Workflows for experimental design or large simulation studies of materials with complex and partially unknown behaviours are an active subject of research in materials science. To generate precise digital models of aqueous foams, various processes governing the microstructure and properties of the final foam need to be considered. These processes are described through numerous statistical and physical parameters such as initial microstructure seeding, interface driving forces, and factors affecting foam stability like coalescence. These interlinked parameters span a large design space that requires tuning to tailor the microstructure evolution and resulting physical qualities.
We aim for a data-driven framework that uses machine learning to guide both experiments and simulations in an autonomous closed-loop. To efficiently explore and exploit the search space, while minimizing the number of required evaluations, the developed design-of-experiments methodology uses Bayesian Optimization. This approach suggests the next most informative evaluation to perform, thereby autonomously and adaptively learning from the already acquired dataset. Thus, this iterative approach accelerates the materials development process by guiding researchers towards promising candidates to investigate.
The design workflow is implemented in the data platform Kadi4Mat [1], which provides the ability to store heterogeneous provenance data, along with a common workspace to integrate analysis methods and visualization. Our contribution within Kadi4Mat strongly relies on the reuse of data and provides an example of close interoperability between experimental and simulation research, in full alignment with the FAIR principles. 

Acknowledgements: This work is funded by the Ministry of Science, Research and Art Baden-Württemberg (MWK-BW) in the project MoMaF–Science Data Center, with funds from the state digitization strategy digital@bw (project number 57).

[1] Kadi4Mat is the Karlsruhe Data Infrastructure for Materials Science, an open-source software for managing research data, developed at the Institute for Applied Materials - Microstructure Modelling and Simulation (IAM-MMS) of the Karlsruhe Institute of Technology (KIT).