Program

In the deployment of new materials into high-performance commercial products, the high cost and time are inevitably required, which is attributable to multiple factors, such as the heavy reliance on experiments, the disconnect between multiscale experiments and multiscale models, and the lack of a suitable framework for facilitating and enhancing the cross-disciplinary collaborations. The emerging discipline of data science is expected to address these key technological gaps. In this session, the potential benefits to the materials innovation that could be obtained from an aggressive adoption of the novel concepts and toolsets offered by data science will be discussed. The fundamental connection between machine learning and material science, and its future application and impact will be also discussed.

• Computational materials science assisted by machine learning
• Derivation of physics-oriented models and knowledge from machine learning techniques
• Big data approaches to materials development
• Uncertainty quantification and Bayesian methods in materials science
• Materials knowledge representation and ontologies

• Irina ROSLYAKOVA, Ruhr-Universität Bochum Artificial Materials Intelligence
• Manabu ENOKI, The University of TokyoOn the consideration of inverse problem analysis for performance of structural materials
• Makoto WATANABE, National Institute for Materials Science
• Tomonaga OKABE, Tohoku University
• Satoshi MINAMOTO, National Institute for Materials Science
• E. Begum GULSOY, Northwestern University Accelerating Materials Innovation: ICME, Materials Design, Data and the Underlying Workforce Training
• Yury LYSOGORSKIY, Ruhr-Universität Bochum

• Junya INOUE The University of Tokyo
• Irina ROSLYAKOVA Ruhr-Universität Bochum
• Masahiko DEMURA National Institute for Materials Science

• Junya INOUE, The University of Tokyo Email: inoue@material.t.u-tokyo.ac.jp