������

The dissertation by Lauri Himanen reviews how data-driven approaches can be used to augment materials research, focusing on two key areas: using data-driven design and tools to re-imagine the life-cycle of materials data and using machine learning to complement existing research methodologies in materials science. Materials informatics and data-driven materials science are umbrella terms for the scientific practice of systematically extracting knowledge from data produced by materials science. This practice differs from traditional scientific approaches in materials research by the volume of processed data and the more automated way information is extracted. This data-driven approach — sometimes referred to as the 4th paradigm of science — is currently transforming the way materials research is carried out.

The dissertation introduces novel tools for automated materials data mining and software for converting material data into an efficient input for use in machine learning. The effect of such data-driven techniques is demonstrated by applying them in finding optimal coating materials for perovskite-based photovoltaics using data mining and using machine learning for identifying catalytically active sites on nanoclusters. The impact and timeliness of the research is highlighted by the fact that the included was among the top 10% most downloaded papers of Advanced Science in the 12 months following online publication.

Himanen’s thesis opponent commented in his report “the thesis work by Lauri Himanen is at the highest international level with excellent, original contributions within material informatics”.

Lauri Himanen is currently a Materials Informatics Specialist at the Fritz-Haber-Institute of the Max-Planck-Society in Berlin, Germany. The can be found in the AaltoDoc repository.