Clustering of Astronomical Transient Candidates Using Deep Variational Embedding

Astorga, Nicolás; Huijse, P.; Estévez, P. A.; Förster, F.

doi:10.1109/ijcnn.2018.8489358

Cited by 3 publications

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several past studies have moved to this direction, including the exploitation of cluster analysis to surrogate radio-frequency based scene descriptors that are achieved from DRAO (Dominion Radio Astrophysical Observatory) into normal and novel events [22]. Besides, Astorga et al [23] make use of VADE (Deep Variational Embedding) to cluster astronomical transient candidates. A similar work introduced by Reis et al [24] confirms the benefit of data clustering for the next generation of sky survey with which a huge amount of data will be witnessed.…”

Section: Introductionmentioning

confidence: 99%

Profiling Astronomical Objects Using Unsupervised Learning Approach

Sangpetch¹,

Boongoen²,

Iam-On³

2023

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

Attempts to determine characters of astronomical objects have been one of major and vibrant activities in both astronomy and data science fields. Instead of a manual inspection, various automated systems are invented to satisfy the need, including the classification of light curve profiles. A specific Kaggle competition, namely Photometric LSST Astronomical Time-Series Classification Challenge (PLAsTiCC), is launched to gather new ideas of tackling the abovementioned task using the data set collected from the Large Synoptic Survey Telescope (LSST) project. Almost all proposed methods fall into the supervised family with a common aim to categorize each object into one of pre-defined types. As this challenge focuses on developing a predictive model that is robust to classifying unseen data, those previous attempts similarly encounter the lack of discriminate features, since distribution of training and actual test datasets are largely different. As a result, well-known classification algorithms prove to be sub-optimal, while more complicated feature extraction techniques may help to slightly boost the predictive performance. Given such a burden, this research is set to explore an unsupervised alternative to the difficult quest, where common classifiers fail to reach the 50% accuracy mark. A clustering technique is exploited to transform the space of training data, from which a more accurate classifier can be built. In addition to a single clustering framework that provides a comparable accuracy to the front runners of supervised learning, a multiple-clustering alternative is also introduced with improved performance. In fact, it is able to yield a higher accuracy rate of 58.32% from 51.36% that is obtained using a simple clustering. For this difficult problem, it is rather good considering for those achieved by well-known models like support vector machine (SVM) with 51.80% and Naïve Bayes (NB) with only 2.92%.

show abstract

Section: Introductionmentioning

confidence: 99%

Profiling Astronomical Objects Using Unsupervised Learning Approach

Sangpetch¹,

Boongoen²,

Iam-On³

2023

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

show abstract

“…extensively in astronomical data applications, such as light-curve and imagebased classification (e.g., [5][6][7][8]), clustering [9,10], physical parameter estimation [11][12][13], and outlier detection [14][15][16][17]. The Vera C. Rubin Community Brokers: ALeRCE [18], AMPEL [19], ANTARES [20], BABAMUL, Fink [21], Lasair [22], and Pitt-Google 2 are processing or will process massive amounts of data that is annotated with cross-matches, ML model predictions, and/or other information that is distributed to the community.…”

mentioning

confidence: 99%

ATAT: Astronomical Transformer for time series And Tabular data

Astorga

Reyes

Cabrera

et al. 2023

Preprint

View full text Add to dashboard Cite

We present ATAT, the Astronomical Transformer for time series And Tabular data, a classification model that receives as input both light-curves and tabular data from astronomical sources. ATAT consists of a light-curve Transformer with a new time modulation that encodes the time of each observation, and a feature Transformer that uses a Quantile Feature Tokenizer. This model was conceived by the ALeRCE alert broker in the context of the recent Extended LSST Astronomical Time-Series Classification Challenge (ELAsTiCC). ATAT outperforms previous decision tree-based ensemble approaches in terms of classification when trained over the ELAsTiCC dataset. Importantly, some of its variants do not require human-engineered features, with significantly reduced inference computational times (400x faster). The use of Transformer multimodal architectures, combining light-curve and tabular data, opens new possibilities for classifying alerts from a new generation of large etendue telescopes, such as the Vera C. Rubin Observatory, in real-world brokering scenarios.

show abstract

ATAT: Astronomical Transformer for time series and Tabular data

Cabrera-Vives,

Moreno-Cartagena,

Astorga

et al. 2024

A&A

View full text Add to dashboard Cite

The advent of next-generation survey instruments, such as the Vera C. Rubin Observatory and its Legacy Survey of Space and Time (LSST), is opening a window for new research in time-domain astronomy. The Extended LSST Astronomical Time-Series Classification Challenge (ELAsTiCC) was created to test the capacity of brokers to deal with a simulated LSST stream. Our aim is to develop a next-generation model for the classification of variable astronomical objects. We describe ATAT, the Astronomical Transformer for time series And Tabular data, a classification model conceived by the ALeRCE alert broker to classify light curves from next-generation alert streams. ATAT was tested in production during the first round of the ELAsTiCC campaigns. ATAT consists of two transformer models that encode light curves and features using novel time modulation and quantile feature tokenizer mechanisms, respectively. ATAT was trained on different combinations of light curves, metadata, and features calculated over the light curves. We compare ATAT against the current ALeRCE classifier, a balanced hierarchical random forest (BHRF) trained on human-engineered features derived from light curves and metadata. When trained on light curves and metadata, ATAT achieves a macro F1 score of $82.9 0.4$ in 20 classes, outperforming the BHRF model trained on 429 features, which achieves a macro F1 score of $79.4 The use of transformer multimodal architectures, combining light curves and tabular data, opens new possibilities for classifying alerts from a new generation of large etendue telescopes, such as the Vera C. Rubin Observatory, in real-world brokering scenarios.

show abstract

Clustering of Astronomical Transient Candidates Using Deep Variational Embedding

Cited by 3 publications

References 9 publications

Profiling Astronomical Objects Using Unsupervised Learning Approach

Profiling Astronomical Objects Using Unsupervised Learning Approach

ATAT: Astronomical Transformer for time series And Tabular data

ATAT: Astronomical Transformer for time series and Tabular data

Contact Info

Product

Resources

About