Saved in:
Bibliographic Details
Main Authors: Chunduri, Krishna, Mahesh, Mithun
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2310.16304
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915028037271552
author Chunduri, Krishna
Mahesh, Mithun
author_facet Chunduri, Krishna
Mahesh, Mithun
contents Data-driven approaches play a crucial role in space computing, and our paper focuses on analyzing data to learn more about celestial objects. Photometric redshift, a measure of the shift of light towards the red part of the spectrum, helps determine the distance of celestial objects. This study used a dataset from the Sloan Digital Sky Survey (SDSS) with five magnitudes alongside their corresponding redshift labels. Traditionally, redshift prediction relied on spectral distribution templates (SEDs), which, though effective, are costly and limited, especially for large datasets. This paper explores data-driven methodologies instead of SEDs. By employing a decision tree regressor and a fully connected neural network (FCN), we found that the FCN outperforms the decision tree regressor in RMS. The results show that data-driven estimation is a valuable tool for astronomical surveys. With the adaptability to complement previous methods, FCNs will reshape the field of redshift estimation.
format Preprint
id arxiv_https___arxiv_org_abs_2310_16304
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Deep Learning Approach to Photometric Redshift Estimation
Chunduri, Krishna
Mahesh, Mithun
Instrumentation and Methods for Astrophysics
Data-driven approaches play a crucial role in space computing, and our paper focuses on analyzing data to learn more about celestial objects. Photometric redshift, a measure of the shift of light towards the red part of the spectrum, helps determine the distance of celestial objects. This study used a dataset from the Sloan Digital Sky Survey (SDSS) with five magnitudes alongside their corresponding redshift labels. Traditionally, redshift prediction relied on spectral distribution templates (SEDs), which, though effective, are costly and limited, especially for large datasets. This paper explores data-driven methodologies instead of SEDs. By employing a decision tree regressor and a fully connected neural network (FCN), we found that the FCN outperforms the decision tree regressor in RMS. The results show that data-driven estimation is a valuable tool for astronomical surveys. With the adaptability to complement previous methods, FCNs will reshape the field of redshift estimation.
title Deep Learning Approach to Photometric Redshift Estimation
topic Instrumentation and Methods for Astrophysics
url https://arxiv.org/abs/2310.16304