Radio Galaxy Zoo: giant radio galaxy classification using multidomain deep learning
Problem
Identifying rare giant radio galaxies in very large radio survey datasets is difficult, and will become harder with next-generation telescopes like the SKA.
Why it matters
Manual inspection of massive survey volumes is infeasible, so rare astronomical objects could be missed.
What the AI did
Multidomain multibranch convolutional neural networks learned jointly from NVSS and FIRST survey images plus numerical redshift information to classify giant radio galaxies.
Results
Multiresolution survey data corrected 39% of misclassifications from equivalent single-domain networks; redshift inclusion moderately improved classification.
Impact
Improves automated identification of rare giant radio galaxies for upcoming radio surveys.
Record
| Venue | Monthly Notices of the Royal Astronomical Society |
|---|---|
| Published | 2021 |
| Work type | article |
| Authors | Hongming Tang, Anna M. M. Scaife, O. Ivy Wong, Stanislav S. Shabala |
| Citations | 0 (OpenAlex, at import time) |
| References | 110 |
| Model or method | multidomain multibranch convolutional neural networks (CNNs) |
| Organization | not stated in source |
| Primary source | https://doi.org/10.1093/mnras/stab3553 |
| Open access | bronze |
| Keywords | radio galaxies, deep learning, CNN, classification, SKA, NVSS, FIRST |
Importance rating
incremental / niche
Identifying rare giant radio galaxies in large upcoming surveys aids astronomy, but abstract states no scale of impact; niche scientific classification task.
More in Physics & Astronomy
| # | Paper | Year | Citations | Importance |
|---|---|---|---|---|
| 1 | Magnetic control of tokamak plasmas through deep reinforcement learning | 2022 | 739 |
7
|
| 2 | Solving the quantum many-body problem with artificial neural networks | 2017 | 2,205 |
7
|
| 3 | Learning high-accuracy error decoding for quantum processors | 2024 | 90 |
7
|
| 4 | Optimizing Quantum Error Correction Codes with Reinforcement Learning | 2019 | 158 |
7
|
| 5 | Machine-learning-assisted correction of correlated qubit errors in a topological code | 2018 | 141 |
7
|