Research
Research Interests
Digital twins
Optimization under uncertainty (OUU)
Uncertainty quantification (UQ)
Surrogate-based design optimization
Use-inspired research
Multifidelity methods
Machine learning in Engineering
Monte Carlo methods
Risk analysis
Coupled multidisciplinary systems
Research Summary
My research interests span computational science and scientific machine learning for optimization, uncertainty quantification, optimization under uncertainty, and digital twins. I am currently developing new multifidelity methods for uncertainty quantification and optimization under uncertainty. I create methods for utilizing multiple information sources in various use-inspired work to make optimization and uncertainty quantification feasible.
My doctoral research mostly focused on implications of cost of evaluating a system in Bayesian optimization. I also worked on designing flapping wing of micro air vehicle tackling the excessive cost of experiments used to estimate thrust production through parallel Bayesian optimization. During my PhD, I spent the summer of 2013 as a visiting researcher at Ecole Nationale Superieure des mines de Saint-Etienne in France working on estimating feasibility of a design under complex constraints using multiple surrogates and ROC curves.