Identification of problematic epochs in astronomical time series through transfer learning

TL;DR

This paper introduces a transfer learning-based method combining deep neural networks and k-nearest neighbors to detect and remove outliers in astronomical time series, enhancing data quality for large surveys.

Contribution

The novel approach leverages a pre-trained EfficientNet and k-NN to identify problematic epochs, improving outlier detection in astronomical light curves.

Findings

Effectively identifies and removes artifacts from VST time series.

Improves data quality and reliability for astronomical observations.

Suitable for large-scale surveys like LSST.

Abstract

We present a novel method for detecting outliers in astronomical time series based on the combination of a deep neural network and a k-nearest neighbor algorithm with the aim of identifying and removing problematic epochs in the light curves of astronomical objects. We use an EfficientNet network pre-trained on ImageNet as a feature extractor and perform a k-nearest neighbor search in the resulting feature space to measure the distance from the first neighbor for each image. If the distance is above the one obtained for a stacked image, we flag the image as a potential outlier. We apply our method to time series obtained from the VLT Survey Telescope (VST) monitoring campaign of the Deep Drilling Fields of the Vera C. Rubin Legacy Survey of Space and Time (LSST). We show that our method can effectively identify and remove artifacts from the VST time series and improve the quality and reliability of the data. This approach may prove very useful in sight of the amount of data that will be provided by the LSST, which will prevent the inspection of individual light curves. We also discuss the advantages and limitations of our method and suggest possible directions for future work.