PhD Student, University of Delaware
I'm Siddharth Chaini, or Sid for short. I'm currently pursuing my PhD at the Department of Physics and Astronomy, University of Delaware.
My work is at the intersection of computer programming, data science, physics, and astronomy. I'm particularly interested in:
When I'm not working on research, I enjoy watching and playing football (soccer), coding for fun (automating the boring stuff!), and bicycling.
Here are some highlights of the projects I have worked on:
I recently released DistClassiPy, a Python library for a new classifier which can use several different distance metrics for classification. We applied this to light curves of variable stars from the Zwicky Transient Facility (ZTF). You can read more about it in our paper: https://arxiv.org/abs/2403.12120
I recently worked on a project where we compared a Milky Way kinematics model developed using data from the Sloan Digital Sky Survey (SDSS), and verified it with data from Gaia (DR3). You can read more about it in our paper: https://arxiv.org/abs/2406.03541
I worked on improving feature extraction methods for RESSPECT. We explored curve fitting approaches and deep learning algorithms (GP-VAE) to extract features from light curves. You can read more about this on the project page here.
I worked on using deep learning for photometric classification of compact images from the Sloan Digital Sky Survey as galaxies, stars or quasars. You can read more about this work in our paper, here.
For a course project, I worked on a solution for the PLAsTiCC data challenge. Our stacked ensemble of GRU and Dense networks was trained on 7878 light curves and achieved an accuracy of 76.2% on a test set consisting of over 2.5 million light curves.
If you have any questions about my work, are interested in collaborating on a project, or find a bug in my code, please don't hesitate to reach out. You can email me at chaini@udel.edu.