arXiv subjects

T. A. Semenikhin

Publications and source records attributed to T. A. Semenikhin.

5 recordsLinked to original sources

arXiv2026

Superluminous supernova search with PineForest

The advent of wide-field astronomical surveys has made available large and complex data sets. However, the process of discovery and interpretation of each potentially new astronomical source is, many times, still handcrafted. In this context, machine learning algorithms have emerged as a powerful tool to mine large data sets and lower the burden on the domain expert. Active learning strategies are specially good in this task. In this article, we used the PineForest algorithm to search for superluminous supernova (SLSN) candidates in the Zwicky Transient Facility data releases. Starting from a data set of $\sim$14 million objects, and using eight previously confirmed SLSN light curves as priors, we found seven SLSN candidates. In the course of this search, we posted to the Transient Name Server three previously unreported transients: AT 2018moa and AT 2018mob as SLSN candidates, and AT 2018mpg as a possible supernova. We also discovered a re-brightening of the SLSN-I SN 2018fcg approximately 1300 days after its main burst, which poses an interesting problem regarding its origin. This study represents the first application of the PineForest algorithm for the targeted search of rare astronomical transients, specifically SLSNe.

astro-ph.IM↗

arXiv2024

Real-bogus scores for active anomaly detection

In the task of anomaly detection in modern time-domain photometric surveys, the primary goal is to identify astrophysically interesting, rare, and unusual objects among a large volume of data. Unfortunately, artifacts -- such as plane or satellite tracks, bad columns on CCDs, and ghosts -- often constitute significant contaminants in results from anomaly detection analysis. In such contexts, the Active Anomaly Discovery (AAD) algorithm allows tailoring the output of anomaly detection pipelines according to what the expert judges to be scientifically interesting. We demonstrate how the introduction real-bogus scores, obtained from a machine learning classifier, improves the results from AAD. Using labeled data from the SNAD ZTF knowledge database, we train four real-bogus classifiers: XGBoost, CatBoost, Random Forest, and Extremely Randomized Trees. All the models perform real-bogus classification with similar effectiveness, achieving ROC-AUC scores ranging from 0.93 to 0.95. Consequently, we select the Random Forest model as the main model due to its simplicity and interpretability. The Random Forest classifier is applied to 67 million light curves from ZTF DR17. The output real-bogus score is used as an additional feature for two anomaly detection algorithms: static Isolation Forest and AAD. While results from Isolation Forest remained unchanged, the number of artifacts detected by the active approach decreases significantly with the inclusion of the real-bogus score, from 27 to 3 out of 100. We conclude that incorporating the real-bogus classifier result as an additional feature in the active anomaly detection pipeline significantly reduces the number of artifacts in the outputs, thereby increasing the incidence of astrophysically interesting objects presented to human experts.

astro-ph.IM↗

arXiv2024

Coniferest: a complete active anomaly detection framework

We present coniferest, an open source generic purpose active anomaly detection framework written in Python. The package design and implemented algorithms are described. Currently, static outlier detection analysis is supported via the Isolation forest algorithm. Moreover, Active Anomaly Discovery (AAD) and Pineforest algorithms are available to tackle active anomaly detection problems. The algorithms and package performance are evaluated on a series of synthetic datasets. We also describe a few success cases which resulted from applying the package to real astronomical data in active anomaly detection tasks within the SNAD project.

astro-ph.IM↗

arXiv2024

SNAD catalogue of M-dwarf flares from the Zwicky Transient Facility

Most of the stars in the Universe are M spectral class dwarfs, which are known to be the source of bright and frequent stellar flares. In this paper, we propose new approaches to discover M-dwarf flares in ground-based photometric surveys. We employ two approaches: a modification of a traditional method of parametric fit search and a machine learning algorithm based on active anomaly detection. The algorithms are applied to Zwicky Transient Facility (ZTF) data release 8, which includes the data from the ZTF high-cadence survey, allowing us to reveal flares lasting from minutes to hours. We analyze over 35 million ZTF light curves and visually scrutinize 1168 candidates suggested by the algorithms to filter out artifacts, occultations of a star by an asteroid, and other types of known variable objects. The result of this analysis is the largest catalogue of ZTF flaring stars to date, representing 134 flares with amplitudes ranging from -0.2 to -4.6 magnitudes, including repeated flares. Using Pan-STARRS DR2 colors, we assign a spectral subclass to each object in the sample. For 13 flares with well-sampled light curves and available geometric distances from Gaia DR3, we estimate the bolometric energy. This research shows that the proposed methods combined with the ZTF's cadence strategy are suitable for identifying M-dwarf flares and other fast transients, allowing for the extraction of significant astrophysical information from their light curves.

astro-ph.SR↗

arXiv2023

Reduction of supernova light curves by vector Gaussian processes

Bolometric light curves play an important role in understanding the underlying physics of various astrophysical phenomena, as they allow for a comprehensive modeling of the event and enable comparison between different objects. However, constructing these curves often requires the approximation and extrapolation from multicolor photometric observations. In this study, we introduce vector Gaussian processes as a new method for reduction of supernova light curves. This method enables us to approximate vector functions, even with inhomogeneous time-series data, while considering the correlation between light curves in different passbands. We applied this methodology to a sample of 29 superluminous supernovae (SLSNe) assembled using the Open Supernova Catalog. Their multicolor light curves were approximated using vector Gaussian processes. Subsequently, under the black-body assumption for the SLSN spectra at each moment of time, we reconstructed the bolometric light curves. The vector Gaussian processes developed in this work are accessible via the Python library gp-multistate-kernel on GitHub. Our approach provides an efficient tool for analyzing light curve data, opening new possibilities for astrophysical research.

astro-ph.IM↗