Throughout my Undergraduate education, I have remained deeply involved in a number of research projects. My primary body of works has been under Prof. Saskia Mordijck on constructing a Machine-Learning pipeline to infer experimental transport conditions in tokamak reactors. This project has allowed me to wear many hats, diving into Computational Modeling, Numerical Methods, High-Performance Computing, Neural Networks, Reinforcement Learning, Uncertainty Quantification, Bayesian Optimization, MCMC, and more.
I have been responsible for nearly all aspects of the project and afforded a high level of independence regarding its direction. I regularly present aspects of this project and its progress to my research group as well as the MIT Neutrals Group under Prof. Jerry Hughes. In addition, I have presented it at APS DPP 2024 and 2025, winning the outstanding poster award both years. I have attached some of the presentation materials for this project below.
I pride myself both in the quality of my research as well as in the effort I put in to communicate my findings with others. I believe that this process is critical to continued progress in science.
In Addition, I worked with Prof. Seth Aubin to construct a microwave interferometer to measure the phase noise in our lab's microwave sources. I was responsible for designing experimental procedures and circuits, running the experiments, analyzing the data, and deciding on which components need to be purchased for the project. I have attached below some of the data analysis notebooks from this project.
I ran well over 100 individual experiments for this project and was able to formulate a clear picture of the noise breakdown present and many circuit layouts for testing specific aspects of this noise.
In addition to these two main projects, I have also been involved in a number of smaller research and personal projects throughout my education including working with numerical simulations of fluids, reinforcement learning agents for game theory, and more.