AppleCiDEr II: SpectraNet -- A Deep Learning Network for Spectroscopic Data

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xu, Maojie, Sasli, Argyro, Junell, Alexandra, Nunes, Felipe Fontinele, Qin, Yu-Jing, Fremling, Christoffer, Rose, Sam, Laz, Theophile Jegou Du, Border, Benny, Calloch, Antoine Le, Chaudhary, Sushant Sharma, Markoff, Hailey, Raghuvanshi, Avyukt, Rehemtulla, Nabeel, Sollerman, Jesper, Sharma, Yashvi, Sravan, Niharika, Adler, Judy, Chen, Tracy X., Dekany, Richard, Riddle, Reed, Kasliwal, Mansi M., Graham, Matthew J., Coughlin, Michael W.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914141927636992
author Xu, Maojie
Sasli, Argyro
Junell, Alexandra
Nunes, Felipe Fontinele
Qin, Yu-Jing
Fremling, Christoffer
Rose, Sam
Laz, Theophile Jegou Du
Border, Benny
Calloch, Antoine Le
Chaudhary, Sushant Sharma
Markoff, Hailey
Raghuvanshi, Avyukt
Rehemtulla, Nabeel
Sollerman, Jesper
Sharma, Yashvi
Sravan, Niharika
Adler, Judy
Chen, Tracy X.
Dekany, Richard
Riddle, Reed
Kasliwal, Mansi M.
Graham, Matthew J.
Coughlin, Michael W.
author_facet Xu, Maojie
Sasli, Argyro
Junell, Alexandra
Nunes, Felipe Fontinele
Qin, Yu-Jing
Fremling, Christoffer
Rose, Sam
Laz, Theophile Jegou Du
Border, Benny
Calloch, Antoine Le
Chaudhary, Sushant Sharma
Markoff, Hailey
Raghuvanshi, Avyukt
Rehemtulla, Nabeel
Sollerman, Jesper
Sharma, Yashvi
Sravan, Niharika
Adler, Judy
Chen, Tracy X.
Dekany, Richard
Riddle, Reed
Kasliwal, Mansi M.
Graham, Matthew J.
Coughlin, Michael W.
contents Time-domain surveys such as the Zwicky Transient Facility (ZTF) have opened a new frontier in the discovery and characterization of transients. While photometric light curves provide broad temporal coverage, spectroscopic observations remain crucial for physical interpretation and source classification. However, existing spectral analysis methods -- often reliant on template fitting or parametric models -- are limited in their ability to capture the complex and evolving spectra characteristic of such sources, which are sometimes only available at low resolution. In this work, we introduce SpectraNet, a deep convolutional neural network designed to learn robust representations of optical spectra from transients. Our model combines multi-scale convolution kernels and multi-scale pooling to extract features from preprocessed spectra in a hierarchical and interpretable manner. We train and validate SpectraNet on low-resolution time-series spectra obtained from the Spectral Energy Distribution Machine (SEDM) and other instruments, demonstrating state-of-the-art performance in classification. Furthermore, in redshift prediction tasks, SpectraNet achieves a root mean squared relative redshift error of 0.02, highlighting its effectiveness in precise regression tasks as well.
format Preprint
id arxiv_https___arxiv_org_abs_2510_07215
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle AppleCiDEr II: SpectraNet -- A Deep Learning Network for Spectroscopic Data
Xu, Maojie
Sasli, Argyro
Junell, Alexandra
Nunes, Felipe Fontinele
Qin, Yu-Jing
Fremling, Christoffer
Rose, Sam
Laz, Theophile Jegou Du
Border, Benny
Calloch, Antoine Le
Chaudhary, Sushant Sharma
Markoff, Hailey
Raghuvanshi, Avyukt
Rehemtulla, Nabeel
Sollerman, Jesper
Sharma, Yashvi
Sravan, Niharika
Adler, Judy
Chen, Tracy X.
Dekany, Richard
Riddle, Reed
Kasliwal, Mansi M.
Graham, Matthew J.
Coughlin, Michael W.
Instrumentation and Methods for Astrophysics
High Energy Astrophysical Phenomena
Time-domain surveys such as the Zwicky Transient Facility (ZTF) have opened a new frontier in the discovery and characterization of transients. While photometric light curves provide broad temporal coverage, spectroscopic observations remain crucial for physical interpretation and source classification. However, existing spectral analysis methods -- often reliant on template fitting or parametric models -- are limited in their ability to capture the complex and evolving spectra characteristic of such sources, which are sometimes only available at low resolution. In this work, we introduce SpectraNet, a deep convolutional neural network designed to learn robust representations of optical spectra from transients. Our model combines multi-scale convolution kernels and multi-scale pooling to extract features from preprocessed spectra in a hierarchical and interpretable manner. We train and validate SpectraNet on low-resolution time-series spectra obtained from the Spectral Energy Distribution Machine (SEDM) and other instruments, demonstrating state-of-the-art performance in classification. Furthermore, in redshift prediction tasks, SpectraNet achieves a root mean squared relative redshift error of 0.02, highlighting its effectiveness in precise regression tasks as well.
title AppleCiDEr II: SpectraNet -- A Deep Learning Network for Spectroscopic Data
topic Instrumentation and Methods for Astrophysics
High Energy Astrophysical Phenomena
url https://arxiv.org/abs/2510.07215