Oral Session

A. New Materials Methodology for Next-Generation » [A-4] New Methodology for Developing Innovative Materials

[A4-O3] Slot 03

Tue. Dec 14, 2021 9:00 AM - 11:00 AM Room E (G416+417)

Chair: Michiko Kusunoki (Nagoya University)

+Add all to schedule

9:00 AM - 9:20 AM

[A4-O3-01] Features in Optical Image of Generation Points of Dislocation Clusters in Multicrystalline Silicon Ingot Predicted by Transfer Learning of Convolutional Neural Network

*Hiroaki Kudo¹, Takuto Kojima¹, Tetsuya Matsumoto¹, Kentaro Kutsukake², Noritaka Usami³ (1. Grad. Sch. Info., Nagoya Univ. (Japan), 2. AIP, RIKEN (Japan), 3. Grad. Sch. Eng., Nagoya Univ. (Japan))

9:20 AM - 9:40 AM

[A4-O3-02] Four-dimensional Variational Method coupled with Bayesian Optimization for Phase-field Simulation of Solid-state Sintering

*Akimitsu Ishii¹, Akinori Yamanaka¹, Eisuke Miyoshi¹, Akiyasu Yamamoto¹ (1. Tokyo Univ. of Agric. and Tech. (Japan))

9:40 AM - 10:00 AM

[A4-O3-03] Two Coexisting Mechanisms for Ferroelectric Phase Transition in Li₂SrNb₂O₇

*Yasuhide Mochizuki¹, Takayuki Nagai², Hirokazu Shirakuni², Akitoshi Nakano², Fumiyasu Oba¹, Ichiro Terasaki², Hiroki Taniguchi² (1. Tokyo Inst. of Tech. (Japan), 2. Nagoya Univ. (Japan))

10:00 AM - 10:20 AM

[A4-O3-04] Precise analysis of segregation sites for As dopants at Si grain boundaries

*Yutaka Ohno¹, Tatsuya Yokoi², Yasuo Shimizu^1,5, Jie Ren¹, Koji Inoue¹, Yasuyoshi Nagai¹, Kentaro Kutsukake³, Kozo Fujiwara¹, Atsutomo Nakamura^2,4, Katsuyuki Matsunaga², Hideto Yoshida⁴ (1. Tohoku Univ. (Japan), 2. Nagoya Univ. (Japan), 3. RIKEN (Japan), 4. Osaka Univ. (Japan), 5. NIMS (Japan))

10:20 AM - 10:40 AM

[A4-O3-05] Improvement of Machine Learning Model for Crystal Orientation Estimation by Data Augmentation

*Takuto Kojima¹, Kyoka Hara², Kentaro Kutsukake³, Tetsuya Matsumoto¹, Hiroaki Kudo¹, Noritaka Usami² (1. Grad. Info. Nagoya Univ. (Japan), 2. Grad. Eng. Nagoya Univ. (Japan), 3. RIKEN AIP (Japan))

10:40 AM - 11:00 AM

[A4-O3-06] Process optimization for the seeded directional solidification of Si ingot using CFD and machine learning

*Xin Liu¹, Yifan Dang¹, Hiroyuki Tanaka¹, Kentaro Kutsukake², Toru Ujihara¹, Noritaka Usami¹ (1. Nagoya Univ. (Japan), 2. RIKEN (Japan))

Session information

[A4-O3] Slot 03

[A4-O3-01] Features in Optical Image of Generation Points of Dislocation Clusters in Multicrystalline Silicon Ingot Predicted by Transfer Learning of Convolutional Neural Network

[A4-O3-02] Four-dimensional Variational Method coupled with Bayesian Optimization for Phase-field Simulation of Solid-state Sintering

[A4-O3-03] Two Coexisting Mechanisms for Ferroelectric Phase Transition in Li₂SrNb₂O₇

[A4-O3-04] Precise analysis of segregation sites for As dopants at Si grain boundaries

[A4-O3-05] Improvement of Machine Learning Model for Crystal Orientation Estimation by Data Augmentation

[A4-O3-06] Process optimization for the seeded directional solidification of Si ingot using CFD and machine learning

Authentication

Session information

[A4-O3] Slot 03

[A4-O3-01] Features in Optical Image of Generation Points of Dislocation Clusters in Multicrystalline Silicon Ingot Predicted by Transfer Learning of Convolutional Neural Network

[A4-O3-02] Four-dimensional Variational Method coupled with Bayesian Optimization for Phase-field Simulation of Solid-state Sintering

[A4-O3-03] Two Coexisting Mechanisms for Ferroelectric Phase Transition in Li2SrNb2O7

[A4-O3-04] Precise analysis of segregation sites for As dopants at Si grain boundaries

[A4-O3-05] Improvement of Machine Learning Model for Crystal Orientation Estimation by Data Augmentation

[A4-O3-06] Process optimization for the seeded directional solidification of Si ingot using CFD and machine learning

Authentication

[A4-O3-03] Two Coexisting Mechanisms for Ferroelectric Phase Transition in Li₂SrNb₂O₇