Scalable Thermoset Informatics Integrated with Autonomous Experimentation for On-Demand Discovery
- 1School of Mechanical Engineering, Georgia Institute of Technology, Atlanta, Georgia 30332, United States.
- 2School of Materials Science and Engineering, Georgia Institute of Technology, Atlanta, Georgia 30332, United States.
- 3School of Computational Science and Engineering, Georgia Institute of Technology, Atlanta, Georgia 30332, United States.
Abstract
As photopolymer additive manufacturing matures, there is an increasing need for on-demand, application-specific materials. A major bottleneck is the limited exploration of the vast design space for new thermoset polymer formulations, which must satisfy both material property requirements and processing constraints. This challenge arises from the combinatorial complexity of formulations and the high cost of experimental evaluation. In this work, we present an end-to-end pipeline that integrates a partial self-driving laboratory (p-SDL) with informatics-driven optimization to discover and validate thermoset acrylate formulations. The pipeline begins with a thermoset acrylate database that consolidates multiple data sources, including in-house experiments, molecular dynamics simulations, and literature data. These data sets are used to train single-task and multitask predictive models, which interface directly with the p-SDL to guide experiments and measure mechanical and processing-related properties. Each component is validated independently and then deployed together to optimize a target elastomeric material with over 90% reduction in human effort. The complete optimization required only ∼40 h of active experimental time, demonstrating rapid identification of formulations that satisfy multiple target properties without exhaustive screening. This work establishes a scalable framework for embedding multifidelity machine learning within laboratory workflows, enabling autonomous, data-driven thermoset formulation discovery.
Related
- Beyond Scalar Objectives: Expert-Feedback-Driven Autonomous Experimentation for Scientific Discovery at the Nanoscale.
- Autonomous Experimentation Enables Rapid Optimization of Photochemical Continuous-Flow Synthesis of Diazaxanthilidene Fluorophores
- Polymer Informatics in the Era of Foundation Models: From Representation to Autonomous Design
- Hierarchical Multi-agent Large Language Model Reasoning for Autonomous Heterogeneous Catalyst Discovery
- Autonomous in-silico inorganic materials discovery via multi-agent physics-aware scientific reasoning
BibTeX
@article{fratarcangeli2026scalable,
title = {{Scalable Thermoset Informatics Integrated with Autonomous Experimentation for On-Demand Discovery}},
author = {Marcus R Fratarcangeli and Ayush Jain and Farzad Gholami and Jiaqi Nie and Anagha Savit and H Jerry Qi and Rampi Ramprasad},
journal = {Chemistry of materials : a publication of the American Chemical Society},
year = {2026},
month = oct,
doi = {10.1021/acs.chemmater.6c01600},
url = {https://europepmc.org/article/PMC/PMC13718556},
note = {CC BY},
}
RIS
TY - JOUR
TI - Scalable Thermoset Informatics Integrated with Autonomous Experimentation for On-Demand Discovery
AU - Marcus R Fratarcangeli
AU - Ayush Jain
AU - Farzad Gholami
AU - Jiaqi Nie
AU - Anagha Savit
AU - H Jerry Qi
AU - Rampi Ramprasad
PY - 2026
DA - 2026/10/09
JO - Chemistry of materials : a publication of the American Chemical Society
DO - 10.1021/acs.chemmater.6c01600
UR - https://europepmc.org/article/PMC/PMC13718556
AB - As photopolymer additive manufacturing matures, there is an increasing need for on-demand, application-specific materials. A major bottleneck is the limited exploration of the vast design space for new thermoset polymer formulations, which must satisfy both material property requirements and processing constraints. This challenge arises from the combinatorial complexity of formulations and the high cost of experimental evaluation. In this work, we present an end-to-end pipeline that integrates a partial self-driving laboratory (p-SDL) with informatics-driven optimization to discover and validate thermoset acrylate formulations. The pipeline begins with a thermoset acrylate database that consolidates multiple data sources, including in-house experiments, molecular dynamics simulations, and literature data. These data sets are used to train single-task and multitask predictive models, which interface directly with the p-SDL to guide experiments and measure mechanical and processing-related properties. Each component is validated independently and then deployed together to optimize a target elastomeric material with over 90% reduction in human effort. The complete optimization required only ∼40 h of active experimental time, demonstrating rapid identification of formulations that satisfy multiple target properties without exhaustive screening. This work establishes a scalable framework for embedding multifidelity machine learning within laboratory workflows, enabling autonomous, data-driven thermoset formulation discovery.
SN - 0897-4756
SN - 1520-5002
ER -