Astrophysics | Data Science
Current focus
I am currently working with the DiRAC Institute at the University of Washington to develop and test Hyrax, an Astro-Machine Learning framework, by looking for anomalous and rare objects in large astronomical datasets.
I'm also a member of the Meg Urry Lab here at Yale, and my research involves doing near-infrared spectroscopy of high-redshift Fermi blazars using Hβ and Mg II λ2800 lines. My previous project (published paper) involved spectroscopy of variable z < 1.5 AGN, using their properties such as mass and brightness to study the black hole-host galaxy mass evolution.
Beyond my research, I serve as a Head of Consulting for Elmseed Consulting and as the Events and Communications Chair for the Yale Astronomical and Space Student Society (YASSS).
Train and benchmark models (CNNs,convolutional autoencoders/DCAE, SimCLR) for Hyrax – an astronomy ML framework – on ~6,000 realistic HSC-simulated IllustrisTNG subhalo images.
Using H-beta and Mg II 2800 line measurements to study high-redshift Fermi blazars and extend the spectroscopic picture of these sources.
Studied variability-selected AGN at z < 1.5, using mass and brightness measurements to examine black hole and host galaxy mass evolution.
A Python CLI for fetching HSC FITS image URLs from IllustrisTNG, downloading and splitting images by filter, and rebuilding enriched catalogs for downstream analysis.
A course project with Abheek Dhawan applying UMAP and HDBSCAN to 1,496 OGLE 2025 microlensing events in order to group light-curve morphologies and flag potentially exotic events without a large labeled training set.
Head of Consulting
I manage 3 teams – enforcing milestones, leading client communication, and overseeing project execution – and also run onboarding and training for new consultants.
Project Chair
Organize and deliver astronomy events including faculty-student dinners, meteor shower and northern lights observing nights, and outreach for local schools.
Bayesian methods, regression, and Python-based analysis of large datasets.
GitHub RepoStatistical-physics approaches to modern machine learning and optimization.
Probabilistic modeling, distributions, central limit theorem, and Markov chains.
Differential equations, linear algebra, and complex analysis for physical modeling.
Fluid dynamics, collisionless dynamics, and radiative processes in astrophysics.
Class Notes