I am a Doctor of Philosophy (PhD) candidate advised by Prof. Kumar Vemaganti at the University of Cincinnati in the computational mechanics field. My research focuses on scientific machine learning with an emphasis on its application to solid mechanics problems. I have investigated data-driven learning using a data-efficient Gaussian process (GP) as a surrogate in the Bayesian optimization framework to solve design optimization problems. I have developed an energy-based machine learning approach using a neural network as a surrogate to solve nonlinear hyperelastic multistable structures and phase-field plasticity problems. I am particularly interested in identifying the advantages and shortcomings of PIML over well-established finite element approaches.
I also work as a Graduate research assistant on research projects in collaboration with Procter & Gamble (P&G) at the UC Simulation Center. My work involves developing an accurate finite element model of paper at the fiber scale level. I am also responsible for developing performance tests for determining the strength of the paper.
I recently passed my PhD candidacy defense and am actively looking for job opportunities in the area of numerical development and scientific machine learning. I earned my Master of Science (M.S.) in mechanical engineering in 2020 from the University of Cincinnati, where my research was focused on developing an efficient Bayesian optimization algorithm to discover optimal design solutions for origami-inspired folding structures.