Deep transfer learning for the classification of variable sources

Kim, Dae Won; Yeo, Doyeob; Bailer‐Jones, C. A. L.; Lee, Giyoung

doi:10.1051/0004-6361/202140369

Cited by 5 publications

(5 citation statements)

References 60 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, only 23.2% RRD variables in ASAS-SN are correctly predicted. Kim et al (2021) also obtained similar results. Figure 10 in their paper showed that 91% RRD variables from ASAS-SN were classified as RRAB variables by the model which was trained based on light curves from OGLE I-band and EROS-2 B E -band.…”

Section: Classification Accuracy Comparison With Asas-sn and Oglesupporting

confidence: 63%

“…Ongoing or upcoming surveys, such as ASAS-SN, Optical Gravitational Lensing Experiment (OGLE; Udalski 2003), Zwicky Transient Facility (ZTF; Bellm et al 2019;Masci et al 2019), China Near-Earth Object Survey Telescope (CNEOST; Wang et al 2016;Yeh et al 2020), Gaia (Gaia Collaboration et al 2016Mowlavi et al 2018), Legacy Survey of Space and Time (LSST; Ivezić et al 2019), and Wide Field Survey Telescope (WFST), will observe the light curves of billions of astronomical sources, and the large amount of data presents new challenges for the rapid identification and classification of different variability types (Kim et al 2021).…”

Section: Introductionmentioning

confidence: 99%

“…In order to extend the census of RR Lyrae stars to highly reddened low-latitude regions of the central Milky Way, Dékány & Grebel (2020) trained a deep long short-term memory recurrent neural network model (Cho et al 2014;Chung et al 2014) based on the data from the VISTA Variables in the Vía Láctea (VVV; Dékány et al 2018). Kim et al (2021) developed a single-band light curve classifier based on deep neural networks using OGLE and EROS-2 data and used transfer learning to solve the problem of training data scarcity by conveying knowledge from one data set to another. Again, they kindly provided a Python package "UPSILoN-T" that contained the pre-trained neural network and could optimize the model using a small set of light curves from the target survey.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A New Period Determination Method for Periodic Variable Stars

Xu¹,

Zhu²,

Li³

et al. 2022

PASP

View full text Add to dashboard Cite

Variable stars play a key role in understanding the Milky Way and the universe. The era of astronomical big data presents new challenges for quick identification of interesting and important variable stars. Accurately estimating the periods is the most important step to distinguish different types of variable stars. Here, we propose a new method of determining the variability periods. By combining the statistical parameters of the light curves, the colors of the variables, the window function and the Generalized Lomb-Scargle (GLS) algorithm, the aperiodic variables are excluded and the periodic variables are divided into eclipsing binaries and NEB variables (other types of periodic variable stars other than eclipsing binaries), the periods of the two main types of variables are derived. We construct a random forest classifier based on 241,154 periodic variables from the ASAS-SN and OGLE data sets of variables. The random forest classifier is trained on 17 features, among which 11 are extracted from the light curves and 6 are from the Gaia Early DR3, ALLWISE, and 2MASS catalogs. The variables are classified into 7 superclasses and 17 subclasses. In comparison with the ASAS-SN and OGLE catalogs, the classification accuracy is generally above approximately 82% and the period accuracy is 70%–99%. To further test the reliability of the new method and classifier, we compare our results with the results of Chen et al. for ZTF DR2. The classification accuracy is generally above 70%. The period accuracy of the EW and SR variables is ∼50% and 53%, respectively. And the period accuracy of other types of variables is 65%–98%.

show abstract

Section: Classification Accuracy Comparison With Asas-sn and Oglesupporting

confidence: 63%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A New Period Determination Method for Periodic Variable Stars

Xu¹,

Zhu²,

Li³

et al. 2022

PASP

View full text Add to dashboard Cite

show abstract

“…Through a transfer-learning method between different radio surveys, Tang et al (2019) proposed a CNN model for classifying radio galaxies. Kim et al (2021) address the problem of insufficient amount of data in variable source classification using a transfer-learning approach.…”

