Universal Phase Identification of Block Copolymers from Physics-informed Machine Learning

Abstract

Block copolymers play a vital role in materials science due to their widely studied self-assembly behavior. Traditionally, exploring the phase space of block copolymer self-assembly and associated structure–property relationships involves iterative synthesis, characterization, and theory, which is labor-intensive both experimentally and computationally. Here, we introduce a versatile, high-throughput workflow towards materials discovery that integrates controlled polymerization and automated chromatographic separation with a novel physics-informed machine learning (ML) algorithm for the rapid analysis of small-angle X-ray scattering (SAXS) data. Leveraging the expansive and high-quality experimental datasets generated by automated chromatography, this machine learning method effectively reduces data dimensionality by extracting chemical-independent features from SAXS data. This new approach allows for the rapid and accurate prediction of morphologies without repetitive manual analysis, achieving out-of-sample predictive accuracy of around 95% for both novel and existing materials in the training dataset. By focusing on a subset of samples with large predictive uncertainty, only a small fraction of the samples needs to be inspected to further improve accuracy and achieve near-perfect predictions. In summary, the synergistic combination of controlled synthesis, automated chromatography, and data-driven analysis creates a powerful workflow that markedly expedites the discovery of structure–property relationships in advanced soft materials.