Detection of extragalactic Ultra-compact dwarfs and Globular Clusters using Explainable AI techniques

Mohammadi, Mohammad; Mutatiina, J.; Saifollahi, Teymoor; Bunte, Kerstin

doi:10.1016/j.ascom.2022.100555

Cited by 6 publications

(4 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In general, the trained models reach good performance levels and are suitable for detecting GCs in photometric data. Our results agree with a recent study evaluating explainable machine learning for extracting ultra-compact dwarfs and GCs from ground-based imaging of the Fornax cluster, which reports true positives rates of 0.89−0.97 and false discovery rates of 0.04−0.07 (Mohammadi et al 2022), although on a much smaller data set of ∼7700 sources containing ∼500 GCs and for six instead of only two bands, making an exact comparison impossible. Recently published studies on detecting star clusters from HST data using machine learning also report similar results: Pérez et al ( 2021) use a CNN (StarcNet) and a data set of ∼15 000 sources from the LEGUS galaxies with observations in five bands for training, validation, and testing.…”

Section: Model Performance and Generalisation To New Datasupporting

confidence: 88%

“…These studies apply various machine learning methods with success and typically report 90% success fractions for identifying bright, symmetric star clusters. While the aforementioned works focused on young or resolved star clusters, identification of (old) GCs with machine learning methods has been recently studied by Mohammadi et al (2022). In this work, random forest (RF) and Localized Generalized Matrix Learning Vector Quantization (LGMLVQ) classifiers are used to identify ∼500 GCs and ultracompact dwarf galaxies in multi-wavelength ground-based photometric data of ∼7700 sources in the Fornax galaxy cluster with promising results (see also Saifollahi et al 2021).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Evaluating the feasibility of interpretable machine learning for globular cluster detection

Dold

Fahrion

2022

A&A

View full text Add to dashboard Cite

Extragalactic globular clusters (GCs) are important tracers of galaxy formation and evolution because their properties, luminosity functions, and radial distributions hold valuable information about the assembly history of their host galaxies. Obtaining GC catalogues from photometric data involves several steps which will likely become too time-consuming to perform on the large data volumes that are expected from upcoming wide-field imaging projects such as Euclid. In this work, we explore the feasibility of various machine learning methods to aid the search for GCs in extensive databases. We use archival Hubble Space Telescope data in the F475W and F850LP bands of 141 early-type galaxies in the Fornax and Virgo galaxy clusters. Using existing GC catalogues to label the data, we obtained an extensive data set of 84929 sources containing 18556 GCs and we trained several machine learning methods both on image and tabular data containing physically relevant features extracted from the images. We find that our evaluated machine learning models are capable of producing catalogues of a similar quality as the existing ones which were constructed from mixture modelling and structural fitting. The best performing methods, ensemble-based models such as random forests, and convolutional neural networks recover ∼90−94% of GCs while producing an acceptable amount of false detections (∼6−8%), with some falsely detected sources being identifiable as GCs which have not been labelled as such in the used catalogues. In the magnitude range 22 < m4_g ≤ 24.5 mag, 98−99% of GCs are recovered. We even find such high performance levels when training on Virgo and evaluating on Fornax data (and vice versa), illustrating that the models are transferable to environments with different conditions, such as different distances than in the used training data. Apart from performance metrics, we demonstrate how interpretable methods can be utilised to better understand model predictions, recovering that magnitudes, colours, and sizes are important properties for identifying GCs. Moreover, comparing colour distributions from our detected sources to the reference distributions from input catalogues finds great agreement and the mean colour is recovered even for systems with fewer than 20 GCs. These are encouraging results, indicating that similar methods trained on an informative sub-sample can be applied for creating GC catalogues for a large number of galaxies, with tools being available for increasing the transparency and reliability of said methods.

show abstract

Section: Model Performance and Generalisation To New Datasupporting

confidence: 88%

Section: Introductionmentioning

confidence: 99%

Evaluating the feasibility of interpretable machine learning for globular cluster detection

Dold

Fahrion

2022

A&A

View full text Add to dashboard Cite

show abstract

“…As a classification problem, selection of star clusters is well suited to machine learning techniques. Recent experiments with machine learning selection of clusters on either images (Pérez et al 2021;Thilker et al 2022) or photometric catalogs (Barbisan et al 2022;Mohammadi et al 2022) show promise. Samples of star clusters, foreground stars and background galaxies from space based imaging (HST or JWST) can be used to train and validate classification techniques with Rubin data; other efforts (photometric redshift pipelines from the LSST Galaxies collaboration, star-galaxy separation techniques from SMWLV collaboration) may also prove useful.…”

Section: Source Classificationmentioning

confidence: 99%

Rubin Observatory LSST Stars Milky Way and Local Volume Star Clusters Roadmap

Usher,

Dage,

Girardi

et al. 2023

PASP

View full text Add to dashboard Cite

The Vera C. Rubin Observatory will undertake the Legacy Survey of Space and Time, providing an unprecedented, volume-limited catalog of star clusters in the Southern Sky, including Galactic and extragalactic star clusters. The Star Clusters subgroup of the Stars, Milky Way and Local Volume Working Group has identified key areas where Rubin Observatory will enable significant progress in star cluster research. This roadmap represents our science cases and preparation for studies of all kinds of star clusters from the Milky Way out to distances of tens of megaparsecs.

show abstract

“…The interpretable machine learning techniques (Localized General Matrix LVQ and RF) were used in Mohammadi et al (2022) to detect extragalactic Ultra-compact dwarfs and Globular Clusters. Authors analysed the importance of features and compared them with features that carry physical information of the objects.…”

Section: Introductionmentioning

confidence: 99%

Crossmatching of high-proper motion L, T, and Y brown dwarfs with large photometric surveys

2023

View full text Add to dashboard Cite

L, T, and Y brown dwarf (BD) exploration is a topical issue. First, the transition boundary between planets and BDs is not fully understood yet. Second, there is a phenomenon called the L/T-transition. The observed properties of cooler BDs differ significantly from the less cool ones, namely, colors of BDs shift much bluer and, simultaneously, dwarfs become brighter with a decrease in temperature. Models of this phenomenon are now being actively developed, for which reason BDs observed in a wide range of spectra are needed. Our goal is to refine the position of BDs in the parameter space of colors and magnitudes in order to effectively search for them in photometric surveys (without involving spectroscopic observations). For that reason, we crossmatched about 500 known L, T, and Y BDs with large photometric surveys. We paid special attention to the problem of identifying objects near the Sun because the crossmatching by default is made by searching for the closest object in a particular survey, which can be inappropriate concerning the high proper motions of our dwarfs. We have determined the color indices that can be used to search for these objects in large photometric surveys, and we have pointed out the color indices that are inappropriate for this purpose. We also made preliminary estimates of the radius matching to search for objects in the modern photometric surveys, given their proximity to the Sun and, consequently, their high proper motion.

show abstract

Detection of extragalactic Ultra-compact dwarfs and Globular Clusters using Explainable AI techniques

Cited by 6 publications

References 31 publications

Evaluating the feasibility of interpretable machine learning for globular cluster detection

Evaluating the feasibility of interpretable machine learning for globular cluster detection

Rubin Observatory LSST Stars Milky Way and Local Volume Star Clusters Roadmap

Crossmatching of high-proper motion L, T, and Y brown dwarfs with large photometric surveys

Contact Info

Product

Resources

About