Application of machine learning for high-performance multicrystalline materials

Noritaka Usami, Kentaro Kutsukake, Takuto Kojima, Hiroaki Kudo, Tetsuya Matsumoto, Tatsuya Yokoi, Yasuo Shimizu, Yutaka Ohno

研究成果: Conference contribution

抄録

We report on our recent attempt to pioneer “multicrystalline informatics” through collaboration of experiments, theory, computation, and machine learning to establish universal guidelines how we can obtain high-performance multicrystalline materials. We employ silicon as a model material, and develop various useful machine learning models. One example is a neural network to predict distribution of crystal orientations in a large-area sample from multiple optical images. Transfer learning of pre-trained image classifier could predict spatial distribution of probability of dislocations generation from photoluminescence images. Extracted regions with high probability of dislocations generation could be characterized by multiscale experiments as well as computation using artificial-neural-network interatomic potential to disclose the physics behind. The obtained knowledge could be useful for process development of high-performance multicrystalline materials.

本文言語English
ホスト出版物のタイトル239th ECS Meeting with the 18th International Meeting on Chemical Sensors, IMCS 2021 - High Purity and High Mobility Semiconductors 16
編集者E. Simoen, O. Kononchuk, O. Nakatsuka, C. Claeys
出版社IOP Publishing Ltd.
ページ11-16
ページ数6
4
ISBN(電子版)9781607685395
DOI
出版ステータスPublished - 2021
イベント239th ECS Meeting with the 18th International Meeting on Chemical Sensors, IMCS 2021 - Chicago, United States
継続期間: 2021 5 302021 6 3

出版物シリーズ

名前ECS Transactions
番号4
102
ISSN(印刷版)1938-6737
ISSN(電子版)1938-5862

Conference

Conference239th ECS Meeting with the 18th International Meeting on Chemical Sensors, IMCS 2021
国/地域United States
CityChicago
Period21/5/3021/6/3

ASJC Scopus subject areas

  • 工学(全般)

フィンガープリント

「Application of machine learning for high-performance multicrystalline materials」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル