The Polymer Society of Korea

Abstract

Recent advances in automation and machine learning have rapidly accelerated autonomous synthesis approaches for nanomaterials. However, their broader impact remains limited by the complexity of multistep chemistries and the lack of real-time, structure-sensitive feedback. Here, an autonomous synthesis framework integrating fluidic reactors with in situ synchrotron SAXS/WAXS is presented as part of a closed experimental workflow, with gold nanoparticles serving as a model system. In situ SAXS/WAXS provides rapid, statistically robust structural feedback on particle size, dispersity, and crystallinity during synthesis, which is used to guide autonomous, AI/ML-based decision-making. By leveraging real-time structural feedback, the platform efficiently explores high-dimensional synthesis parameter spaces and converges toward targeted gold nanoparticle characteristics with significantly reduced experimental iterations.