Machine learning in astronomy

 

Show simple item record

dc.contributor.advisor Bassett, Bruce en_ZA
dc.contributor.author Du Buisson, Lise en_ZA
dc.date.accessioned 2015-12-02T04:04:21Z
dc.date.available 2015-12-02T04:04:21Z
dc.date.issued 2015 en_ZA
dc.identifier.citation Du Buisson, L. 2015. Machine learning in astronomy. University of Cape Town. en_ZA
dc.identifier.uri http://hdl.handle.net/11427/15502
dc.description.abstract The search to find answers to the deepest questions we have about the Universe has fueled the collection of data for ever larger volumes of our cosmos. The field of supernova cosmology, for example, is seeing continuous development with upcoming surveys set to produce a vast amount of data that will require new statistical inference and machine learning techniques for processing and analysis. Distinguishing between real objects and artefacts is one of the first steps in any transient science pipeline and, currently, is still carried out by humans - often leading to hand scanners having to sort hundreds or thousands of images per night. This is a time-consuming activity introducing human biases that are extremely hard to characterise. To succeed in the objectives of future transient surveys, the successful substitution of human hand scanners with machine learning techniques for the purpose of this artefact-transient classification therefore represents a vital frontier. In this thesis we test various machine learning algorithms and show that many of them can match the human hand scanner performance in classifying transient difference g, r and i-band imaging data from the SDSS-II SN Survey into real objects and artefacts. Using principal component analysis and linear discriminant analysis, we construct a grand total of 56 feature sets with which to train, optimise and test a Minimum Error Classifier (MEC), a naive Bayes classifier, a k-Nearest Neighbours (kNN) algorithm, a Support Vector Machine (SVM) and the SkyNet artificial neural network. en_ZA
dc.language.iso eng en_ZA
dc.subject.other Mathematics and Applied Mathematics en_ZA
dc.title Machine learning in astronomy en_ZA
dc.type Master Thesis
uct.type.publication Research en_ZA
uct.type.resource Thesis en_ZA
dc.publisher.institution University of Cape Town
dc.publisher.faculty Faculty of Science en_ZA
dc.publisher.department Department of Mathematics and Applied Mathematics en_ZA
dc.type.qualificationlevel Masters
dc.type.qualificationname MSc en_ZA
uct.type.filetype Text
uct.type.filetype Image
dc.identifier.apacitation Du Buisson, L. (2015). <i>Machine learning in astronomy</i>. (Thesis). University of Cape Town ,Faculty of Science ,Department of Mathematics and Applied Mathematics. Retrieved from http://hdl.handle.net/11427/15502 en_ZA
dc.identifier.chicagocitation Du Buisson, Lise. <i>"Machine learning in astronomy."</i> Thesis., University of Cape Town ,Faculty of Science ,Department of Mathematics and Applied Mathematics, 2015. http://hdl.handle.net/11427/15502 en_ZA
dc.identifier.vancouvercitation Du Buisson L. Machine learning in astronomy. [Thesis]. University of Cape Town ,Faculty of Science ,Department of Mathematics and Applied Mathematics, 2015 [cited yyyy month dd]. Available from: http://hdl.handle.net/11427/15502 en_ZA
dc.identifier.ris TY - Thesis / Dissertation AU - Du Buisson, Lise AB - The search to find answers to the deepest questions we have about the Universe has fueled the collection of data for ever larger volumes of our cosmos. The field of supernova cosmology, for example, is seeing continuous development with upcoming surveys set to produce a vast amount of data that will require new statistical inference and machine learning techniques for processing and analysis. Distinguishing between real objects and artefacts is one of the first steps in any transient science pipeline and, currently, is still carried out by humans - often leading to hand scanners having to sort hundreds or thousands of images per night. This is a time-consuming activity introducing human biases that are extremely hard to characterise. To succeed in the objectives of future transient surveys, the successful substitution of human hand scanners with machine learning techniques for the purpose of this artefact-transient classification therefore represents a vital frontier. In this thesis we test various machine learning algorithms and show that many of them can match the human hand scanner performance in classifying transient difference g, r and i-band imaging data from the SDSS-II SN Survey into real objects and artefacts. Using principal component analysis and linear discriminant analysis, we construct a grand total of 56 feature sets with which to train, optimise and test a Minimum Error Classifier (MEC), a naive Bayes classifier, a k-Nearest Neighbours (kNN) algorithm, a Support Vector Machine (SVM) and the SkyNet artificial neural network. DA - 2015 DB - OpenUCT DP - University of Cape Town LK - https://open.uct.ac.za PB - University of Cape Town PY - 2015 T1 - Machine learning in astronomy TI - Machine learning in astronomy UR - http://hdl.handle.net/11427/15502 ER - en_ZA


Files in this item

This item appears in the following Collection(s)

Show simple item record