Scope

The workshop aims to provide a discussion forum for researchers of the Max-Planck-Research Network on Big-Data-Driven Materials Science (BiGmax). Interdisciplinary in nature, the workshop brings together materials scientists with physicists, machine learning, scientific computing, and data science domain experts. We will discuss cutting-edge examples of machine learning method development and application in the following topical areas:

  • How to improve and enrich the characterization of the structure and plasticity of materials from the atomic scale to the continuum scale.
  • How to use machine learning for predictive quantification of microstructure-material property links.
  • Development of machine learning data diagnostics methods in imaging in electron diffraction and atom probe tomography.
  • How to use machine learning for discovering interpretable patterns, structure-property correlations, and causality based on experimentally and computationally mined materials data.
  • How to quantify uncertainty in experiments and computer simulations.
  • How to build Materials Encyclopedia with functionally rich metadata in accordance with the FAIR data stewardship principles and use ideally open source tools to arrive at easy to use and scalable machine learning tools.
Go to Editor View