MSc thesis presentation - Zhuoting Xie

Name:  Zhuoting Xie

Date:   Jul 30 2024

Time:   2-3pm

Location:   ICCS 238

Supervisor(s):  Kwang Moo Yi, Sébastien Fabbro

Title: Generative Spectra Modelling for Galaxy Redshift Estimation

Abstract:

Knowledge of galaxy distance is important for cosmological studies. Re- cent deep learning-based approaches may not leverage the full potential of the neural network. We propose a generative model to reconstruct 1D elec- tromagnetic spectra with application to estimate astronomical redshift. The generative model is an auto-decoding neural field network. We represent each spectrum as a high-dimensional embedding which is converted to spectra re- construction by the following decoder. We optimize the decoder in restframe simultaneously with the embedding by maximizing the structural similarity between the reconstructed and the observed spectra. We then train a clas- sifier based on the reconstructed spectra for redshift classification.

During inference, we fit the auto-decoder to the test spectra and then use the classifier to estimate redshift. Compared with a regressor, our classification model features a simplified optimization surface. We combine spectroscopic data from the zCOSMOS, the DEIMOS, and the VIPERS surveys as our dataset. We split the data into training and testing data and outperform the baseline by 0.6% on test redshift accuracy.