I am a PhD Student in the Computational Science, Engineering, and Mathematics program at the University of Texas at Austin with co-advisors Prof. Karen Willcox and Dr. Anirban Chaudhuri. My research has revolved around developing fast and data-efficient multi-fidelity surrogate models with applications in inverse problems and optimization. I have had the great privilege to be funded by and contribute to the following projects during my PhD: DARPA ASKEM & ARPA-E LOADS.
Multifidelity linear regression for scientific machine learning from scarce data
Proposed a multifidelity linear regression approach that significantly reduces model variance and improves robustness in data-scarce scenarios.
Read More
Multifidelity Linear Regression (MFLR) Demo
Live interactive visualization of the surface pressure field upon a hypersonic vehicle, calculated on-the-fly by MFLR methods.
Read More
LectureGPT - an open-source GPT-3 based AI-assistant
A LLM is fine-tuned on course lecture notes and retrieval augmented generation is used to create a conversational AI-assistant for students to ask specific questions about their course material.
Read More
Automating Scientific Knowledge Extraction and Modeling (ASKEM)
DARPA’s Automating Scientific Knowledge Extraction and Modeling (ASKEM) program uses AI approaches and tools to create, sustain, and enhance complex models and simulators.
Read More
Projection-based multifidelity linear regression for data-poor applications
Developed multifidelity linear regression methods to enhance predictive accuracy in data-poor, high-dimensional applications, showing significant improvement on a hypersonic vehicle surface pressure prediction example.
Read More
Improving Neural Network Efficiency With Multifidelity and Dimensionality Reduction Techniques
Developed projection-enabled multifidelity neural networks to reduce computational costs for a 2D aerodynamic airfoil inverse design problem.
Read More
