Reconstructing the local density field with combined convolutional and point cloud architecture
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908676325900288 |
|---|---|
| author | Barthe-Gold, Baptiste Nguyen, Nhat-Minh Thiele, Leander |
| author_facet | Barthe-Gold, Baptiste Nguyen, Nhat-Minh Thiele, Leander |
| contents | We construct a neural network to perform regression on the local dark-matter density field given line-of-sight peculiar velocities of dark-matter halos, biased tracers of the dark matter field. Our architecture combines a convolutional U-Net with a point-cloud DeepSets. This combination enables efficient use of small-scale information and improves reconstruction quality relative to a U-Net-only approach. Specifically, our hybrid network recovers both clustering amplitudes and phases better than the U-Net on small scales. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_08573 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Reconstructing the local density field with combined convolutional and point cloud architecture Barthe-Gold, Baptiste Nguyen, Nhat-Minh Thiele, Leander Cosmology and Nongalactic Astrophysics Machine Learning We construct a neural network to perform regression on the local dark-matter density field given line-of-sight peculiar velocities of dark-matter halos, biased tracers of the dark matter field. Our architecture combines a convolutional U-Net with a point-cloud DeepSets. This combination enables efficient use of small-scale information and improves reconstruction quality relative to a U-Net-only approach. Specifically, our hybrid network recovers both clustering amplitudes and phases better than the U-Net on small scales. |
| title | Reconstructing the local density field with combined convolutional and point cloud architecture |
| topic | Cosmology and Nongalactic Astrophysics Machine Learning |
| url | https://arxiv.org/abs/2510.08573 |