Tuesday, March 16th


You're invited to join Bruker and Prof. Philippe Leclère, Ph.D. (Univ. of Mons) for a 60-minute webinar, Quantitative AFM Nanomechanics Data for Machine Learning and Materials Developments. This webinar discusses how AFM-based nanomechanical measurements and machine learning can provide new insights into the mechanical properties of polymeric materials.

First, by additionally providing quantitative maps of mechanical properties at the nanoscale, AFM is shown to be ideally suited to providing the data needed to apply machine learning (ML) to materials development. Several AFM modes that are often used in polymer research are covered, including their strengths and weaknesses. We will discuss methods to automate and maximize speed of acquisition, optimize accuracy of property maps, and take advantage of novel property channels and data cubes.

In the second part, we will discuss computational methods and ML algorithms dealing with data clustering (such as K-Means or Automatic Gaussian Mixture Model) that can be used to detect the different domains and (inter)phases in materials (e.g., polymer blends, hydrogels, nanocomposites, and block copolymers) by partitioning the recorded data (i.e., the observables) into clusters according to their similarities. This algorithmically driven approach enables the analysis of materials with more complex architectures and/or other properties (such as electrical), opening new avenues of research on advanced materials with specific functions and desired properties for the creation of functional and more reliable structural materials.

* *
What best describes your current interest?*