Matches in SemOpenAlex for { <https://semopenalex.org/work/W4226017003> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W4226017003 abstract "All-sky radio surveys are set to revolutionise the field with new discoveries. However, the vast majority of the tens of millions of radio galaxies won't have the spectroscopic redshift measurements required for a large number of science cases. Here, we evaluate techniques for estimating redshifts of galaxies from a radio-selected survey. Using a radio-selected sample with broadband photometry at infrared and optical wavelengths, we test the k-Nearest Neighbours (kNN) and Random Forest machine learning algorithms, testing them both in their regression and classification modes. Further, we test different distance metrics used by the kNN algorithm, including the standard Euclidean distance, the Mahalanobis distance and a learned distance metric for both the regression mode (the Metric Learning for Kernel Regression metric) and the classification mode (the Large Margin Nearest Neighbour metric). We find that all regression-based modes fail on galaxies at a redshift $z > 1$. However, below this range, the kNN algorithm using the Mahalanobis distance metric performs best, with an $eta_{0.15}$ outlier rate of 5.85%. In the classification mode, the kNN algorithm using the Mahalanobis distance metric also performs best, with an $eta_{0.15}$ outlier rate of 5.85%, correctly placing 74% of galaxies in the top $z > 1.02$ bin. Finally, we also tested the effect of training in one field and applying the trained algorithm to similar data from another field and found that variation across fields does not result in statistically significant differences in predicted redshifts. Importantly, we find that while we may not be able to predict a continuous value for high-redshift radio sources, we can identify the majority of them using the classification modes of existing techniques." @default.
- W4226017003 created "2022-05-05" @default.
- W4226017003 creator A5005934142 @default.
- W4226017003 creator A5006560423 @default.
- W4226017003 creator A5008485249 @default.
- W4226017003 creator A5016791023 @default.
- W4226017003 creator A5058982639 @default.
- W4226017003 date "2022-02-27" @default.
- W4226017003 modified "2023-10-16" @default.
- W4226017003 title "Estimating Galaxy Redshift in Radio-Selected Datasets using Machine Learning" @default.
- W4226017003 doi "https://doi.org/10.48550/arxiv.2202.13504" @default.
- W4226017003 hasPublicationYear "2022" @default.
- W4226017003 type Work @default.
- W4226017003 citedByCount "0" @default.
- W4226017003 crossrefType "posted-content" @default.
- W4226017003 hasAuthorship W4226017003A5005934142 @default.
- W4226017003 hasAuthorship W4226017003A5006560423 @default.
- W4226017003 hasAuthorship W4226017003A5008485249 @default.
- W4226017003 hasAuthorship W4226017003A5016791023 @default.
- W4226017003 hasAuthorship W4226017003A5058982639 @default.
- W4226017003 hasBestOaLocation W42260170031 @default.
- W4226017003 hasConcept C113238511 @default.
- W4226017003 hasConcept C11413529 @default.
- W4226017003 hasConcept C121332964 @default.
- W4226017003 hasConcept C153180895 @default.
- W4226017003 hasConcept C154945302 @default.
- W4226017003 hasConcept C162324750 @default.
- W4226017003 hasConcept C169258074 @default.
- W4226017003 hasConcept C176217482 @default.
- W4226017003 hasConcept C1921717 @default.
- W4226017003 hasConcept C21547014 @default.
- W4226017003 hasConcept C33024259 @default.
- W4226017003 hasConcept C41008148 @default.
- W4226017003 hasConcept C44870925 @default.
- W4226017003 hasConcept C79337645 @default.
- W4226017003 hasConcept C98444146 @default.
- W4226017003 hasConceptScore W4226017003C113238511 @default.
- W4226017003 hasConceptScore W4226017003C11413529 @default.
- W4226017003 hasConceptScore W4226017003C121332964 @default.
- W4226017003 hasConceptScore W4226017003C153180895 @default.
- W4226017003 hasConceptScore W4226017003C154945302 @default.
- W4226017003 hasConceptScore W4226017003C162324750 @default.
- W4226017003 hasConceptScore W4226017003C169258074 @default.
- W4226017003 hasConceptScore W4226017003C176217482 @default.
- W4226017003 hasConceptScore W4226017003C1921717 @default.
- W4226017003 hasConceptScore W4226017003C21547014 @default.
- W4226017003 hasConceptScore W4226017003C33024259 @default.
- W4226017003 hasConceptScore W4226017003C41008148 @default.
- W4226017003 hasConceptScore W4226017003C44870925 @default.
- W4226017003 hasConceptScore W4226017003C79337645 @default.
- W4226017003 hasConceptScore W4226017003C98444146 @default.
- W4226017003 hasLocation W42260170031 @default.
- W4226017003 hasOpenAccess W4226017003 @default.
- W4226017003 hasPrimaryLocation W42260170031 @default.
- W4226017003 hasRelatedWork W1972359685 @default.
- W4226017003 hasRelatedWork W1976627859 @default.
- W4226017003 hasRelatedWork W1991774265 @default.
- W4226017003 hasRelatedWork W2099612160 @default.
- W4226017003 hasRelatedWork W2593844102 @default.
- W4226017003 hasRelatedWork W2964248325 @default.
- W4226017003 hasRelatedWork W3037030989 @default.
- W4226017003 hasRelatedWork W3084546154 @default.
- W4226017003 hasRelatedWork W3127815541 @default.
- W4226017003 hasRelatedWork W3184307035 @default.
- W4226017003 isParatext "false" @default.
- W4226017003 isRetracted "false" @default.
- W4226017003 workType "article" @default.