A Machine-Learning Study on the Prediction of the Efficiency of Red CdSe Quantum Dot Light Emitting Diodes

DOI Web Site
  • KINOSHITA Takayuki
    Department of Physics and Electronics, Osaka Metropolitan University
  • SANO Shoichi
    Department of Physics and Electronics, Osaka Prefecture University
  • NAGASE Takashi
    Department of Physics and Electronics, Osaka Metropolitan University The Research Institute for Molecular Electronic Devices (Osaka Metropolitan Univ. RIMED)
  • KOBAYASHI Takashi
    Department of Physics and Electronics, Osaka Metropolitan University The Research Institute for Molecular Electronic Devices (Osaka Metropolitan Univ. RIMED)
  • NAITO Hiroyoshi
    The Research Institute for Molecular Electronic Devices (Osaka Metropolitan Univ. RIMED) Department of Applied Chemistry, Osaka Metropolitan University

Bibliographic Information

Other Title
  • 機械学習によるCdSe量子ドット赤色発光ダイオードの効率予測
  • 機械学習によるCdSe量子ドット赤色発光ダイオードの効率予測 : 編集委員長賞受賞論文
  • キカイ ガクシュウ ニ ヨル CdSe リョウシ ドット アカイロ ハッコウ ダイオード ノ コウリツ ヨソク : ヘンシュウ イインチョウショウ ジュショウ ロンブン

Search this article

Description

<p>Quantum dot light emitting diodes (QLEDs) with a structure of ITO (indium tin oxide)/poly (3,4-ethylenedioxythiophene) polystyrene sulfonate/hole transport layer/QD (quantum dot)/electron transport layer/Al using CdSe QD were fabricated, and machine learning was used to predict the efficiency of the QLEDs. A machine learning model was constructed to relate the efficiency of the QLEDs and the electronic transport properties of the QLEDs using a large number of data generated by device simulation. The efficiency limiting factors found by the machine learning model are consistent with those found experimentally. In addition, the machine learning model predicts the electronic properties of the hole transport layer for the fabrication of high-efficiency CdSe QLEDs.</p>

Journal

Related Projects

See more

Keywords

Details 詳細情報について

Report a problem

Back to top