier concentrations evenly across the active region. Statistical analysis and machine learning effectively guide the selection of the next LED structure to be examined based upon its expected efficiency as well as model uncertainty. This active learning strategy rapidly constructs a model that predicts Poisson-Schrödinger simulations of devices, and that simultaneously produces structures with higher simulated efficiencies.

Authors:
 [1]; ORCiD logo [2];  [2];  [3]
  1. Univ. of Cambridge (United Kingdom). Dept. of Materials Science and Metallurgy; Los Alamos National Lab. (LANL), Los Alamos, NM (United States). Theoretical Division
  2. Los Alamos National Lab. (LANL), Los Alamos, NM (United States). Theoretical Division
  3. Univ. of Cambridge (United Kingdom). Dept. of Materials Science and Metallurgy
Publication Date:
Research Org.:
Los Alamos National Lab. (LANL), Los Alamos, NM (United States); Univ. of Cambridge (United Kingdom)
Sponsoring Org.:
USDOE Laboratory Directed Research and Development (LDRD) Program
OSTI Identifier:
1335601
Report Number(s):
LA-UR-15-27950
Journal ID: ISSN 2045-2322
Grant/Contract Number:  
AC52-06NA25396; 20140013DR
Resource Type:
Accepted Manuscript
Journal Name:
Scientific Reports
Additional Journal Information:
Journal Volume: 6; Journal ID: ISSN 2045-2322
Publisher:
Nature Publishing Group
Country of Publication:
United States
Language:
English
Subject:
30 DIRECT ENERGY CONVERSION; 36 MATERIALS SCIENCE; Information Science; Material Science; computational methods; inorganic LEDs; scientific data

Citation Formats

Rouet-Leduc, Bertrand, Barros, Kipton Marcos, Lookman, Turab, and Humphreys, Colin J. Optimisation of GaN LEDs and the reduction of efficiency droop using active machine learning. United States: N. p., 2016. Web. doi:10.1038/srep24862.
Rouet-Leduc, Bertrand, Barros, Kipton Marcos, Lookman, Turab, & Humphreys, Colin J. Optimisation of GaN LEDs and the reduction of efficiency droop using active machine learning. United States. doi:10.1038/srep24862.
Rouet-Leduc, Bertrand, Barros, Kipton Marcos, Lookman, Turab, and Humphreys, Colin J. Tue . "Optimisation of GaN LEDs and the reduction of efficiency droop using active machine learning". United States. doi:10.1038/srep24862. https://www.osti.gov/servlets/purl/1335601.
@article{osti_1335601,
title = {Optimisation of GaN LEDs and the reduction of efficiency droop using active machine learning},
author = {Rouet-Leduc, Bertrand and Barros, Kipton Marcos and Lookman, Turab and Humphreys, Colin J.},
abstractNote = {A fundamental challenge in the design of LEDs is to maximise electro-luminescence efficiency at high current densities. We simulate GaN-based LED structures that delay the onset of efficiency droop by spreading carrier concentrations evenly across the active region. Statistical analysis and machine learning effectively guide the selection of the next LED structure to be examined based upon its expected efficiency as well as model uncertainty. This active learning strategy rapidly constructs a model that predicts Poisson-Schrödinger simulations of devices, and that simultaneously produces structures with higher simulated efficiencies.},
doi = {10.1038/srep24862},
journal = {Scientific Reports},
number = ,
volume = 6,
place = {United States},
year = {2016},
month = {4}
}

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

Citation Metrics:
Cited by: 4 works
Citation information provided by
Web of Science

Save / Share:

Works referenced in this record:

The LED's dark secret
journal, August 2009


Blue-emitting InGaN–GaN double-heterostructure light-emitting diodes reaching maximum quantum efficiency above 200A∕cm2
journal, December 2007

  • Gardner, N. F.; Müller, G. O.; Shen, Y. C.
  • Applied Physics Letters, Vol. 91, Issue 24
  • DOI: 10.1063/1.2807272

On the efficiency droop in InGaN multiple quantum well blue light emitting diodes and its reduction with p-doped quantum well barriers
journal, September 2008

  • Xie, Jinqiao; Ni, Xianfeng; Fan, Qian
  • Applied Physics Letters, Vol. 93, Issue 12
  • DOI: 10.1063/1.2988324

Carrier leakage in InGaN quantum well light-emitting diodes emitting at 480 nm
journal, April 2003

  • Pope, I. A.; Smowton, P. M.; Blood, P.
  • Applied Physics Letters, Vol. 82, Issue 17
  • DOI: 10.1063/1.1570515

On resonant optical excitation and carrier escape in GaInN/GaN quantum wells
journal, February 2009

  • Schubert, Martin F.; Xu, Jiuru; Dai, Qi
  • Applied Physics Letters, Vol. 94, Issue 8
  • DOI: 10.1063/1.3089691

Anti-localization suppresses non-radiative recombination in GaInN/GaN quantum wells
journal, May 2007


