Japanese page
SCEJ

SCEJ 53rd Autumn Meeting (Nagano, 2022)

Last modified: 2022-09-26 13:32:00

Session programs : ST-21

The preprints can be viewed by clicking the Paper IDs.
Yellow-back sessions on Technical sessions will be On-site/online Hybrid sessions, others are Online sessions.
Please check notices on menu page.
Preview of the Program book is now available (Sep. 9).

ST-21 [Trans-Division Symposium]
Frontiers of Data-driven Research and Development

Organizers: Shimada Iori (Shinshu Univ.), Kim Sanghong (Tokyo Univ. of Agri. and Tech.), Toya Yoshihiro (Osaka Univ.), Kaneko Shogo (Sumitomo Chemical), Mukaida Shiho (Mitsui Chemicals)

Data science has been rapidly developing in recent years as the fourth science following experimental science, theoretical science, and computational science. The early realization of a data-driven society led by data science has been recognized as a key to international competitiveness. This symposium will have speakers who are making pioneering efforts toward a data-driven society from various viewpoints and discuss future research and development.

Hall DC, Day 3

TimePaper
ID
Title / AuthorsKeywordsTopic codeAck.
number
Hall DC(C3 1F 102), Day 3(Sep. 16)
(9:00–10:20) (Chair: Mukaida Shiho)
9:009:40DC301[Invited lecture] Data-driven AI Laboratory and Cyber Catalysis
(Shinshu U.) (Reg)Koyama Michihisa
Data-driven
Cyber Catalysis
Computational Chemistry
ST-21102
9:4010:20DC303[Invited lecture] AI-Driven peptide/antibody molecule design for drug discovery
(MOLCURE) Tamaki Satoshi
Artificial Intelligence
Drug Discovery
Antibody
ST-21316
(10:20–12:00) (Chair: Toya Yoshihiro)
10:2010:40DC305Data-driven analysis of charge variants in monoclonal antibody production
(U. Tokyo) *(Stu)Yoshiyama Yuki, (Int)Badr Sara, (Stu)Okamura Kozue, (Manufacturing Tech. Association of Biologics) Murakami Sei, (U. Tokyo) (Reg)Sugiyama Hirokazu
Charge variant
Monoclonal antibody
PLS
ST-21641
10:4011:00DC306Multi-step approach for data-driven equipment condition assessment in biopharmaceutical drug product manufacturing
(U. Tokyo) *(Int)Zuercher Philipp Samuel, (Int)Badr Sara, (ROCHE) Knueppel Stephanie, (U. Tokyo) (Reg)Sugiyama Hirokazu
Predictive maintenance
Unsupervised learning
Industrial application
ST-21590
11:0011:20DC307Reinforcement learning to optimally control the bio and chemical processes
(Kyoto U.) (Int)Oh Tae Hoon
Reinforcement Learning
Process control
Optimal control
ST-2160
11:2011:40DC308Soft sensor study in film manufacturing process
(Meiji U.) *(Stu)Nakayama Yuki, Shiraki Yuya, (Zeon) (Cor)Natori Satoshi, (Cor)Ono Yuki, (Cor)Suda Kazuya, (Meiji U.) (Reg)Kaneko Hiromasa
Soft sensor
Fault detection
Film manufacturing process
ST-21366
11:4012:00DC309Prediction of phase equilibrium of water-organic compounds system at high-temperature and high-pressure using machine learning
(Shinshu U.) *(Stu)Tamura Kotaro, (Reg)Shimada Iori, (Reg)Fukunaga Hiroshi, (Reg)Takahashi Nobuhide, (Reg)Osada Mitsumasa
machine learning
prediction of phase equilibrium
high-temperature and high-pressure
ST-21532
(13:00–14:20) (Chair: Kaneko Shogo)
13:0013:40DC313[Invited lecture] Exploration of functional inorganic thin-film materials using autonomous systems
(Tokyo Tech) Shimizu Ryota
autonomous synthesis
inorganic materials
functional thin films
ST-21103
13:4014:20DC315[Invited lecture] Data-driven polymer material development powered by Polymer SmartLab and Material DX
(NIMS) Naito Masanobu
smart lab
material DX
database
ST-21129
(14:20–15:40) (Chair: Shimada Iori)
14:2014:40DC317Inverse design of polymer membrane structure for gas separation using Junction Tree VAE machine learning
(Kogakuin U.) *(Stu)Matsumoto Takumi, (Reg)Miyagawa Masaya, (Reg)Takaba Hiromitsu
machine learning
polymer membrane
gas separation
ST-21712
14:4015:00DC318Design of both membrane-based process and membrane materials with machine learning
(Meiji U.) *(Stu)Yuyama Shunsuke, (Reg)Kaneko Hiromasa
Membrane module
Materials Informatics
Process design
ST-21187
15:0015:20DC319[Featured presentation] Development of digital twin of the bulk single crystal growth of Si by using PINNs (Physics Informed Neural Networks)
(Osaka U.) *(Stu)Takehara Yuto, (Reg)Okano Yasunori
Digital twin
Machine learning
Physics Informed Neural Networks
ST-21396
15:2015:40DC320Growth interface shape optimization and adaptive process control for InGaSb crystal growth under microgravity using machine learning
(Osaka U.) *(Stu)Ghritli Rachid, (JAXA-SOKENDAI) Inatomi Yuko, (Osaka U.) (Reg)Okano Yasunori
Machine Learning
Reinforcement Learning
Crystal Growth
ST-21428
(15:40–17:00) (Chair: Kim Sanghong)
15:4016:00DC321Multimodal Artificial Intelligence for Data-driven Developments of Complex Composite Materials
(AIST) *(Reg)Muroga Shun, Miki Yasuaki, (ADMAT) Honda Takashi, (AIST) Morita Hiroshi, Okazaki Toshiya, Hata Kenji
Multimodal AI
Materials Informatics
Composite Material
ST-21669
16:0016:20DC322Effect of physics-based feature engineering in predicting product yields of catalytic cracking reactions
(Shinshu U.) *(Stu)Yasuike Shun, (Reg)Osada Mitsumasa, (Reg)Shimada Iori
catalytic cracking
machine learning
feature engineering
ST-21101
16:2016:40DC323Developing identifiers to link materials databases
(UTokyo) *(Reg)Muraoka Koki, Munekata Tsubasa, Nakayama Akira
materials informatics
database
ST-21580
16:4017:00DC324Discusstion on initial sample selection for Bayesian optimization of compound combinations
(Meiji U.) *(Stu)Morishita Toshiharu, (Reg)Kaneko Hiromasa
Bayesian optimization
Machine learning
Clustering
ST-21328

Technical program
Technical sessions (Wide)  (For narrow screen)
Session programs
Search in technical program
SCEJ 53rd Autumn Meeting (Nagano, 2022)


© 2022 The Society of Chemical Engineers, Japan. All rights reserved.
For more information contact Organizing Committee of SCEJ 53rd Autumn Meeting
E-mail: inquiry-53fwww3.scej.org