Galaxy Zoo: Reproducing Galaxy Morphologies Via Machine Learning
We present morphological classifications obtained using machine learning for objects in SDSS DR6 that have been classified by Galaxy Zoo into three classes, namely early types, spirals and point sources/artifacts. An artificial neural network is trained on a subset of objects classified by the human...
| Autores principales: | , , , , , , , , , , , , |
|---|---|
| Formato: | Journal article |
| Lenguaje: | English |
| Publicado: |
2009
|
| _version_ | 1826270217398910976 |
|---|---|
| author | Banerji, M Lahav, O Lintott, C Abdalla, F Schawinski, K Bamford, S Andreescu, D Murray, P Raddick, M Slosar, A Szalay, A Thomas, D Vandenberg, J |
| author_facet | Banerji, M Lahav, O Lintott, C Abdalla, F Schawinski, K Bamford, S Andreescu, D Murray, P Raddick, M Slosar, A Szalay, A Thomas, D Vandenberg, J |
| author_sort | Banerji, M |
| collection | OXFORD |
| description | We present morphological classifications obtained using machine learning for objects in SDSS DR6 that have been classified by Galaxy Zoo into three classes, namely early types, spirals and point sources/artifacts. An artificial neural network is trained on a subset of objects classified by the human eye and we test whether the machine learning algorithm can reproduce the human classifications for the rest of the sample. We find that the success of the neural network in matching the human classifications depends crucially on the set of input parameters chosen for the machine-learning algorithm. The colours and parameters associated with profile-fitting are reasonable in separating the objects into three classes. However, these results are considerably improved when adding adaptive shape parameters as well as concentration and texture. The adaptive moments, concentration and texture parameters alone cannot distinguish between early type galaxies and the point sources/artifacts. Using a set of twelve parameters, the neural network is able to reproduce the human classifications to better than 90% for all three morphological classes. We find that using a training set that is incomplete in magnitude does not degrade our results given our particular choice of the input parameters to the network. We conclude that it is promising to use machine- learning algorithms to perform morphological classification for the next generation of wide-field imaging surveys and that the Galaxy Zoo catalogue provides an invaluable training set for such purposes. |
| first_indexed | 2024-03-06T21:37:24Z |
| format | Journal article |
| id | oxford-uuid:46bcf42e-64a1-4ac9-bcb7-c6d21a152adc |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-03-06T21:37:24Z |
| publishDate | 2009 |
| record_format | dspace |
| spelling | oxford-uuid:46bcf42e-64a1-4ac9-bcb7-c6d21a152adc2022-03-26T15:15:33ZGalaxy Zoo: Reproducing Galaxy Morphologies Via Machine LearningJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:46bcf42e-64a1-4ac9-bcb7-c6d21a152adcEnglishSymplectic Elements at Oxford2009Banerji, MLahav, OLintott, CAbdalla, FSchawinski, KBamford, SAndreescu, DMurray, PRaddick, MSlosar, ASzalay, AThomas, DVandenberg, JWe present morphological classifications obtained using machine learning for objects in SDSS DR6 that have been classified by Galaxy Zoo into three classes, namely early types, spirals and point sources/artifacts. An artificial neural network is trained on a subset of objects classified by the human eye and we test whether the machine learning algorithm can reproduce the human classifications for the rest of the sample. We find that the success of the neural network in matching the human classifications depends crucially on the set of input parameters chosen for the machine-learning algorithm. The colours and parameters associated with profile-fitting are reasonable in separating the objects into three classes. However, these results are considerably improved when adding adaptive shape parameters as well as concentration and texture. The adaptive moments, concentration and texture parameters alone cannot distinguish between early type galaxies and the point sources/artifacts. Using a set of twelve parameters, the neural network is able to reproduce the human classifications to better than 90% for all three morphological classes. We find that using a training set that is incomplete in magnitude does not degrade our results given our particular choice of the input parameters to the network. We conclude that it is promising to use machine- learning algorithms to perform morphological classification for the next generation of wide-field imaging surveys and that the Galaxy Zoo catalogue provides an invaluable training set for such purposes. |
| spellingShingle | Banerji, M Lahav, O Lintott, C Abdalla, F Schawinski, K Bamford, S Andreescu, D Murray, P Raddick, M Slosar, A Szalay, A Thomas, D Vandenberg, J Galaxy Zoo: Reproducing Galaxy Morphologies Via Machine Learning |
| title | Galaxy Zoo: Reproducing Galaxy Morphologies Via Machine Learning |
| title_full | Galaxy Zoo: Reproducing Galaxy Morphologies Via Machine Learning |
| title_fullStr | Galaxy Zoo: Reproducing Galaxy Morphologies Via Machine Learning |
| title_full_unstemmed | Galaxy Zoo: Reproducing Galaxy Morphologies Via Machine Learning |
| title_short | Galaxy Zoo: Reproducing Galaxy Morphologies Via Machine Learning |
| title_sort | galaxy zoo reproducing galaxy morphologies via machine learning |
| work_keys_str_mv | AT banerjim galaxyzooreproducinggalaxymorphologiesviamachinelearning AT lahavo galaxyzooreproducinggalaxymorphologiesviamachinelearning AT lintottc galaxyzooreproducinggalaxymorphologiesviamachinelearning AT abdallaf galaxyzooreproducinggalaxymorphologiesviamachinelearning AT schawinskik galaxyzooreproducinggalaxymorphologiesviamachinelearning AT bamfords galaxyzooreproducinggalaxymorphologiesviamachinelearning AT andreescud galaxyzooreproducinggalaxymorphologiesviamachinelearning AT murrayp galaxyzooreproducinggalaxymorphologiesviamachinelearning AT raddickm galaxyzooreproducinggalaxymorphologiesviamachinelearning AT slosara galaxyzooreproducinggalaxymorphologiesviamachinelearning AT szalaya galaxyzooreproducinggalaxymorphologiesviamachinelearning AT thomasd galaxyzooreproducinggalaxymorphologiesviamachinelearning AT vandenbergj galaxyzooreproducinggalaxymorphologiesviamachinelearning |