AI-guided Autonomous Workflows Accelerate Kinetic Analysis of Polymer Depolymerization

Read full text Summarise with VIRAT
Authors: Tomonori Saito, Nicholas J. Galan, Britney Baez, Ju-An Kim, Beibei Yao, Nduka D. Ogbonna, Dishner, Jared I. Bowman, Jesse McGaha, Ankit Shrivastava, Stephen J. DeWitt, Sheng Dai
+2 more Craig A. Bridges, Jeffrey C. Foster
Cited by: 0
References: 34

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

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.

Fields of Study & Subjects

Machine Learning in Materials Science Advanced Polymer Synthesis and Characterization Thermal and Kinetic Analysis

Publication details

Journal / source
Research Square
Publication date
31 March 2026
Language
EN
Document type
Preprint