| Scope |
Autonomous, self-driving laboratories and AI/ML-driven platforms are rapidly transforming materials science and technology. These integrated approaches promise revolutionary advances in real-time optimization and materials discovery. However, unlocking their full potential requires overcoming significant barriers, such as steep technical learning curves, lack of accessible tools, and the need for close integration of domain knowledge. This symposium will bring together researchers from across disciplines—including materials science, chemistry, and AI/ML—to showcase the latest innovations in autonomous experimentation, from high-throughput experimentation to interpretable AI models, digital twins, and closed-loop simulation–experiment platforms.
Topics of Interest Include (but are not limited to):
• High-throughput experimental for materials screening and optimization.
• Closed-loop simulation-experiment platforms for autonomous decision making.
• ML algorithms and real-time data analytics for automation and materials property prediction.
• Incorporation of physical/domain knowledge into AI/ML models to improve accuracy, interpretability, and generalizability.
• Development of autonomous materials synthesis and characterization systems.
• Human-AI synergies in decision making and experiment design.
• Digital twins to simulate, guide, and validate ML-enabled experimental research.
• Visualization and interpretation of ML prediction and decision-making for enhanced understanding in AI-driven discoveries.
• Integration of HPC, cloud, and edge computing to support real-time analysis and scalability of autonomous research systems.
This symposium aims to catalyze cross-disciplinary collaborations and empower a broader scientific community to adopt and contribute to the future of autonomous, AI-enabled materials discovery. |