PhD Student, University of Delaware
I am Siddharth Chaini, or Sid for short - a PhD student at the Department of Physics and Astronomy, University of Delaware.
I love to combine my passion for computer programming and data science with my background in physics and astronomy. I am chiefly interested in the following topics:
In my free time, I watch and play football (soccer), code for fun (automate the boring stuff!) and play role-playing video games!
Here are some highlights of the projects I have worked on:
I am currently working with Prof. Federica Bianco and Prof. Ashish Mahabal on the classification using data from the Zwicky Transient Facility (ZTF) through machine learning and distance metrics. We are in the process of publishing a paper on this.
I worked with Dr. Johann Cohen-Tanugi, on the project RESSPECT. We looked at improving feature extraction methods for RESSPECT, by looking at curve fitting approaches, as well as deep learning algorithms (GP-VAE) to extract features from light curves.
I worked on a project Prof. Ajit Kembhavi, Dr. Vivek M. and Dr. Kaushal Sharma. We used deep learning for photometric classification of of compact images from the Sloan Digital Sky Survey as galaxies, stars or quasars on the basis of their images. You can read more about this work in our paper, here.
My teammate and I worked on developing a solution for the PLAsTiCC 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.
My team and I implemented a Monte Carlo algorithm to study the thermodynamic properties of ice. We computed the residual entropy and identified a phase transition.
Please reach out to me if you have any questions about my work, are interested in collaborating on a project, or find a bug in my code. My email id is chaini@udel.edu.