Browsing by Author "Protopapas, P."

Now showing 1 - 7 of 7
  • Thumbnail Image
    Item
    An improved quasar detection method in EROS-2 and MACHO LMC data sets
    (2012) Pichara Baksai, Karim Elías; Protopapas, P.; Kim, D.-W.; Marquette, J.-B.; Tisserand, P.
  • Thumbnail Image
    Item
    An Information Theory Approach on Deciding Spectroscopic Follow-ups
    (2020) Astudillo, J.; Protopapas, P.; Pichara Baksai, Karim Elías; Huijse, P.
  • No Thumbnail Available
    Item
    ASTROMER A transformer-based embedding for the representation of light curves
    (2023) Donoso-Oliva, C.; Becker, I.; Protopapas, P.; Cabrera-Vives, G.; Vishnu, M.; Vardhan, H.
    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.
  • Thumbnail Image
    Item
    Meta-classification for variable stars
    (2016) Pichara Baksai, Karim Elías; Protopapas, P.; Leon, D.
  • Thumbnail Image
    Item
    Multiband embeddings of light curves
    (2025) Becker Troncoso, Ignacio Eduardo Pablo; Protopapas, P.; Catelan, Márcio; Pichara, K.
    In this work, we propose a novel ensemble of recurrent neural networks (RNNs) that considers the multiband and non-uniform cadence without having to compute complex features. Our proposed model consists of an ensemble of RNNs, which do not require the entire light curve to perform inference, making the inference process simpler. The ensemble is able to adapt to varying numbers of bands, tested on three real light curve datasets, namely Gaia, Pan-STARRS1, and ZTF, to demonstrate its potential for generalization. We also show the capabilities of deep learning to perform not only classification, but also regression of physical parameters such as effective temperature and radius. Our ensemble model demonstrates superior performance in scenarios with fewer observations, thus providing potential for early classification of sources from facilities such as Vera C. Rubin Observatory's LSST. The results underline the model's effectiveness and flexibility, making it a promising tool for future astronomical surveys. Our research has shown that a multitask learning approach can enrich the embeddings obtained by the models, making them instrumental to solve additional tasks, such as determining the orbital parameters of binary systems or estimating parameters for object types beyond periodic ones.
  • No Thumbnail Available
    Item
    Scalable end-to-end recurrent neural network for variable star classification
    (OUP, 2020) Becker Troncoso, Ignacio; Pichara Baksai, Karim Elías; Catelan, Márcio; Protopapas, P.; Aguirre Orellana, Carlos Alfonso; Nikzat, Fatemeh
    During the last decade, considerable effort has been made to perform automatic classification of variable stars using machine-learning techniques. Traditionally, light curves are represented as a vector of descriptors or features used as input for many algorithms. Some features are computationally expensive, cannot be updated quickly and hence for large data sets such as the LSST cannot be applied. Previous work has been done to develop alternative unsupervised feature extraction algorithms for light curves, but the cost of doing so still remains high. In this work, we propose an end-to-end algorithm that automatically learns the representation of light curves that allows an accurate automatic classification. We study a series of deep learning architectures based on recurrent neural networks and test them in automated classification scenarios. Our method uses minimal data pre-processing, can be updated with a low computational cost for new observations and light curves, and can scale up to massive data sets. We transform each light curve into an input matrix representation whose elements are the differences in time and magnitude, and the outputs are classification probabilities. We test our method in three surveys: OGLE-III, Gaia, and WISE. We obtain accuracies of about 95 per cent in the main classes and 75 per cent in the majority of subclasses. We compare our results with the Random Forest classifier and obtain competitive accuracies while being faster and scalable. The analysis shows that the computational complexity of our approach grows up linearly with the light-curve size, while the traditional approach cost grows as Nlog (N).
  • Thumbnail Image
    Item
    Streaming classification of variable stars
    (OUP, 2019) Zorich, L; Pichara Baksai, Karim Elías; Protopapas, P.
    In the last years, automatic classification of variable stars has received substantial attention. Using machine learning techniques for this task has proven to be quite useful. Typically, machine learning classifiers used for this task require to have a fixed training set, and the training process is performed offline. Upcoming surveys such as the Large Synoptic Survey Telescope will generate new observations daily, where an automatic classification system able to create alerts online will be mandatory. A system with those characteristics must be able to update itself incrementally. Unfortunately, after training, most machine learning classifiers do not support the inclusion of new observations in light curves, they need to re-train from scratch. Naively re-training from scratch is not an option in streaming settings, mainly because of the expensive pre-processing routines required to obtain a vector representation of light curves (features) each time we include new observations. In this work, we propose a streaming probabilistic classification model; it uses a set of newly designed features that work incrementally. With this model, we can have a machine learning classifier that updates itself in real time with new observations. To test our approach, we simulate a streaming scenario with light curves from Convention, Rotation and planetary Transits (CoRoT), Orbital Gravitational Lensing Experiment (OGLE), and Massive Compact Halo Object (MACHO) catalogues. Results show that our model achieves high classification performance, staying an order of magnitude faster than traditional classification approaches.