Open Access
Table 1
Common tasks in astrophysics and their machine learning analogs.
| Astrophysics task | Machine learning task or method | Selected references |
|---|---|---|
| Image reconstruction | CNNs, denoising diffusion | (Schmidt et al. 2022; Drozdova et al. 2023) |
| Source detection | Object detection | (Vafaei Sadr et al. 2019; Jia et al. 2023; Riggi et al. 2023) |
| Source characterization | Object segmentation | (Farias et al. 2020; Sortino et al. 2023) |
| Source classification | Image or object classification | (Burke et al. 2019; Riggi et al. 2023; Merz et al. 2023) |
| Source deblending | Instance segmentation | (Burke et al. 2019; Reiman & Göhre 2019; Hausen & Robertson 2022) |
| Object/event discovery | Anomaly detection | (Lochner & Bassett 2021; Villar et al. 2021) |
| RFI detection | CNNs, GANs | fee(Vos et al. 2019; Li et al. 2021) |
| Background/foreground removal | UNET, denoising diffusion | (Cohen & Lu 2021 ; Zhou et al. 2023; Chen et al. 2024a) |
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.