| About this Symposium |
| Meeting |
MS&T25: Materials Science & Technology
|
| Symposium
|
Enhancing the Accessibility of Machine Learning-Enabled Experiments
|
| Sponsorship |
ACerS Basic Science Division
|
| Organizer(s) |
Yongtao Liu, Oak Ridge National Laboratory
Arpan Biswas, University of Tennessee |
| Scope |
The rapid integration of machine learning (ML) and artificial intelligence (AI) into experimental research has revolutionized how science is conducted. From autonomous laboratories to real-time data analysis, ML/AI technologies offer unprecedented capabilities that can significantly accelerate scientific discovery. However, the adoption of these technologies requires a steep learning curve for materials scientists. This symposium proposes to address these challenges by showcasing the latest advancements of user-friendly ML/AI tools for materials scientists, catalyzing further development and dissemination of accessible ML/AI tools in the scientific community. This symposium will highlight the innovative ideas to integrate any prior or on the fly physical knowledge into the ML tools, to bridge the gap between ML and material scientists to accelerate discovery. This symposium aims to democratize advanced technologies and empower more researchers to leverage ML/AI for innovative and efficient scientific exploration. Attendees will gain knowledge about the latest tools and approaches for integrating ML/AI into their research workflows. They will also gain insights into overcoming technical challenges and fostering collaborations across different scientific disciplines.
Symposium topics include but are not limited to
• Machine learning (ML) packages and distributions facilitating easy integration of ML models in research.
• Innovative integration of physical/domain knowledge into ML-enabled experimentation
• Interfaces and visualization tools for interpreting ML outputs effectively.
• Application program interfaces that allow seamless communication between laboratory instruments and ML systems, and enables more efficient and reproducible experiments.
• Digital twins in assisting ML enabled experimentation.
• Human-AI synergies
• Interpretable ML for scientific research |
| Abstracts Due |
05/01/2025 |