A multi-band AGN-SFG classifier for extragalactic radio surveys using machine learning

Karsten, Juan; Wang, L.; Margalef-Bentabol, Berta; Best, P. N.; Kondapally, R.; Marca, Antonio La; Morganti, Raffaella; Röttgering, H. J. A.; Vaccari, M.; Sabater, J.

doi:10.1051/0004-6361/202346770

Cited by 2 publications

(1 citation statement)

References 76 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The classification of objects in survey catalogues could speed up considerably studies focusing on a particular object. Many classification problems in astronomy have started to be approached using a machine learning (ML) algorithm, which is a purely data-driven methodology [1][2][3][4][5][6][7][8][9][10][11][12].…”

Section: Introductionmentioning

confidence: 99%

The Classification for The Sources in SDSS DR18: Searching for QSOs by Machine Learning

Wen,

Jiang,

Liu

et al. 2023

Preprint

View full text Add to dashboard Cite

We tested selecting data randomly or proportionally in class imbalanced sample. Collecting data into the training and test set according to the initial ratio of QSOs, galaxies and stars were rec-ommended. We experimented using the original imbalanced data or introducing the class balance technologies: SMOTE, SMOTEENN, SMOTETomek, ADASYN, BorderlineSMOTE1, Border-lineSMOTE2, and RandomUndersampling. The SMOTEENN performed the best in the Sample 1. The LightGBM, CatBoost, XGBoost, and RF were compared when adopting the SMOTEENN using the petroMag_u, petroMag_g, petroMag_r, petroMag_i, petroMag_z, J, H, Ks, W1, W2, W3, W4 magnitudes as features. All of the precisions or recalls exceeded 0.94. The RF cost a little more time than the other three algorithms, but resulted in the best evaluating indicators. Utilizing the SMOTEENN +RF technology, the precision, recall and f1-score for QSOs (galaxies, stars) could achieve 0.98 (0.99, 0.98), 0.99 (0.96, 1.00), 0.98 (0.97, 0.99) respectively in Sample 1. Utilizing the SMOTEENN +RF technology, the precision, recall and f1-score for QSOs (galaxies, stars) could achieve 0.94 (0.96, 0.96), 0.98 (0.90, 0.97), 0.96 (0.93, 0.97) using the petroMag_u, petroMag_g, petroMag_r, petroMag_i, petroMag_z, W1, W2, W3, W4 magnitudes as features.

show abstract

Section: Introductionmentioning

confidence: 99%

The Classification for The Sources in SDSS DR18: Searching for QSOs by Machine Learning

Wen,

Jiang,

Liu

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

Galaxy merger challenge: A comparison study between machine learning-based detection methods

Margalef-Bentabol,

Wang,

La Marca

et al. 2024

A&A

View full text Add to dashboard Cite

Various galaxy merger detection methods have been applied to diverse datasets. However, it is difficult to understand how they compare. Our aim is to benchmark the relative performance of merger detection methods based on machine learning (ML). We explore six leading ML methods using three main datasets. The first dataset consists of mock observations from the IllustrisTNG simulations, which acts as the training data and allows us to quantify the performance metrics of the detection methods. The second dataset consists of mock observations from the Horizon-AGN simulations, introduced to evaluate the performance of classifiers trained on different, but comparable data to those employed for training. The third dataset is composed of real observations from the Hyper Suprime-Cam Subaru Strategic Program (HSC-SSP) survey. We also compare mergers and non-mergers detected by the different methods with a subset of HSC-SSP visually identified galaxies. For the simplest binary classification task (i.e. mergers vs. non-mergers), all six methods perform reasonably well in the domain of the training data. At the lowest redshift explored $0.1<z<0.3$, precision and recall generally range between sim 70<!PCT!> and 80<!PCT!>, both of which decrease with increasing $z$ as expected (by sim 5<!PCT!> for precision and sim 10<!PCT!> for recall at the highest $z$ explored $0.76<z<1.0$). When transferred to a different domain, the precision of all classifiers is only slightly reduced, but the recall is significantly worse (by sim 20-40<!PCT!> depending on the method). Zoobot offers the best overall performance in terms of precision and F1 score. When applied to real HSC observations, different methods agree well with visual labels of clear mergers, but can differ by more than an order of magnitude in predicting the overall fraction of major mergers. For the more challenging multi-class classification task to distinguish between pre-mergers, ongoing-mergers, and post-mergers, none of the methods in their current set-ups offer good performance, which could be partly due to the limitations in resolution and the depth of the data. In particular, ongoing-mergers and post-mergers are much more difficult to classify than pre-mergers. With the advent of better quality data (e.g. from JWST and Euclid), it is of great importance to improve our ability to detect mergers and distinguish between merger stages.

show abstract

A multi-band AGN-SFG classifier for extragalactic radio surveys using machine learning

Cited by 2 publications

References 76 publications

The Classification for The Sources in SDSS DR18: Searching for QSOs by Machine Learning

The Classification for The Sources in SDSS DR18: Searching for QSOs by Machine Learning

Galaxy merger challenge: A comparison study between machine learning-based detection methods

Contact Info

Product

Resources

About