Japan Geoscience Union Meeting 2025

Presentation information

[J] Oral

M (Multidisciplinary and Interdisciplinary) » M-IS Intersection

[M-IS13] Interface- and nano-phenomena on crystal growth and dissolution

Sun. May 25, 2025 9:00 AM - 10:30 AM 201B (International Conference Hall, Makuhari Messe)

convener:Yuki Kimura(Institute of Low Temperature Science, Hokkaido University), Hitoshi Miura(Graduate School of Science, Department of Information and Basic Science, Nagoya City University), Hisao Satoh(Low-Level Radioactive Waste Disposal Center, Japan Nuclear Fuel Limited), Chairperson:Jun Kawano(Faculty of Science, Hokkaido University), Hitoshi Miura(Graduate School of Science, Department of Information and Basic Science, Nagoya City University)

9:00 AM - 9:30 AM

[MIS13-01] AI for Science: The Dawn and Dilemmas of a New Data-Driven Science

★Invited Papers

*Ichigaku Takigawa1 (1.Kyoto University)

Keywords:AI for Science, Machine Learning (ML), Artificial Intelligence (AI), Data-driven Sciences

In recent years, artificial intelligence (AI) technologies based on machine learning (ML) have become indispensable in both daily life and scientific research. Technologies such as image and speech recognition and generation, text generation by large language models (LLMs), and text-guided image and video generation have moved beyond the research phase and are now widely used in commercial services, becoming everyday tools in our information-driven society. These advancements are powered by ML trained on vast amounts of data and are rapidly expanding into the natural sciences, including materials science, chemistry, and physics. The awarding of the 2024 Nobel Prizes in Physics and Chemistry to AI-related research serves as a recent milestone in this trend.

Having achieved commercial success in areas like computer vision, speech, and language, the natural sciences are now attracting great interest as the next frontier for ML. This talk will explore how ML can contribute to the analysis and prediction of complex natural phenomena from the perspective of "AI for Science." It will provide an overview of recent trends, current challenges, and future prospects for AI applications. We hope this talk will inspire new research approaches in crystal growth, interface science, and nanoscience.