Microstructural origins of localization in InGaN quantum wells
journal, August 2010


Carrier Density Dependent Localization and Consequences for Efficiency Droop in InGaN/GaN Quantum Well Structures
journal, August 2013

  • Badcock, Tom J.; Hammersley, Simon; Watson-Parris, Duncan
  • Japanese Journal of Applied Physics, Vol. 52, Issue 8S
  • DOI: 10.7567/JJAP.52.08JK10

On the origin of IQE-‘droop’ in InGaN LEDs
journal, May 2009

  • Laubsch, Ansgar; Sabathil, Matthias; Bergbauer, Werner
  • physica status solidi (c), Vol. 6, Issue S2
  • DOI: 10.1002/pssc.200880950

Curve Fitting and Optimal Design for Prediction
journal, September 1978


Design and Analysis of Computer Experiments
journal, November 1989

  • Sacks, Jerome; Welch, William J.; Mitchell, Toby J.
  • Statistical Science, Vol. 4, Issue 4
  • DOI: 10.1214/ss/1177012413

Bayesian look ahead one-stage sampling allocations for selection of the best population
journal, September 1996


The Knowledge-Gradient Policy for Correlated Normal Beliefs
journal, November 2009

  • Frazier, Peter; Powell, Warren; Dayanik, Savas
  • INFORMS Journal on Computing, Vol. 21, Issue 4
  • DOI: 10.1287/ijoc.1080.0314

Information-Theoretic Regret Bounds for Gaussian Process Optimization in the Bandit Setting
journal, May 2012

  • Srinivas, Niranjan; Krause, Andreas; Kakade, Sham M.
  • IEEE Transactions on Information Theory, Vol. 58, Issue 5
  • DOI: 10.1109/TIT.2011.2182033

Efficient band-structure calculations of strained quantum wells
journal, April 1991


Carrier distribution in (0001)InGaN∕GaN multiple quantum well light-emitting diodes
journal, February 2008

  • David, Aurélien; Grundmann, Michael J.; Kaeding, John F.
  • Applied Physics Letters, Vol. 92, Issue 5
  • DOI: 10.1063/1.2839305

Improving output power performance of InGaN-based light-emitting diodes by employing step-down indium contents
journal, March 2015

  • Kang, Daesung; Kim, Taejoon; Song, Kiyoung
  • Japanese Journal of Applied Physics, Vol. 54, Issue 4
  • DOI: 10.7567/JJAP.54.042102

An investigation of the effect of graded layers and tunneling on the performance of AlGaAs/GaAs heterojunction bipolar transistors
journal, December 1984

  • Grinberg, A. A.; Shur, M. S.; Fischer, R. J.
  • IEEE Transactions on Electron Devices, Vol. 31, Issue 12
  • DOI: 10.1109/T-ED.1984.21784

Impact of active layer design on InGaN radiative recombination coefficient and LED performance
journal, March 2012

  • Li, X.; Okur, S.; Zhang, F.
  • Journal of Applied Physics, Vol. 111, Issue 6
  • DOI: 10.1063/1.3699199

Materials informatics
journal, October 2005


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

Materials Prediction via Classification Learning
journal, August 2015

  • Balachandran, Prasanna V.; Theiler, James; Rondinelli, James M.
  • Scientific Reports, Vol. 5, Issue 1
  • DOI: 10.1038/srep13285

Neural Networks in Materials Science.
journal, January 1999


Finding Nature’s Missing Ternary Oxide Compounds Using Machine Learning and Density Functional Theory
journal, June 2010

  • Hautier, Geoffroy; Fischer, Christopher C.; Jain, Anubhav
  • Chemistry of Materials, Vol. 22, Issue 12
  • DOI: 10.1021/cm100795d

Accelerating materials property predictions using machine learning
journal, September 2013

  • Pilania, Ghanshyam; Wang, Chenchen; Jiang, Xun
  • Scientific Reports, Vol. 3, Issue 1
  • DOI: 10.1038/srep02810

Designing rules and probabilistic weighting for fast materials discovery in the Perovskite structure
journal, May 2014

  • Castelli, I. E.; Jacobsen, K. W.
  • Modelling and Simulation in Materials Science and Engineering, Vol. 22, Issue 5
  • DOI: 10.1088/0965-0393/22/5/055007

Big Data of Materials Science: Critical Role of the Descriptor
journal, March 2015


    Works referencing / citing this record:

    Recent advances and applications of machine learning in solid-state materials science
    journal, August 2019

    • Schmidt, Jonathan; Marques, Mário R. G.; Botti, Silvana
    • npj Computational Materials, Vol. 5, Issue 1
    • DOI: 10.1038/s41524-019-0221-0

    Recent advances and applications of machine learning in solid-state materials science
    journal, August 2019

    • Schmidt, Jonathan; Marques, Mário R. G.; Botti, Silvana
    • npj Computational Materials, Vol. 5, Issue 1
    • DOI: 10.1038/s41524-019-0221-0