Investigating the Impact of Unsupervised Feature-Extraction from Multi-Wavelength Image Data for Photometric Classification of Stars, Galaxies and QSOs

Authors

Annika Lindh, Technological University DublinFollow

Document Type

Conference Paper

Rights

Available under a Creative Commons Attribution Non-Commercial Share Alike 4.0 International Licence

Disciplines

1.2 COMPUTER AND INFORMATION SCIENCE, Computer Sciences

Publication Details

Proceedings of the 24th Irish Conference on Artificial Intelligence and Cognitive Science (pp. 320-331), Dublin, Ireland.

Abstract

Accurate classification of astronomical objects currently relies on spectroscopic data. Acquiring this data is time-consuming and expensive compared to photometric data. Hence, improving the accuracy of photometric classification could lead to far better coverage and faster classification pipelines. This paper investigates the benefit of using unsupervised feature-extraction from multi-wavelength image data for photometric classification of stars, galaxies and QSOs. An unsupervised Deep Belief Network is used, giving the model a higher level of interpretability thanks to its generative nature and layer-wise training. A Random Forest classifier is used to measure the contribution of the novel features compared to a set of more traditional baseline features.

DOI

https://doi.org/10.21427/D7TX67

Recommended Citation

Lindh, A. (2016). Investigating the Impact of Unsupervised Feature-Extraction from Multi-Wavelength Image Data for Photometric Classification of Stars, Galaxies and QSOs. Proceedings of the 24th Irish Conference on Artificial Intelligence and Cognitive Science, Dublin, Ireland, p. 320-331. doi:10.21427/D7TX67