~ / research

Research

Harnessing the power of artificial intelligence and machine learning in fields where data is scarce or costly.

focus areas
01

Physico-Chemical Representations

Integrating domain knowledge and physico-chemical insights into material representations to build more robust and interpretable ML models.

feature-engineeringdomain-knowledge
02

Transfer & Active Learning

Advanced training techniques that minimize the need for large labeled datasets—crucial where data generation is expensive.

transfer-learningactive-learning
03

Interpretable AI Models

Models that uncover structure–property relationships, translating data into actionable insights for hypothesis-driven materials design.

explainable-aistructure-property
04

Accelerated Discovery

Tools that enable AI-guided experimentation to accelerate the design cycle of functional materials for energy applications.

automationhigh-throughput
See publications →