Session Details

[22a-52A-1~9]23.1 Joint Session N "Informatics"

Fri. Mar 22, 2024 9:00 AM - 11:45 AM JST
Fri. Mar 22, 2024 12:00 AM - 2:45 AM UTC
52A (Building No. 5)
Kentaro Kutsukake(RIKEN), Yukari Katsura(NIMS)

[22a-52A-1][INVITED] Introduction to applied informatics session

〇Yuma Iwasaki1 (1.NIMS)

[22a-52A-2]Measurement data-analysis framework 2DMAT : application studies with Fugaku

〇Takeo Hoshi1,2,3, Harumichi Iwamoto4, Naoki Kinoshita4, Takeru Sawagashira4, Akito Nakano1, Yuma Terachi1, Izumi Mochizuki2, Rezwan Ahmed2, Ken Wada2, Satoru Takakusagi5, Shuhei Kudo6, Yuichi Motoyama3, Kazuyoshi Yoshimi3 (1.Nat. Inst. Fusion Science, 2.KEK, 3.Univ. Tokyo, 4.Tottori Univ., 5.Hokkaido Univ., 6.Univ. Elec. Comm.)

[22a-52A-3]Multi-component plasma analysis by the measurement data analysis framework 2DMAT.

〇(M1)Yuma Terachi1, Kentaro Sakai1, Lan Gao2, Hantao Ji2, Takeo Hoshi1 (1.Nat. Inst. Fusion Science, 2.Princeton Plasma Phys. Lab.)

[22a-52A-4]Data-driven Approach for Multifaceted Characterization of Carbon Nanotubes

〇Shun Muroga1, Satoshi Yamazaki2, Kaori Fujii1, Koji Michishio1, Hideaki Nakajima1, Takahiro Morimoto1, Nagayasu Oshima1, Kazufumi Kobashi1, Toshiya Okazaki1 (1.AIST, 2.ADMAT)

[22a-52A-5]Benchmark for LLM in Materials Science and the evaluation of ChatGPT and Bard

〇Michiko Yoshitake1, Yuta Suzuki2, Ryo Igarashi1, Yoshitaka Ushiku1, Keisuke Nagato3 (1.OSX, 2.Osaka Univ., 3.Univ. Tokyo)

[22a-52A-6]Evaluation and Improvement of Large-Scale Language Models for Retrieval of Magnetic Material Synthesis Conditions

〇Luca Foppiano1, Guillaume Lambard1, Masashi Ishii1 (1.Data-driven Materials Design Group, CBRM, NIMS)

[22a-52A-7]Extracting compound synthesis methods by text mining

〇Hironori Nakaoka1, Takashi Inui2 (1.SMM, 2.Univ. of Tsukuba)

[22a-52A-8]Development of semi-automatic AI system for large-scale data curation in Starrydata

〇Tomoya Mato1, Masaya Kumagai2,3, Yu Takada1, Yukari Katsura1,2,4 (1.NIMS, 2.RIKEN, 3.SAKURA Internet Inc., 4.University of Tsukuba)

[22a-52A-9]Prospects of machine learning by using large-scale experimental data on Starrydata

〇Yukari Katsura1,2,3, Tomoya Mato1, Masaya Kumagai3,4, Koji Tsuda1,3,5 (1.NIMS, 2.Univ. of Tsukuba, 3.RIKEN, 4.SAKURA Internet Inc., 5.Univ. of Tokyo)