Towards Quantitative Mapping of Mechanical Properties of Soft Materials—When AI Meets Materials!

Over the past few decades, functional materials have replaced existing materials in many applications from aerospace to cosmetics. With these novel materials impacting every part of our lives, they have become ubiquitous. Mechanical property mapping can provide critical insights into the fundamental processes at the local scale that lead to deformation phenomena in these materials or their degradation upon external mechanical stress.
Here, we focus on the latest cutting-edge developments of scanning probe microscopies (SPM) and spectroscopies for the characterization of materials surfaces and interfaces in soft polymeric materials (i.e. polymer blends, nanocomposites, hydrogels, cosmetics). We highlight the abilities of modern SPM-based techniques (PeakForce Tapping, Ringing Mode, nanoDynamic Mechanical Analysis) to characterize the properties of materials via the collection of multiple physical and mechanical property maps of samples with sub-nanometer lateral resolution in a highly repeatable manner. Particular attention is given on the quantitative mapping of nanomechanical properties such as adhesion, deformation, rigidity modulus, storage modulus, loss modulus.
In this context, Machine Learning (ML) has been perceived as a promising tool for the design and discovery of novel materials for a broad range of applications. Here, we present a novel mechano-spectroscopic SPM technique that overcomes the limitations of current spectroscopic methods by combining the high-resolution imaging capabilities of SPM with ML classification. This novel approach employs SPM operating in sub-resonance tapping imaging mode. We also shortly discuss computational methods and ML algorithms dealing with data acquisition validation and clustering that can detect the different domains and (inter)phases in materials by partitioning the recorded data (i.e. the observables) into clusters according to their similarities.
This algorithmically driven approach will enable the analysis of materials with more complex architectures and/or other properties, opening new avenues of research on advanced materials with specific functions and desired properties leading to the creation of functional, more reliable, and ideally eco-responsible materials. Through this approach, we aim to help the scientific community better understand the key parameters in optimizing material behavior for fundamental aspects and industrial applications.