{"@type": "dcat:Dataset", "accessLevel": "public", "accrualPeriodicity": "irregular", "bureauCode": ["026:00"], "contactPoint": {"@type": "vcard:Contact", "fn": "Elizabeth Foughty", "hasEmail": "mailto:elizabeth.a.foughty@nasa.gov"}, "description": "DATA MINING THE GALAXY ZOO MERGERS\r\n\r\nSTEVEN BAEHR*, ARUN VEDACHALAM*, KIRK BORNE*, AND DANIEL SPONSELLER*\r\n\r\nAbstract. Collisions between pairs of galaxies usually end in the coalescence (merger) of the two\r\ngalaxies. Collisions and mergers are rare phenomena, yet they may signal the ultimate fate of\r\nmost galaxies, including our own Milky Way. With the onset of massive collection of astronomical\r\ndata, a computerized and automated method will be necessary for identifying those colliding\r\ngalaxies worthy of more detailed study. This project researches methods to accomplish that goal.\r\nAstronomical data from the Sloan Digital Sky Survey (SDSS) and human-provided classifications\r\non merger status from the Galaxy Zoo project are combined and processed with machine learning\r\nalgorithms. The goal is to determine indicators of merger status based solely on discovering those\r\nautomated pipeline-generated attributes in the astronomical database that correlate most strongly\r\nwith the patterns identified through visual inspection by the Galaxy Zoo volunteers. In the end,\r\nwe aim to provide a new and improved automated procedure for classification of collisions and\r\nmergers in future petascale astronomical sky surveys. Both information gain analysis (via the\r\nC4.5 decision tree algorithm) and cluster analysis (via the Davies-Bouldin Index) are explored as\r\ntechniques for finding the strongest correlations between human-identified patterns and existing\r\ndatabase attributes. Galaxy attributes measured in the SDSS green waveband images are found to\r\nrepresent the most influential of the attributes for correct classification of collisions and mergers.\r\nOnly a nominal information gain is noted in this research, however, there is a clear indication of\r\nwhich attributes contribute so that a direction for further study is apparent.", "distribution": [{"@type": "dcat:Distribution", "description": "DATA MINING THE GALAXY ZOO MERGERS", "downloadURL": "https://c3.nasa.gov/dashlink/static/media/publication/Paper_11_.pdf", "format": "PDF", "mediaType": "application/pdf", "title": "Paper 11 .pdf"}], "identifier": "DASHLINK_233", "issued": "2010-10-13", "keyword": ["ames", "dashlink", "nasa"], "landingPage": "https://c3.nasa.gov/dashlink/resources/233/", "modified": "2025-03-31", "programCode": ["026:029"], "publisher": {"@type": "org:Organization", "name": "Dashlink"}, "title": "DATA MINING THE GALAXY ZOO MERGERS"}