Research: Machine Learning-Guided Discovery and Optimization of Polymer Electrolytes fo...

Research question: How can machine learning models accelerate the discovery and optimization of polymer electrolytes with enhanced ionic conductivity and stability?

Polymer electrolytes are critical components in electrochemical devices such as batteries, fuel cells, and supercapacitors. Their performance is governed by complex interplay of chemical structure, morphology, and ionic transport properties. Traditional discovery methods rely heavily on experimental trial-and-error, which is both time-consuming and resource-intensive.

Despite advances in high-throughput experimentation and computational chemistry, there remains a significant gap in efficiently navigating the vast chemical space of polymer electrolytes to identify candidates with optimal properties. Recent progress in machine learning (ML) offers promise for data-driven screening, but practical integration with chemical engineering workflows is under-explored.

This research will develop and validate machine learning models to predict key properties (e.g., ionic conductivity, thermal stability) of polymer electrolytes from molecular descriptors and experimental data. The methodology includes literature review, dataset curation, model training, and experimental validation of selected ML-guided candidates. The expected contribution is a robust ML pipeline for guiding polymer electrolyte discovery, with critical assessment of its predictive power.

The project is significant as it bridges chemical engineering and data science, offering scalable approaches to materials discovery. Success could shorten development cycles for next-generation electrochemical devices, impacting both sustainable energy storage and broader process engineering fields.