Section: Introductionmentioning

confidence: 99%

A White Dwarf Search Model Based on a Deep Transfer-learning Method

Tan 谈,

Liu 柳,

Wang 王

et al. 2023

ApJS

View full text Add to dashboard Cite

White dwarfs represent the ultimate stage of evolution for over 97% of stars and play a crucial role in studies of the Milky Way’s structure and evolution. Recent years have witnessed significant progress in using deep-learning methods for identifying unique objects in large-scale data. In this paper, we present a model based on transfer learning for identifying white dwarfs. We constructed a data set using the spectra released by LAMOST DR9 and trained a convolutional neural network model. The model was then further trained using a transfer-learning approach for a binary classification model. Our final model is comprised of a seven-class classification model and a binary classification model. The testing set yielded an accuracy rate of 96.08%. Our proposed model successfully identifies 4314 of the 4479 white dwarfs published in previous papers. We applied this model to filter the 1,121,128 spectral data from the LAMOST DR9 V1 catalog. Subsequently, we obtained 6317 white dwarf candidates, of which 5014 were cross-validated and found to be known white dwarfs. We finally identified 489 new white dwarfs out of the remaining 1303 candidates, containing 377 DAs, 1 DB, 4 DZs, 1 magnetic WD, 101 DA+M binaries, and 1 DB+M binary. Our study also compared transfer-learning methods with non-transfer-learning methods, and the results show that transfer learning provides faster training speed and a higher accuracy rate. We provide the trained model and a corresponding usage program for subsequent studies.

show abstract

“…The most common usage is for classification tasks (see Cavanagh, Bekki & Groves 2021;Fremling et al 2021;Kim et al 2021 for the most recent examples), but also generative networks start to be widely adopted (see Bretonnière et al 2021;Curtis, Brainerd & Hernandez 2021;Li et al 2021, again for the latest examples). Deep Learning has also been exploited for the detection of sources, as in Sánchez-Sáez et al (2021) or Kim et al (2021) and as in our previous work (Gheller, Vazza & Bonafede 2018), where we have explored the potential of Convolutional Neural Networks (CNN) in identifying the faint radio signal from extended cosmological radio sources (such as emission from shocked gas around galaxy clusters and filaments) in noisy radio observations, which are at the limit of sensitivity of instruments like ASKAP or LOFAR. The resulting methodology, named COSMODEEP, allowed us to detect diffuse radio sources and to localize their position within large images thanks to a tiling based procedure with an accuracy of around the 90 per cent (i.e.…”

mentioning

confidence: 99%

Convolutional deep denoising autoencoders for radio astronomical images

Gheller

Vazza

2021

Monthly Notices of the Royal Astronomical Society

View full text Add to dashboard Cite

We apply a Machine Learning technique known as Convolutional Denoising Autoencoder to denoise synthetic images of state-of-the-art radio telescopes, with the goal of detecting the faint, diffused radio sources predicted to characterise the radio cosmic web. In our application, denoising is intended to address both the reduction of random instrumental noise and the minimization of additional spurious artefacts like the sidelobes, resulting from the aperture synthesis technique. The effectiveness and the accuracy of the method are analysed for different kinds of corrupted input images, together with its computational performance. Specific attention has been devoted to create realistic mock observations for the training, exploiting the outcomes of cosmological numerical simulations, to generate images corresponding to LOFAR HBA 8 hours observations at 150 MHz. Our autoencoder can effectively denoise complex images identifying and extracting faint objects at the limits of the instrumental sensitivity. The method can efficiently scale on large datasets, exploiting high performance computing solutions, in a fully automated way (i.e. no human supervision is required after training). It can accurately perform image segmentation, identifying low brightness outskirts of diffused sources, proving to be a viable solution for detecting challenging extended objects hidden in noisy radio observations.

show abstract

Deep transfer learning for the classification of variable sources

Cited by 5 publications

References 60 publications

A New Period Determination Method for Periodic Variable Stars

A New Period Determination Method for Periodic Variable Stars

A White Dwarf Search Model Based on a Deep Transfer-learning Method

Convolutional deep denoising autoencoders for radio astronomical images

Contact Info

Product

Resources

About