Utilizza questo identificativo per citare o creare un link a questo documento:
http://hdl.handle.net/20.500.12386/32140
Titolo: | Improving the reliability of photometric redshift with machine learning | Autori: | Razim, Oleksandra CAVUOTI, STEFANO BRESCIA, Massimo RICCIO, GIUSEPPE Salvato, Mara Longo, Giuseppe |
Data pubblicazione: | 2021 | Rivista: | MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY | Numero: | 507 | Fascicolo: | 4 | Da pagina:: | 5034 | Abstract: | In order to answer the open questions of modern cosmology and galaxy evolution theory, robust algorithms for calculating photometric redshifts (photo-z) for very large samples of galaxies are needed. Correct estimation of the various photo-z algorithms' performance requires attention to both the performance metrics and the data used for the estimation. In this work, we use the supervised machine learning algorithm MLPQNA (Multi-Layer Perceptron with Quasi-Newton Algorithm) to calculate photometric redshifts for the galaxies in the COSMOS2015 catalogue and the unsupervised Self-Organizing Maps (SOM) to determine the reliability of the resulting estimates. We find that for z<SUB>spec</SUB> < 1.2, MLPQNA photo-z predictions are on the same level of quality as spectral energy distribution fitting photo-z. We show that the SOM successfully detects unreliable z<SUB>spec</SUB> that cause biases in the estimation of the photo-z algorithms' performance. Additionally, we use SOM to select the objects with reliable photo-z predictions. Our cleaning procedures allow us to extract the subset of objects for which the quality of the final photo-z catalogues is improved by a factor of 2, compared to the overall statistics. | URI: | http://hdl.handle.net/20.500.12386/32140 | URL: | https://academic.oup.com/mnras/article-abstract/507/4/5034/6350583?redirectedFrom=fulltext&login=false https://arxiv.org/abs/2108.04784 |
ISSN: | 0035-8711 | DOI: | 10.1093/mnras/stab2334 | Bibcode ADS: | 2021MNRAS.507.5034R | Fulltext: | open |
È visualizzato nelle collezioni: | 1.01 Articoli in rivista |
File in questo documento:
File | Descrizione | Dimensioni | Formato | |
---|---|---|---|---|
stab2334.pdf | PDF editoriale | 7.51 MB | Adobe PDF | Visualizza/apri |
Page view(s)
25
controllato il 25-apr-2024
Download(s)
22
controllato il 25-apr-2024
Google ScholarTM
Check
Altmetric
Altmetric
Tutti i documenti in DSpace sono pubblicati ad Accesso Aperto, salvo diversa indicazione per alcuni documenti specifici.