I work on scientific machine learning for process systems engineering: models that combine engineering knowledge with data, and the software that makes them usable. In Data and Intelligent Systems at Princeton University, I build machine learning methods and research software with research groups across disciplines. My aim is to push what models can do while maintaining safety and trust.
Data and Intelligent Systems, Princeton University
Research
All themes-
Hybrid models with physical and qualitative constraints
Models that place engineering knowledge, from balances to qualitative trends, into machine learning.
-
Testing data-driven methods for chemical plants
Frameworks that test learned models and controllers on simulated plants before they reach a real one.
-
Scientific machine learning software
Research software and scalable training workflows, built with research groups across disciplines.
-
Electrochemical systems and separations
Machine learning for fuel cells, hydrogen pumps, and ion-exchange membranes.
News
All news-
Joined Data and Intelligent Systems at Princeton University