CSST Slitless Spectra: Target Detection and Classification with YOLO

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhou, Yingying, Liu, Chao, Tian, Hao, Zhang, Xin, Li, Nan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911236463001600
author Zhou, Yingying
Liu, Chao
Tian, Hao
Zhang, Xin
Li, Nan
author_facet Zhou, Yingying
Liu, Chao
Tian, Hao
Zhang, Xin
Li, Nan
contents Addressing the spatial uncertainty and spectral blending challenges in CSST slitless spectroscopy, we present a deep learning-driven, end-to-end framework based on the You Only Look Once (YOLO) models. This approach directly detects, classifies, and analyzes spectral traces from raw 2D images, bypassing traditional, error-accumulating pipelines. YOLOv5 effectively detects both compact zero-order and extended first-order traces even in highly crowded fields. Building on this, YOLO11 integrates source classification (star/galaxy) and discrete astrophysical parameter estimation (e.g., redshift bins), showcasing complete spectral trace analysis without other manual preprocessing. Our framework processes large images rapidly, learning spectral-spatial features holistically to minimize errors. We achieve high trace detection precision (YOLOv5) and demonstrate successful quasar identification and binned redshift estimation (YOLO11). This study establishes machine learning as a paradigm shift in slitless spectroscopy, unifying detection, classification, and preliminary parameter estimation in a scalable system. Future research will concentrate on direct, continuous prediction of astrophysical parameters from raw spectral traces.
format Preprint
id arxiv_https___arxiv_org_abs_2510_24087
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CSST Slitless Spectra: Target Detection and Classification with YOLO
Zhou, Yingying
Liu, Chao
Tian, Hao
Zhang, Xin
Li, Nan
Instrumentation and Methods for Astrophysics
Astrophysics of Galaxies
Addressing the spatial uncertainty and spectral blending challenges in CSST slitless spectroscopy, we present a deep learning-driven, end-to-end framework based on the You Only Look Once (YOLO) models. This approach directly detects, classifies, and analyzes spectral traces from raw 2D images, bypassing traditional, error-accumulating pipelines. YOLOv5 effectively detects both compact zero-order and extended first-order traces even in highly crowded fields. Building on this, YOLO11 integrates source classification (star/galaxy) and discrete astrophysical parameter estimation (e.g., redshift bins), showcasing complete spectral trace analysis without other manual preprocessing. Our framework processes large images rapidly, learning spectral-spatial features holistically to minimize errors. We achieve high trace detection precision (YOLOv5) and demonstrate successful quasar identification and binned redshift estimation (YOLO11). This study establishes machine learning as a paradigm shift in slitless spectroscopy, unifying detection, classification, and preliminary parameter estimation in a scalable system. Future research will concentrate on direct, continuous prediction of astrophysical parameters from raw spectral traces.
title CSST Slitless Spectra: Target Detection and Classification with YOLO
topic Instrumentation and Methods for Astrophysics
Astrophysics of Galaxies
url https://arxiv.org/abs/2510.24087