AI-guided Autonomous Workflows Accelerate Kinetic Analysis of Polymer Depolymerization

Deep understanding of polymerization and depolymerization kinetic behavior enables precision synthesis and manufacturing. However, traditional kinetic experiments are bottlenecked by labor-intensive sample collection and analysis practices and suffer reproducibility challenges due to human error and bias. Here, we introduce an artificial intelligence (AI)-driven automated kinetics platform to facilitate kinetic analysis and produce large volumes of high-quality kinetic data with minimal human intervention. Our autonomous workflow, encompassing automated synthesis, analysis, and cloud computing capabilities navigated complex parameter space using an importance-guided Bayesian optimization algorithm, effectively reducing sampling burden while maintaining accuracy in calculating apparent reaction rate constants. Kinetic data from these experiments supported the development of a stochastic simulation model to extract valuable mechanistic information. These capabilities were exploited for “scale-up” synthesis by conducting automated reactions in parallel, facilitating reproducible access to highly precise polymeric building blocks and providing a powerful alternative to polycondensation for the synthesis of telechelics by depolymerization. This work demonstrates how the throughput and accuracy of kinetic experiments can be significantly enhanced by synergizing AI and automation, highlighting the significant potential of these tools to transform the practice of fundamental polymer science.