| The discovery and development of novel materials in the field of energy are essential to accelerate the transition to a low-carbon economy. Bringing recent technological innovations in automation, robotics and computer science together with current approaches in chemistry , materials synthesis and characterization will act as a catalyst for revolutionizing traditional research and development in both industry and academia. This Perspective provides a vision for an integrated artificial intelligence approach towards autonomous materials discovery , which, in our opinion, will emerge within the next 5 to 10 years. The approach we discuss requires the integration of the following tools, which have already seen substantial development to date: high-throughput virtual screening, automated synthesis planning, automated laboratories and machine learning algorithms. In addition to reducing the time to deployment of new materials by an order of magnitude, this integrated approach is expected to lower the cost associated with the initial discovery. Thus, the price of the final products (for example, solar panels, batteries and electric vehicles) will also decrease. This in turn will enable industries and governments to meet more ambitious targets in terms of reducing greenhouse gas emissions at a faster pace. volume 3 | mAY 2018 | 5 PERSPECTIVES

Pourbaix diagrams are an invaluable tool for exploring the corrosion profiles of materials as a function of ambient pH and electrochemical potential. 1 In recent years, high-throughput computational materials science efforts like those from the Materials Project 2,3 have enabled more comprehensive Pourbaix diagrams to be constructed and disseminated from computational data. 4,5 These analyses have informed a number of computational studies of materials for electrochemical applications, aqueous electrocatalysis 6-9 and photoelectrocatalysis, 10? ,11 non-equilibrium crystallization, 12,13 and corrosion-resistant alloy design. 14,15 In these, pourbaix analysis of multi-element systems is particularly valuable, as finding elusive materials like acid-stable oxygen evolution catalysts, 7 earth-abundant hydrogen evolution catalysts, 16 and selective CO 2 reduction catalysts 17 has and will likely continue to require exploration and optimization in multi-element spaces. However, Pourbaix analysis of phase stability on these resources have been limited to 3 or fewer elements, largely because computing the electrochemical phase stability of higher composition spaces has proven inefficient with existing 1 arXiv:1909.00035v1 [cond-mat.mtrl-sci]

We present an end-to-end computational system for autonomous materials discovery. The system aims for cost-effective optimization in large, high-dimensional search spaces of materials by adopting a sequential, agent-based approach to...