Matches in SemOpenAlex for { <https://semopenalex.org/work/W2989628531> ?p ?o ?g. }
- W2989628531 endingPage "A154" @default.
- W2989628531 startingPage "A154" @default.
- W2989628531 abstract "Classification will be an important first step for upcoming surveys that will detect billions of new sources such as LSST and Euclid, as well as DESI, 4MOST and MOONS. The application of traditional methods of model fitting and colour-colour selections will face significant computational constraints, while machine-learning (ML) methods offer a viable approach to tackle datasets of that volume. While supervised learning methods can perform very well for classification tasks, the creation of representative and accurate training sets is a resource and time consuming task. We present a viable alternative using an unsupervised ML method to separate stars, galaxies and QSOs using photometric data. The heart of our work uses HDBSCAN to find the star, galaxy and QSO clusters in a multidimensional colour space. We optimized the hyperparameters and input attributes of three separate HDBSCAN runs, each to select a particular object class, and thus treat the output of each separate run as a binary classifier. We subsequently consolidate the output to give our final classifications, optimized on their F1 scores. We explore the use of Random Forest and PCA as part of the pre-processing stage for feature selection and dimensionality reduction. Using our dataset of 50,000 spectroscopically labelled objects we obtain an F1 score of 98.9, 98.9 and 93.13 respectively for star, galaxy and QSO selection using our unsupervised learning method. We find that careful attribute selection is a vital part of accurate classification with HDBSCAN. We applied our classification to a subset of the SDSS spectroscopic catalogue and demonstrate the potential of our approach in correcting misclassified spectra useful for DESI and 4MOST. Finally, we create a multiwavelength catalogue of 2.7 million sources using the KiDS, VIKING and ALLWISE surveys and publish corresponding classifications and photometric redshifts." @default.
- W2989628531 created "2019-12-05" @default.
- W2989628531 creator A5002975086 @default.
- W2989628531 creator A5051423042 @default.
- W2989628531 date "2020-01-01" @default.
- W2989628531 modified "2023-09-27" @default.
- W2989628531 title "Unsupervised star, galaxy, QSO classification" @default.
- W2989628531 cites W1491925085 @default.
- W2989628531 cites W151377110 @default.
- W2989628531 cites W1761970395 @default.
- W2989628531 cites W1924655545 @default.
- W2989628531 cites W1925373677 @default.
- W2989628531 cites W1943306457 @default.
- W2989628531 cites W1967876247 @default.
- W2989628531 cites W1972726488 @default.
- W2989628531 cites W1979503956 @default.
- W2989628531 cites W1983961944 @default.
- W2989628531 cites W1988123625 @default.
- W2989628531 cites W1993283828 @default.
- W2989628531 cites W2013702926 @default.
- W2989628531 cites W2018489450 @default.
- W2989628531 cites W2023037133 @default.
- W2989628531 cites W2026154763 @default.
- W2989628531 cites W2029912483 @default.
- W2989628531 cites W2052937506 @default.
- W2989628531 cites W2093190121 @default.
- W2989628531 cites W2100185260 @default.
- W2989628531 cites W2111817932 @default.
- W2989628531 cites W2112193291 @default.
- W2989628531 cites W2127138952 @default.
- W2989628531 cites W2130638402 @default.
- W2989628531 cites W2135375759 @default.
- W2989628531 cites W2142238829 @default.
- W2989628531 cites W2142955287 @default.
- W2989628531 cites W2148719886 @default.
- W2989628531 cites W2153478568 @default.
- W2989628531 cites W2155653793 @default.
- W2989628531 cites W2157917411 @default.
- W2989628531 cites W2162125418 @default.
- W2989628531 cites W2167635287 @default.
- W2989628531 cites W2168912860 @default.
- W2989628531 cites W2375984290 @default.
- W2989628531 cites W2585129687 @default.
- W2989628531 cites W2601243251 @default.
- W2989628531 cites W2603624303 @default.
- W2989628531 cites W2608232290 @default.
- W2989628531 cites W2750551525 @default.
- W2989628531 cites W2864116548 @default.
- W2989628531 cites W2911964244 @default.
- W2989628531 cites W2920804737 @default.
- W2989628531 cites W2935751639 @default.
- W2989628531 cites W2951699563 @default.
- W2989628531 cites W2968961343 @default.
- W2989628531 cites W3098640821 @default.
- W2989628531 cites W3099110583 @default.
- W2989628531 cites W3099268282 @default.
- W2989628531 cites W3100107773 @default.
- W2989628531 cites W3100901804 @default.
- W2989628531 cites W3100939326 @default.
- W2989628531 cites W3101542025 @default.
- W2989628531 cites W3104025419 @default.
- W2989628531 cites W3104276331 @default.
- W2989628531 cites W3105205770 @default.
- W2989628531 cites W3105442080 @default.
- W2989628531 cites W3105733428 @default.
- W2989628531 cites W3123158482 @default.
- W2989628531 cites W4240017161 @default.
- W2989628531 cites W4247359480 @default.
- W2989628531 doi "https://doi.org/10.1051/0004-6361/201936648" @default.
- W2989628531 hasPublicationYear "2020" @default.
- W2989628531 type Work @default.
- W2989628531 sameAs 2989628531 @default.
- W2989628531 citedByCount "26" @default.
- W2989628531 countsByYear W29896285312021 @default.
- W2989628531 countsByYear W29896285312022 @default.
- W2989628531 countsByYear W29896285312023 @default.
- W2989628531 crossrefType "journal-article" @default.
- W2989628531 hasAuthorship W2989628531A5002975086 @default.
- W2989628531 hasAuthorship W2989628531A5051423042 @default.
- W2989628531 hasBestOaLocation W29896285311 @default.
- W2989628531 hasConcept C119857082 @default.
- W2989628531 hasConcept C121332964 @default.
- W2989628531 hasConcept C153180895 @default.
- W2989628531 hasConcept C154945302 @default.
- W2989628531 hasConcept C169258074 @default.
- W2989628531 hasConcept C2776968204 @default.
- W2989628531 hasConcept C33024259 @default.
- W2989628531 hasConcept C41008148 @default.
- W2989628531 hasConcept C44870925 @default.
- W2989628531 hasConcept C70518039 @default.
- W2989628531 hasConcept C8642999 @default.
- W2989628531 hasConcept C95623464 @default.
- W2989628531 hasConcept C98444146 @default.
- W2989628531 hasConceptScore W2989628531C119857082 @default.
- W2989628531 hasConceptScore W2989628531C121332964 @default.
- W2989628531 hasConceptScore W2989628531C153180895 @default.
- W2989628531 hasConceptScore W2989628531C154945302 @default.
- W2989628531 hasConceptScore W2989628531C169258074 @default.