Polymer Informatics: Algorithmic Advances & Materials Design

Rampi Ramprasad

Georgia Institute of Technology

http://ramprasad.mse.gatech.edu

Polymers display extraordinary diversity in their chemistry, structure, and applications. However, finding the ideal polymer possessing the right combination of properties for a given application is non-trivial as the chemical space of polymers is practically infinite. This daunting search problem can be mitigated by surrogate models, trained using machine learning algorithms on available property data, that can make instantaneous predictions of polymer properties. I will present versatile, interpretable, and scalable schemes to build such predictive models. Our ‘‘multi-task learning’’ approach efficiently, effectively, and simultaneously learns and predicts multiple polymer properties. It is thus a powerful tool to solve “forward materials problems”, i.e., property predictions. I will also discuss new approaches to solve “inverse materials problems”, i.e., identifying materials that satisfy target property criteria. These forward and inverse method developments are expected to have a significant impact on data-driven materials discovery, as will be illustrated using a few examples.

[1] Rohit Batra, Le Song and Rampi Ramprasad, “Emerging materials intelligence ecosystems propelled by machine learning”, Nature Reviews Materials (2020).

[2] Christopher Kuenneth, Arunkumar Chitteth Rajan, Huan Tran, Lihua Chen, Chiho Kim, and Rampi Ramprasad, “Polymer informatics with multi-task learning”, Patterns (2021)

[3] Rishi Gurnani, Deepak Kamal, Huan Tran, Harikrishna Sahu, Kenny Scharm, Usman Ashraf and Rampi Ramprasad, “polyG2G: A Novel Machine Learning Algorithm Applied to the Generative Design of Polymer Dielectrics”, Chemistry of Materials (2021).

[4] Christopher Kuenneth and Rampi Ramprasad, “polyBERT: A chemical language model to enable fully machine-driven ultrafast polymer informatics”, Nature Communications (2023).

[5] Rishi Gurnani, Christopher Kuenneth, Aubrey Toland and Rampi Ramprasad, “Polymer informatics at-scale with multitask graph neural networks”, Chemistry of Materials (2023).