Project description

Focused ion beam (FIB) tomography determines the three-dimensional microstructure of materials via a series of two-dimensional scanning electron microscope (SEM) images. In nanoporous metals, FIB tomography is often facing problems with so-called shine-through effects, which can significantly reduce the accuracy with which FIB tomography data can be segmented. This project will use machine learning to develop a new segmentation method which can efficiently suppress shine-through effects and thus enable a reconstruction even of complex hierarchical multi-scale microstructures of nanoporous metals with excellent accuracy.

Project leader
Prof. Dr.-Ing. Christian J. Cyron,
Dr.-Ing. Martin Ritter

nanoporous                                                        metal

electron microscopy



machine learning


1. T. Sardhara, R. C. Aydin, Y. Li, N. Piché , R. Gauvin, C. J. Cyron and M. Ritter: Training Deep Neural Networks to Reconstruct Nanoporous Structures From FIB Tomography Images Using Synthetic Training Data. Front. Mater. 9, 837006 (2022) open access

2. F.E. Bock, R.C. Aydin, C.J. Cyron, N. Huber, S.R. Kalidindi and B. Klusemann: A Review of the Application of Machine Learning and Data Mining Approaches in Continuum Materials Mechanics. Frontiers in Materials 6, (2019) open access

3. R.C. Aydin, F.A, Braeu and C.J. Cyron: General Multi-Fidelity Framework for Training Artificial Neural Networks With Computational Models.  Frontiers in Materials 6, (2019) open access