Towards Artificially Intelligent Microscopy of Functional Materials

Artificial intelligence (AI) promises to reshape scientific inquiry and enable breakthrough discoveries in areas such as quantum computing, energy storage, and advanced manufacturing. While it is now possible to produce materials in almost limitless configurations, engineering of desirable functionality depends on precise control of structure and defects across scales. Complex synthesis pathways can lead to significant deviations from idealized structures, which occur at length and time scales that are challenging to probe experimentally and theoretically. Mastery of materials is therefore predicated on the ability to acquire and act on complex, heterogeneous, and fast-evolving microscopy data streams, a task uniquely suited to emerging AI and machine learning methods. Here I will discuss my research efforts to develop a new framework for materials discovery, leveraging embedded automation, domain-grounded analytics, and predictive control for human-like reasoning. I will show how AI is transforming the present and future of materials discovery and design, allowing us to richly manipulate matter for emerging technologies.