We are looking for a highly motivated PhD student to explore using machine learning (ML) algorithms to automatically interpret crystallographic information contained within atom probe data.
Atom probe tomography (APT) is a powerful microanalytical technique that enables the position and chemical identity of millions of individual atoms to be reconstructed in 3D with sub nm spatial resolution. It is this unique capability that makes APT a highly valuable tool for characterising the nanostructure of important engineering materials and facilitating the understanding of structure-property relationships at the atomic level. Interpretation of crystallographic information contained within the data is often a very important part of this process, yet the currently available analysis tools make this error-prone and impractically slow. Machine learning approaches hold much promise for more accurate and rapid interpretation which in turn will enable high-end materials science that is not currently possible.
The successful candidate will be based at the Max-Planck-Insitut für Eisenforschung (MPIE) where he or she will be trained in the use of APT and the current protocols in analysis of the data. The student will also spend 25 % of the time learning kernel-based model ML algorithms at the Max-Planck-Insitut für Polymerforschung. These algorithms will then be applied to the interpretation of crystallographic information in APT data. The project is funded through BiGmax, a network of the Max Planck Society (https://www.bigmax.mpg.de/) aimed at exploiting the potentials of data-driven materials science. There will be a great opportunity to collaborate with other scientists and data analytics experts through this network as well as at international conferences throughout the candidature.
Requirements: A strong background in an engineering or a physics related field with a master’s degree or equivalent. Computer programming skills in languages such as Python or Matlab are also desirable.
Please send your application material, including a motivation letter, CV, and contact details of at least two references as one pdf file to [log in to unmask] . We will be aiming to fill the position by early 2019 and you will be informed via email as soon as possible with news of your application.
A. Breen, Microstructure Physics and Alloy Design, MPI Eisenforschung (MPIE)
T. Bereau, Theory Group, MPI Polymerforschung (MPIP)
To join or leave the molecular-dynamics-news email list, go to: