Papers › Performant feature extraction for photometric time series
Performant feature extraction for photometric time series
Anastasia Lavrukhina, Konstantin Malanchev
The archive published only this paper's code-link row. Authors, date and abstract are from arXiv's metadata (CC0), read from the Kaggle arXiv metadata snapshot of 2026-09-12 where its title matched the archive's; the title is the archive's.
Astronomy is entering the era of large surveys of the variable sky such as Zwicky Transient Facility (ZTF) and the forthcoming Legacy Survey of Space and Time (LSST) which are intended to produce up to a million alerts per night. Such an amount of photometric data requires efficient light-curve pre-processing algorithms for the purposes of subsequent data quality cuts, classification, and characterization analysis. In this work, we present the new library "light-curve" for Python and Rust, which is intended for feature extraction from light curves of variable astronomical sources. The library is suitable for machine learning classification problems: it provides a fast implementation of feature extractors, which outperforms other public available codes, and consists of dozens features describing shape, magnitude distribution, and periodic properties of light curves. It includes not only features which had been shown to provide a high performance in classification tasks, but also new features we developed to improve classification quality of selected types of objects. The "light-curve" library is currently used by the ANTARES, AMPEL, and Fink broker systems for analyzing the ZTF alert stream, and has been selected for use with the LSST.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Results from the paper archive 2025-07-28
No leaderboard rows for this paper in the archive.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections