arXiv · 2312.08043
Deep learning based photometric redshifts for the Kilo-Degree Survey Bright Galaxy Sample
Abstract
In cosmological analyses, precise redshift determination remains pivotal for understanding cosmic evolution. However, with only a fraction of galaxies having spectroscopic redshifts (spec-$z$s), the challenge lies in estimating redshifts for a larger number. To address this, photometry-based redshift (photo-$z$) estimation, employing machine learning algorithms, is a viable solution. Identifying the limitations of previous methods, this study focuses on implementing deep learning (DL) techniques within the Kilo-Degree Survey (KiDS) Bright Galaxy Sample for more accurate photo-$z$ estimations. Comparing our new DL-based model against prior `shallow' neural networks, we showcase improvements in redshift accuracy. Our model gives mean photo-$z$ bias $\langle \Delta z\rangle= 10^{-3}$ and scatter $\mathrm{SMAD}(\Delta z)=0.016$, where $\Delta z = (z_\mathrm{phot}-z_\mathrm{spec})/(1+z_\mathrm{spec})$. This research highlights the promising role of DL in revolutionizing photo-$z$ estimation.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Anjitha John William, Priyanka Jalan, Maciej Bilicki, Wojciech A. Hellwing. 2023-12-13. Deep learning based photometric redshifts for the Kilo-Degree Survey Bright Galaxy Sample. https://arxiv.org/abs/2312.08043
Cite the original work for its findings. Save a collection to share your selection of sources.