Machine learning based computational methods to analyze structural characterization in soft materials

Soft materials researcher aiming to establish design-structure-property relationships have to rely on structural characterization from multiple complementary techniques to obtain a holistic understanding of structures within their newly designed material. Depending on the availability and accessibility of the different characterization techniques (e.g., scattering, microscopy, spectroscopy), each research facility or academic research lab may have access to high-throughput capability in one technique but face limitations (sample preparation, resolution, access time) with other technique(s). Furthermore, one type of structural characterization data may be easier to interpret than another (e.g., microscopy images are easier to interpret than small angle scattering profiles). Thus, it is useful to have machine learning models that can be trained on paired structural characterization data from multiple techniques (easy and difficult to interpret, fast and slow in data collection or sample preparation), so that the model can generate one set of characterization data from the other. In this talk I will discuss one such machine learning model called PairVAE that pairs small angle scattering results (i.e., information about bulk morphology) and electron microscopy images (i.e., information about two-dimensional local structure). Using paired SAXS and SEM data of newly observed block copolymer assembled morphologies [open access data from Doerk G.S., et al. Science Advances. 2023 Jan 13;9(2): eadd3687], we trained the PairVAE model. After successful training, PairVAE is able to generate SEM images of the block copolymer morphology when it takes as input that sample’s corresponding SAXS 2D pattern, and vice versa.