Papers › On Neural Architectures for Astronomical Time-series Classification with Application...
On Neural Architectures for Astronomical Time-series Classification with Application to Variable Stars
Sara Jamal, Joshua S. Bloom
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.
Despite the utility of neural networks (NNs) for astronomical time-series classification, the proliferation of learning architectures applied to diverse datasets has thus far hampered a direct intercomparison of different approaches. Here we perform the first comprehensive study of variants of NN-based learning and inference for astronomical time-series, aiming to provide the community with an overview on relative performance and, hopefully, a set of best-in-class choices for practical implementations. In both supervised and self-supervised contexts, we study the effects of different time-series-compatible layer choices, namely the dilated temporal convolutional neural network (dTCNs), Long-Short Term Memory (LSTM) NNs, Gated Recurrent Units (GRUs) and temporal convolutional NNs (tCNNs). We also study the efficacy and performance of encoder-decoder (i.e., autoencoder) networks compared to direct classification networks, different pathways to include auxiliary (non-time-series) metadata, and different approaches to incorporate multi-passband data (i.e., multiple time-series per source). Performance---applied to a sample of 17,604 variable stars from the MACHO survey across 10 imbalanced classes---is measured in training convergence time, classification accuracy, reconstruction error, and generated latent variables. We find that networks with Recurrent NN (RNNs) generally outperform dTCNs and, in many scenarios, yield to similar accuracy as tCNNs. In learning time and memory requirements, convolution-based layers are more performant. We conclude by discussing the advantages and limitations of deep architectures for variable star classification, with a particular eye towards next-generation surveys such as LSST, WFIRST and ZTF2.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
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