A Framework for Fully Autonomous Design of Materials via Multiobjective Optimization and Active Learning: Challenges and Next Steps
Abstract
In order to deploy machine learning in a real-world self-driving laboratory where data acquisition is costly and there are multiple competing design criteria, systems need to be able to intelligently sample while balancing performance trade-offs and constraints. For these reasons, we present an active learning process based on multiobjective black-box optimization with continuously updated machine learning models. This workflow is built on open-source technologies for real-time data streaming and modular multiobjective optimization software development. We demonstrate a proof of concept for this workflow through the autonomous operation of a continuous-flow chemistry laboratory, which identifies ideal manufacturing conditions for the electrolyte 2,2,2-trifluoroethyl methyl carbonate.
Cite
Text
Chang et al. "A Framework for Fully Autonomous Design of Materials via Multiobjective Optimization and Active Learning: Challenges and Next Steps." ICLR 2023 Workshops: ML4Materials, 2023.Markdown
[Chang et al. "A Framework for Fully Autonomous Design of Materials via Multiobjective Optimization and Active Learning: Challenges and Next Steps." ICLR 2023 Workshops: ML4Materials, 2023.](https://mlanthology.org/iclrw/2023/chang2023iclrw-framework/)BibTeX
@inproceedings{chang2023iclrw-framework,
title = {{A Framework for Fully Autonomous Design of Materials via Multiobjective Optimization and Active Learning: Challenges and Next Steps}},
author = {Chang, Tyler H and Elias, Jakob R and Wild, Stefan M. and Chaudhuri, Santanu and Libera, Joseph A.},
booktitle = {ICLR 2023 Workshops: ML4Materials},
year = {2023},
url = {https://mlanthology.org/iclrw/2023/chang2023iclrw-framework/}
}