Digitalization and Machine Learning

The digitalization of materials science and engineering is currently addressed with high priority worldwide. The FAIR handling of data, i.e. making them findable, accessible, interoperable and reusable, is also within the CM department a major driving force for novel digitial concepts and software developments. The employment of the integrated development pyiron is a central activity in this regard. The activities of the CM department are embedded in large-scale collaborative initiatives like Plattform MaterialDigital and NFDI-MatWerk.

Complex simulation protocols combine distinctly different computer codes and have to run on heterogeneous computer architectures. To enable these complex simulation protocols, the CM department has developed pyiron. [more]
Atom probe tomography (APT) provides three dimensional(3D) chemical mapping of materials at sub nanometer spatial resolution. In this project, we develop machine-learning tools to facilitate the microstructure analysis of APT data sets in a well-controlled way. [more]
PMD initiated in 2019 as a collaborative effort to facilitate digitalization of material science industry, with the focus on implementing novel and sustainable concepts to manage and share data hosted on decentralized and highly diverse servers. The CM department and MPIE with the expertise in development of pyiron has been one of the initiators and founding members of the innovation platform MaterialDigital. [more]
The initiative NFDI-MatWerk is a community-driven effort to structure materials data according to the FAIR principles, i.e., making them accessible, findable, interoperable and reusable. [more]
The project’s goal is to synergize experimental phase transformations dynamics, observed via scanning transmission electron microscopy, with phase-field models that will enable us to learn the continuum description of complex material systems directly from experiment.  [more]
In order to prepare raw data from scanning transmission electron microscopy for analysis, pattern detection algorithms are developed that allow to identify automatically higher-order feature such as crystalline grains, lattice defects, etc. from atomically resolved measurements. [more]
In this project, the pyiron GUI is developed as a super-thin additional layer on top of the overall pyiron framework to interact with the underlying software. As such, the current development focuses on providing graphical elements for specific tasks performed in pyiron. The first fully implemented task is browsing through the project structure (files) and its data. [more]
To achieve FAIR data, i.e. make data findable, acessible, interoperable, and reuseable, extending the raw data with metadata is required. Good metadata includes information about data creation, e.g. experimental setup, and provides key results in a handy way. Such rich information allows us to search for data matching specific requirements. In this project we develop and test metadata schemes for experimental materials science. 
In order to ease the inter-departmental collaborations, the CM department actively contributes in providing the required infrastucture for digital workflows connecting tools developed in different departments of MPIE. [more]
Machine Learning Potentials Including Magnetism
The Magnetic Moment Tensor Potentials (mMTPs) are a class of machine-learning interatomic potentials, which could accurately reproduce both vibrational and magnetic degrees of freedom as provided, e.g., from first-principles calculations [1]. Application to prototypical bcc iron has demonstrated that these potentials are capable to quantitatively approximate local magnetic moments, energies, and forces for various magnetic states. In this project, a number of applications such as the computation of phonon spectra in ferro- and paramagnetic states as well as molecular-dynamics simulations including spin-flips are explored.  more
Go to Editor View