Ïã¸ÛÁùºÏ²ÊÖÐÌØÍø

I am a PhD student at Ïã¸ÛÁùºÏ²ÊÖÐÌØÍø's Centre for Data Intensive Science and Industry, interested in machine learning and galaxy dynamics.

Project title:ÌýDenoise Gaia data with normalizing flow

Research Group:ÌýAstrophysics

Supervisor(s): Dr Jason Sanders

±õ²Ô³Ù°ù´Ç»å³Ü³¦³Ù¾±´Ç²Ô:Ìý

Introduction: I completed my undergraduate degree in Mathematics at the University of Cambridge, followed by a master's in Astrophysics at University College London. Now I am a PhD student at Ïã¸ÛÁùºÏ²ÊÖÐÌØÍø's Centre for Data Intensive Science and Industry, interested in machine learning and galaxy dynamics. I am now working with Dr Jason Sanders focusing on applying generative model normalizing flows to Gaia satellite data to study the Milky Way's structure by denoising density estimation.

---

Project description:ÌýÌý

The Gaia mission’s radial velocity dataset reveals intricate kinematic substructures of Milky Way. But it is corrupted by heterogeneous noise complicating precise density estimation. Traditional methods like Gaussian Mixture Models with extreme deconvolution are computationally expensive and insufficient for accurate reconstructions. In my project, we propose using generative model normalizing flows for denoising density estimation, which transforms a simple base distribution into a complex target distribution through bijective transformations. This method effectively reconstructs high-resolution velocity distributions from noisy mock data and offering a robust tool for studying the Milky Way’s kinematics

First year group project:ÌýASOS --- Learning Graph Representations to Predict Customer Returns in Fashion Retail

Placement:Ìý

---

Ìý

Ìý