Materials Data Science and Informatics (IAS-9)

We address inverse problems, which may lack unique solutions but can be transformed into well-posed problems through deep learning-based regularization and the incorporation of physics constraints. There, analyzing and tuning the latent space representation is one of the used approaches.

Related Publications:

• L. Morand, T. Iraki, J. Dornheim, S. Sandfeld, N.Link, D. Helm, Machine learning for structure-guided materials and process design, Materials & Design, Volume 248, 2024, 113453, ISSN 0264-1275, https://doi.org/10.1016/j.matdes.2024.113453.