Closed-loop discovery of optimal materials using artificial intelligence

Recent progress in applications of machine learning in physics, chemistry and materials science indicate that automation of scientific discovery itself in some parts of these fields is no longer an implausible goal. In this talk, I will present how closed-loop research systems that build on past data and knowledge, automated experiments/computations and automated decision-making can be designed, tested and deployed to solve certain discovery problems in materials science through iterative, sequential optimization. The emphasis will be placed on the need for integration of data-driven methods with proper physics and researcher heuristics in designing agents that guide the selection of experiments or computations. I will describe the details of a particular autonomous computational platform built to find new stable, synthesizable inorganic materials by choosing which crystal structures out of infinitely many options to calculate with automated density functional theory. This cloud-based platform is running 24/7 and has already found thousands of new inorganic ground state or metastable compounds.