ASTROMER

A transformer-based embedding for the representation of light curves^★

¹ Department of Computer Science, Universidad de Concepcion, Concepcion 4070386, Chile
e-mail: cridonoso@inf.udec.cl
² Department of Computer Science, Pontificia Universidad Catolica de Chile, Macul, Santiago 7820436, Chile
³ Inst. for Applied Computational Science, Harvard University, Cambridge, MA 02138, USA
⁴ Millennium Institute of Astrophysics (MAS), Nuncio Monsenor Sotero Sanz 100, Providencia, Santiago, Chile
⁵ Univ. AI, Singapore 050531, Singapore

Received: 2 May 2022
Accepted: 31 October 2022

Abstract

Taking inspiration from natural language embeddings, we present ASTROMER, a transformer-based model to create representations of light curves. ASTROMER was pre-trained in a self-supervised manner, requiring no human-labeled data. We used millions of R-band light sequences to adjust the ASTROMER weights. The learned representation can be easily adapted to other surveys by re-training ASTROMER on new sources. The power of ASTROMER consists in using the representation to extract light curve embeddings that can enhance the training of other models, such as classifiers or regressors. As an example, we used ASTROMER embeddings to train two neural-based classifiers that use labeled variable stars from MACHO, OGLE-III, and ATLAS. In all experiments, ASTROMER-based classifiers outperformed a baseline recurrent neural network trained on light curves directly when limited labeled data were available. Furthermore, using ASTROMER embeddings decreases the computational resources needed while achieving state-of-the-art results. Finally, we provide a Python library that includes all the functionalities employed in this work.