| Scope |
Autonomous materials development: using machine learning and automated workflows for designing and understanding materials
Autonomous 'self-driving' laboratories offer tremendous potential in the space of materials science and technology, enabling rapid prototyping, optimization of processing parameters, understanding materials behavior, and perhaps most exciting, the potential for discovering new materials at unprecedented pace. However, creating autonomous workflows for materials science requires significant effort, as it necessitates combining experts from multiple fields including core materials science, experts in synthesis and characterization methods, and core computer science. This symposium seeks to bring together experts who are focused on developing autonomous workflows, in simulation and/or experiment, to encourage knowledge sharing in this rapidly developing space.
Topics of interest include:
1. High throughput experimental and/or theoretical workflows
2. Closed-loop simulation-experiment platforms
3. Algorithms, machine learning models and computational methods for real-time data analysis and automation, and
4. Materials design via machine learning and advanced optimization
5. Integration of high-performance computing (HPC) or edge computing with instrumentation
6. Development of autonomous materials synthesis and characterization systems |