Discovering Rare Ca II Quasar Absorption Lines with a Neural Network
CSEF · 2023 Physics & Astronomy Honorable_mention Award
Overview
As we continue to understand the origin of the universe, the study of galaxy evolution has become essential to reconstruct the mechanisms that led to our present-day galaxies. Quasar absorption lines (QALs), created when the light of bright celestial objects passes through the gas of distant galaxies, detect gas components from the early to the recent universe, making them crucial in the study of galaxy evolution. Ca II QALs, in particular, are important for studying both star formation and recent galaxies. However, existing catalogs are extremely limited because traditional detection methods are inefficient, leaving important models and theories unconfirmed. In this study, I developed an accurate and efficient approach to search for Ca II QALs using deep learning. I created simulation data by inserting artificial Ca II QALs onto spectra from the Sloan Digital Sky Survey (SDSS) for my training set while using an existing Ca II QAL catalog for my test set. I also designed a novel preprocessing method aimed at discovering weak Ca II QALs. My solution achieved an accuracy of 96% on the test dataset and transformed a process that used to take days into one that only takes a fraction of a second. My trained neural network model was applied to SDSS’s Data Releases 7, 12, and 14, which resulted in the discovery of 542 brand-new Ca II QALs, the largest catalog ever discovered. My approach can also be applied to the search of other QALs, opening up the field for ground-breaking research about galaxy evolution.
Source coverage
This record comes from a published award list, not a complete project archive. Its abstract comes from CSEF's public project showcase as archived by the Internet Archive before judging (https://web.archive.org/web/20230401224130/https://ca-csef.zfairs.com/showcase/ShowcaseInfo?f=838e60b7-ea75-46e8-865c-fde4864244b3); the version presented may differ.
Awards (1)
- Category Award: HM
Competition history
- CSEF 2023
Resources
Related projects
ISEF · 2022
Discovering Extremely Rare Neutral Carbon Absorbers in Intergalactic Medium Using Machine Learning
ISEF · 2025
QuasarCodex: Quantifying AGN Feedback in High-Redshift Quasars Through Outflow Kinematics
ISEF · 2026
Discovering Hidden Galaxy Populations in TNG100-1 With Unsupervised Autoencoder Learning
JSHS · 2022
A Novel Deep Learning/Machine Learning Hybrid Technique for Automatic Classification of Nebulae
ISEF · 2022
Analysis of Ring Galaxies Detected Using Deep Learning With Real and Simulated Data
ISEF · 2018
Challenging Limitations: Using Deep Learning, Time Series Analysis, and Statistical Methods for Noise Reduction to Develop an Innovative Approach to Exoplanet Candidate Detection Using Earth-Based Telescopes
CSEF · 2023
Finding Galaxies Beyond: Vision Transformer Based Gravitational Lens Search Model Using Synthetic Data
ISEF · 2025
Discovery of the First Double Exocomet Using an Automated Deep Learning Convolutional Neural Network
Closest projects by meaning, across every fair and year in the corpus.
Browse more like this
Source: California Science & Engineering Fair public projects