Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2503.17202 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913750402990080 |
|---|---|
| author | Vera-Casanova., Alex Gonzalez, Nicolas Monsalves Gómez, Facundo A. Arancibia., Marcelo Jaque Fontirroig, Valentina Pallero., Diego Pakmor., Rüdiger van de Voort., Freeke Grand., Robert J. J. Bieri., Rebekka Marinacci, Federico |
| author_facet | Vera-Casanova., Alex Gonzalez, Nicolas Monsalves Gómez, Facundo A. Arancibia., Marcelo Jaque Fontirroig, Valentina Pallero., Diego Pakmor., Rüdiger van de Voort., Freeke Grand., Robert J. J. Bieri., Rebekka Marinacci, Federico |
| contents | Context. Galactic halos host faint substructures, such as stellar streams and shells, which provide insights into the hierarchical assembly history of galaxies. To date, such features have been identified in external galaxies by visual inspection. However, with the advent of larger and deeper surveys and the associated increase in data volume, this methodology is becoming impractical. Aims. Here we aim to develop an automated method to detect low surface brightness features in galactic stellar halos. Moreover, we seek to quantify its performance when considering progressively more complex data sets, including different stellar disc orientations and redshifts. Methods. We develop the Stream Automatic Detection with Convolutional Neural Networks, SAD-CNN. This tool is trained on mock surface brightness maps obtained from simulations of the Auriga Project. The model incorporates transfer learning, data augmentation and balanced datasets to optimise its detection capabilities at surface brightness limiting magnitudes ranging from 27 to 31 mag arcsec^-2. Results. The iterative training approach, coupled with transfer learning, allowed the model to adapt to increasingly challenging datasets, achieving precision and recall metrics above 80% in all considered scenarios. The use of a well-balanced training dataset is critical for mitigating biases, ensuring that the CNN accurately distinguishes between galaxies with and without streams. Conclusions. SAD-CNN is a reliable and scalable tool for automating the detection of faint substructures in galactic halos. Its adaptability makes it well-suited for future applications, including the analysis of data from upcoming large astronomical surveys (such as LSST, JWT). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_17202 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Stream Automatic Detection with Convolutional Neural Network (SAD-CNN) Vera-Casanova., Alex Gonzalez, Nicolas Monsalves Gómez, Facundo A. Arancibia., Marcelo Jaque Fontirroig, Valentina Pallero., Diego Pakmor., Rüdiger van de Voort., Freeke Grand., Robert J. J. Bieri., Rebekka Marinacci, Federico Astrophysics of Galaxies Context. Galactic halos host faint substructures, such as stellar streams and shells, which provide insights into the hierarchical assembly history of galaxies. To date, such features have been identified in external galaxies by visual inspection. However, with the advent of larger and deeper surveys and the associated increase in data volume, this methodology is becoming impractical. Aims. Here we aim to develop an automated method to detect low surface brightness features in galactic stellar halos. Moreover, we seek to quantify its performance when considering progressively more complex data sets, including different stellar disc orientations and redshifts. Methods. We develop the Stream Automatic Detection with Convolutional Neural Networks, SAD-CNN. This tool is trained on mock surface brightness maps obtained from simulations of the Auriga Project. The model incorporates transfer learning, data augmentation and balanced datasets to optimise its detection capabilities at surface brightness limiting magnitudes ranging from 27 to 31 mag arcsec^-2. Results. The iterative training approach, coupled with transfer learning, allowed the model to adapt to increasingly challenging datasets, achieving precision and recall metrics above 80% in all considered scenarios. The use of a well-balanced training dataset is critical for mitigating biases, ensuring that the CNN accurately distinguishes between galaxies with and without streams. Conclusions. SAD-CNN is a reliable and scalable tool for automating the detection of faint substructures in galactic halos. Its adaptability makes it well-suited for future applications, including the analysis of data from upcoming large astronomical surveys (such as LSST, JWT). |
| title | Stream Automatic Detection with Convolutional Neural Network (SAD-CNN) |
| topic | Astrophysics of Galaxies |
| url | https://arxiv.org/abs/2503.17202 |