Anushka Doke PhD Student at UMass Dartmouth

Research

Detection and reconstruction of GWs from core-collapse supernovae

Advisors: Dr. Elena Cuoco (Scuola Normale Superiore and the European Gravitational Observatory (EGO), Italy), Dr. Alberto Iess (Scuola Normale Superiore, Italy)
Core-collapse supernovae (CCSNe) are a type of burst signals that have eluded detection so far, and a significant effort is therefore being put into achieving a detection in coming years. Compared to binary mergers, core-collapse supernovae cannot be modelled precisely, and it is, therefore, impossible to apply classical matched filter techniques for detection and analysis. In this project, I utilized a wavelet-based detection pipeline, the Wavelet Detection Filter (WDF), to generate event triggers. I developed a clustering algorithm to group triggers associated with a single event. Using WDF parameters, I successfully reconstructed the injected signal with a good accuracy. My Master's thesis can be found here.

Multiclass Classification for Standard Model Processes

Advisor: Prof. Sourabh Dube (IISER Pune)
I worked on a research project involving the development of a complex artificial neural network, which incorporated 24 input variables like missing transverse energy and the count of b-jets. My investigation primarily revolved around utilizing CMS data from 2017 and 2018, specifically focusing on events characterized by multilepton final states. With the neural network I created, I was able to categorize these events into three Standard Model processes: ZZ, WZ, and the ttZ process. By studying the output distribution of the network, I gained insights into the complex relationships among the input variables.

Convolutional neural networks for particle track classification

Advisor: Prof. Sourabh Dube (IISER Pune)
I was tasked with reproducing work from a previous Master's thesis. Using a toy detector model, I generated two sets of images pertaining to signal and background. My aim was to train a convolutional neural network to classify between these two classes. Prior to this, I designed and trained a binary neural network to distinguish Drell-Yan and ttbar processes.