SCEJ 57th Autumn Meeting (Higashihiroshima, 2026)
Last modified: 2026-07-16 06:38:20
Session programs : ST-21
The chairs are under negotiation.
Yellow-backs on Technical sessions denote the Hybrid sessions.
(All other sessions are on-site only sessions).
Yellow-backs on Technical sessions denote the Hybrid sessions.
(All other sessions are on-site only sessions).
ST-21 [Trans-Division Symposium]
Frontiers of Data-driven Research and Development
Data science has been rapidly developing in recent years as the fourth science following experimental science, theoretical science, and computational science. In the field of chemical engineering, data-driven science, which derives superior materials and processes by making full use of a large amount of accumulated data and information, is becoming increasingly important, and many efforts are being made. This symposium will have speakers who are making pioneering efforts toward a data-driven society from various viewpoints and discuss future research and development.
| Time | Paper ID | Title / Authors | Keywords | Topic code | Ack. number |
|---|---|---|---|---|---|
| Hall A, Day 1 | |||||
| (10:00–11:20) | |||||
| A104 | Development of a Machine Learning Model for Predicting Solubility in Binary Solvent Systems at Arbitrary Temperatures | Chemoinformatics Solubility prediction Machine learning | ST-21 | 104 | |
| A105 | A data-driven framework for identifying critical solvent parameters in hydrogenation reactions | Machine learning Hydrogenation Solvent effect | ST-21 | 778 | |
| A106 | Optimal Design of e-Methanol Production Process Using Machine Learning and Superstructure Optimization | e-methanol Machine learning Process design | ST-21 | 301 | |
| A107 | Verification and Evaluation of Large Language Models for Supporting Chemical Process Design | Large Language Models Chemical Process Benchmark | ST-21 | 481 | |
| (11:20–12:00) | |||||
| A108 | [Invited lecture] Hybrid modeling for connecting experimental data with process design | hybrid modeling pharmaceutical manufacturing design space | ST-21 | 920 | |
| (13:00–13:40) | |||||
| A113 | [Invited lecture] The Frontline of AI and Autonomous Experimentation for Winning the Competition | AI agent Autonomous experiment Materials informatics | ST-21 | 921 | |
| (13:40–15:00) | |||||
| A115 | Sequential Processing of Long Texts Using Large Language Models for Literature Mining of Endothelial Cell Culture Protocols | LLM Text mining Endothelial cell | ST-21 | 791 | |
| A116 | Construction of machine learning models for predicting in vivo responses of artificial bone materials using in vitro indicators | artificial bone in vivo in vitro | ST-21 | 112 | |
| A117 | Construction of a miRNA-mRNA Binding Prediction Model Using Unknown Interaction Data and Performance Evaluation with Non-binding Data | Machine Learning bioinformatics RNA | ST-21 | 305 | |
| A118 | Development of an instability analysis for freezing process changes in cell-based products | Instability analysis Freezing process change Cell-based product | ST-21 | 578 | |
| (15:20–16:40) | |||||
| A120 | Automated MOF Synthesis Using a Robotic Arm and an Electric Pipette | Metal-organic framework Laboratory automation Particle size control | ST-21 | 450 | |
| A121 | Advancing Chemical Engineering Research through an Integrated AI Platform | AI Cheminformatics Optimization | ST-21 | 635 | |
| A122 | Development and evaluation using novel chemical feature-augmented GNN | machine learning molecular graph coarse graph | ST-21 | 754 | |
| A123 | Fast estimation of H+ conductive barriers in perovskite oxides using the bond valence approach with machine learning | H+ conductive oxides Machine learning Solid oxide fuel cell | ST-21 | 474 | |
| Hall A, Day 2 | |||||
| (10:00–11:00) | |||||
| A204 | Machine learning-based extrapolative prediction of dual-functional materials for CO and CH4 production via CO2 capture and reduction | CO2 capture and reduction (CCR) dual-functional materials (DFMs) machine learning (ML) | ST-21 | 264 | |
| A205 | Development of a data-driven model for estimation of reaction diffusion mechanisms in porous solid catalysts | Reaction mechanism Reaction-diffusion system Data-driven | ST-21 | 909 | |
| A206 | Integrating DFT Reaction Kinetics with Group Contribution-Based Environmental Impacts for Sustainable Solvent Selection | Density functional theory (DFT) Solvents screening Reaction rates | ST-21 | 326 | |
| (11:00–12:00) | |||||
| A207 | Data-Driven Research in MMA Production Catalyst Development: Utilization of HTS Data Based on Reaction Engineering | high throughput kinetics catalyst deactivation | ST-21 | 850 | |
| A208 | Quantifying propagation distance of structural information in crystals | zeolite intergrowths crystal growth simulation | ST-21 | 462 | |
| A209 | The relationship between entropy production governing crystal growth and information entropy identifying pattern formation | entropy production information entropy crystal growth | ST-21 | 389 | |
Technical program
Technical sessions (Wide)
(For narrow screen)
Session programs
Search in technical program
SCEJ 57th Autumn Meeting (Higashihiroshima, 2026)
© 2026 The Society of Chemical Engineers, Japan. All rights reserved.For more information contact Organizing Committee of SCEJ 57th Autumn Meeting
E-mail: inquiry-57f
www4.scej.org