Innovative materials are one of the key technologies for keeping products and industrial processes economically competitive and ecologically sustainable. Modern materials science requires a multi-discipline approach embracing chemistry, physics, engineering, as well as data science. This summer school will provide an overview of current developments in data-driven materials science involving Machine Learning and modern numerical techniques and will offer a platform for discussions about future perspectives.

Materials innovations enable new technological capabilities and drive major societal advancements but typically require long and costly development cycles. A major challenge for materials development is the interplay of different time and length scales relevant for many advanced materials. Reliable theoretical predictions, their experimental verification and technological implementation are crucial in this context. Complementary efforts and the seamless integration of theory, computation and experiment, will result in a remarkable acceleration of the pace of new materials discovery, design and deployment. To fully take advantage of its potential, this scheme has to rely on cross-innovation and convergence of various scientific fields such as materials science, computer science, physics, chemistry as well as information and data science.

This online summer school targets Master students, Ph.D. students and (early-stage) Postdocs interested in or working on topics related to computational and experimental high-throughput approaches, machine learning and data-driven materials science.