Advances on the morphological classification of radio galaxies: A review

Ndung’u, Steven; Grobler, Trienko; Wijnholds, Stefan J.; Karastoyanova, Dimka; Azzopardi, George

doi:10.1016/j.newar.2023.101685

Cited by 5 publications

(2 citation statements)

References 95 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With many million sources to classify, the development of advanced software tools for an automatic selection and classification of the objects is needed. This is a rapidly expanding field (e.g., [81,82]) which will also benefit from tools specifically tuned to identify rare objects like remnant radio source (see [83] and Brienza et al, in prep).…”

Section: Conclusion and Future Possibilitiesmentioning

confidence: 99%

What Have We Learned about the Life Cycle of Radio Galaxies from New Radio Surveys

Morganti

2024

Galaxies

View full text Add to dashboard Cite

The recurrent activity of radio AGN, with phases of activity alternating with periods of quiescence, has been known since the early studies of these objects. The full relevance of this cycle is emphasised by the requirement, from the AGN feedback scenario, of a recurrent impact of the energy released by the SMBH during the lifetime of the host galaxy: only in this way can AGN feedback influence galaxy evolution. Radio AGN in different evolutionary phases can be identified by their properties, like morphology and spectral indices. Dying/remnant and restarted sources have been the most elusive to select and characterise, but they are crucial to quantify the full life cycle. Thanks to the availability of new, large radio surveys (particularly at low frequencies), it is finally possible to make a more complete census of these rare sources and start building larger samples. This paper gives an overview of the recent work conducted using a variety of radio telescopes and surveys, highlighting some of the new results characterising the properties of dying/remnant and restarted radio sources and what has been learned about the life cycle of radio AGN. The comparison with the predictions from numerical simulations is also discussed. The results so far show that remnant and restarted radio AGN have a variety of properties which make these objects more complex than previously thought.

show abstract

Section: Conclusion and Future Possibilitiesmentioning

confidence: 99%

What Have We Learned about the Life Cycle of Radio Galaxies from New Radio Surveys

Morganti

2024

Galaxies

View full text Add to dashboard Cite

show abstract

“…deep learning to classify radio galaxies, and several other studies worked on improving the classification performance by training more sophisticated neural network architectures on various datasets (see [14] for a review on the progress so far). Most of the methods that have been considered to identify radio galaxy morphology are supervised learning based.…”

Section: Jcap06(2024)034mentioning

confidence: 99%

Radio Galaxy Zoo: Leveraging latent space representations from variational autoencoder

Andrianomena,

Tang

2024

J. Cosmol. Astropart. Phys.

View full text Add to dashboard Cite

We propose to learn latent space representations of radio galaxies, and train a very deep variational autoencoder (VDVAE) on RGZ DR1, an unlabeled dataset, to this end. We show that the encoded features can be leveraged for downstream tasks such as classifying galaxies in labeled datasets, and similarity search. Results show that the model is able to reconstruct its given inputs, capturing the salient features of the latter. We use the latent codes of galaxy images, from MiraBest Confident and FR-DEEP NVSS datasets, to train various non-neural network classifiers. It is found that the latter can differentiate FRI from FRII galaxies achieving accuracy ≥ 76%, roc-auc ≥ 0.86, specificity ≥ 0.73 and recall ≥ 0.78 on MiraBest Confident dataset, comparable to results obtained in previous studies. The performance of simple classifiers trained on FR-DEEP NVSS data representations is on par with that of a deep learning classifier (CNN based) trained on images in previous work, highlighting how powerful the compressed information is. We successfully exploit the learned representations to search for galaxies in a dataset that are semantically similar to a query image belonging to a different dataset. Although generating new galaxy images (e.g. for data augmentation) is not our primary objective, we find that the VDVAE model is a relatively good emulator. Finally, as a step toward detecting anomaly/novelty, a density estimator — Masked Autoregressive Flow (MAF) — is trained on the latent codes, such that the log-likelihood of data can be estimated. The downstream tasks conducted in this work demonstrate the meaningfulness of the latent codes.

show abstract

Classification of radio galaxies with trainable COSFIRE filters

Ndung’u,

Grobler,

Wijnholds

et al. 2024

Monthly Notices of the Royal Astronomical Society

View full text Add to dashboard Cite

Radio galaxies exhibit a rich diversity of morphological characteristics, which make their classification into distinct types a complex challenge. To address this challenge effectively, we introduce an innovative approach for radio galaxy classification using COSFIRE filters. These filters possess the ability to adapt to both the shape and orientation of prototype patterns within images. The COSFIRE approach is explainable, learning-free, rotation-tolerant, efficient, and does not require a large training set. To assess the efficacy of our method, we conducted experiments on a benchmark radio galaxy data set comprising of 1180 training samples and 404 test samples. Notably, our approach achieved an average accuracy rate of 93.36 %. This achievement outperforms contemporary deep learning models, and it is the best result ever achieved on this data set. Additionally, COSFIRE filters offer better computational performance, ∼20 × fewer operations than the DenseNet-based competing method (when comparing at the same accuracy). Our findings underscore the effectiveness of the COSFIRE filter-based approach in addressing the complexities associated with radio galaxy classification. This research contributes to advancing the field by offering a robust solution that transcends the orientation challenges intrinsic to radio galaxy observations. Our method is versatile in that it is applicable to various image classification approaches.

show abstract

Advances on the morphological classification of radio galaxies: A review

Cited by 5 publications

References 95 publications

What Have We Learned about the Life Cycle of Radio Galaxies from New Radio Surveys

What Have We Learned about the Life Cycle of Radio Galaxies from New Radio Surveys

Radio Galaxy Zoo: Leveraging latent space representations from variational autoencoder

Classification of radio galaxies with trainable COSFIRE filters

Contact Info

Product

Resources

About