{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/quasarnet-human-level-spectral-classification","title":"QuasarNET: Human-level spectral classification and redshifting with Deep Neural Networks","arxiv_id":"1808.09955","date":"2018-08-29","proceeding":null,"authors":["Nicolas Busca","Christophe Balland"],"abstract":"We introduce QuasarNET, a deep convolutional neural network that performs\nclassification and redshift estimation of astrophysical spectra with\nhuman-expert accuracy. We pose these two tasks as a \\emph{feature detection}\nproblem: presence or absence of spectral features determines the class, and\ntheir wavelength determines the redshift, very much like human-experts proceed.\nWhen ran on BOSS data to identify quasars through their emission lines,\nQuasarNET defines a sample $99.51\\pm0.03$\\% pure and $99.52\\pm0.03$\\% complete,\nwell above the requirements of many analyses using these data. QuasarNET\nsignificantly reduces the problem of line-confusion that induces catastrophic\nredshift failures to below 0.2\\%. We also extend QuasarNET to classify spectra\nwith broad absorption line (BAL) features, achieving an accuracy of\n$98.0\\pm0.4$\\% for recognizing BAL and $97.0\\pm0.2$\\% for rejecting non-BAL\nquasars. QuasarNET is trained on data of low signal-to-noise and medium\nresolution, typical of current and future astrophysical surveys, and could be\neasily applied to classify spectra from current and upcoming surveys such as\neBOSS, DESI and 4MOST.","url_abs":"http://arxiv.org/abs/1808.09955v1","url_pdf":"http://arxiv.org/pdf/1808.09955v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"quasarnet-human-level-spectral-classification","repo_url":"https://github.com/ngbusca/QuasarNET","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"classification","task_name":"General Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1808.09955","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}