arXiv subjects

Juan Rafael Martínez-Galarza

Publications and source records attributed to Juan Rafael Martínez-Galarza.

13 recordsLinked to original sources

arXiv2026

The Chandra-Gaia Catalog of Counterparts: Resolving ambiguous Gaia matches to X-ray sources in the Chandra Source Catalog using Machine Learning

We present a framework to cross-match sources from the Chandra Source Catalog (CSC v2.1) with optical sources from Gaia Data Release 3. Unlike purely spatial approaches, we use source properties such as magnitudes, colors, and distances to identify true counterparts, detect chance coincidences, and resolve ambiguities when multiple plausible candidates exist. We define a training set of high-confidence matches using NWAY, a Bayesian cross-matching framework that accounts for positional errors and source densities. We train a gradient-boosted classifier (LightGBM) on a variety of features from both catalogs. Of the ~$254$k unique X-ray sources, we find counterparts for ~$113$k sources, of which plausible multiple counterparts are found for ~$7$k. We find no counterparts for ~$20$k sources for which separation-based cross-matching does find a match, and attribute half of these to chance coincidences. We validate the pipeline on the Chandra Orion Ultradeep Project (COUP), where the machine-learning matches reproduce 95% of NWAY cross-matches without using any positional information. We release a catalog of the ~$113$k Chandra-Gaia counterparts, together with ~$7$k alternative matches and ~$20$k ambiguous NWAY associations, supporting future population studies of sources detectable by both Chandra and Gaia. We discuss limitations and provide a generalization of the framework that is applicable in other cross-matching scenarios.

astro-ph.IM↗

arXiv2026

The Galaxy's Guide to the Tokenizer: A Benchmark for Scientific Foundation Models

Tokenization is central to adapting scientific data for transformer-based foundation models, yet its impact on learned representations remains poorly understood. We compare four tokenization strategies, Affine, AIM, JetFormer, and VQ-VAE, within a unified transformer framework for astronomical imaging. Using 640,000 galaxy images from the DESI Legacy Survey and a shared AstroPT backbone, we evaluate each method on reconstruction fidelity and prediction of physical properties. Our results reveal trade-offs across approaches. The flow-based JetFormer achieves higher reconstruction quality, while VQ-VAE yields strong probe performance for galaxy physical properties. Affine and AIM better preserve localized morphological information. We find that reconstruction and representation quality are decoupled, and no single method consistently performs best across the tasks considered here. By grounding our evaluation in independently measured physical quantities, we hope this study serves to highlight the potential of scientific data as a basis for constructing interpretable benchmarks for foundation models.

astro-ph.IM↗

arXiv2026

Extracting latent representations from X-ray spectra. Classification, regression, and accretion signatures of Chandra sources

Spectral signatures are crucial in the era of large X-ray surveys. Automatic machine learning methods have proven useful in this respect, but so far they have not been applied to large spectral datasets, such as the Chandra Source Catalog (CSC). This work aims to develop a compact and physically meaningful representation of Chandra X-ray spectra using deep learning. To verify that the learned representation captures relevant information, we evaluate it through classification, regression, and interpretability analyses, and measure the mutual information between spectral and time-domain properties of these sources, aiding in the future identification of transient events. We use a transformer-based autoencoder to compress X-ray spectra into representations in an 8-dimensional latent space. Astrophysical source types and physical summary statistics are compiled from external catalogs. We evaluate the learned representation in terms of spectral reconstruction accuracy, clustering performance on 8 known astrophysical source classes, and correlation with physical quantities such as hardness ratios and hydrogen column densities ($N_H$). Upon reconstruction, clustering in the latent space yields a balanced classification accuracy of $\sim$40% across the 8 source classes, increasing to $\sim$69% when restricted to AGNs and stellar-mass compact objects exclusively. Moreover, latent features correlate with spectral and temporal properties, suggesting that the compressed representation captures physically relevant information. Features learned directly from X-ray spectra capture relevant physical information as effectively as human-extracted features that require additional computations. They can be used for both classification and regression in large surveys, and also share mutual information with time-domain properties. The method can be adapted to existing and upcoming X-ray catalogs.

astro-ph.IM↗

arXiv2025

Modeling X-ray photon pile-up with a normalizing flow

The dynamic range of imaging detectors flown on-board X-ray observatories often only covers a limited flux range of extrasolar X-ray sources. The analysis of bright X-ray sources is complicated by so-called pile-up, which results from high incident photon flux. This nonlinear effect distorts the measured spectrum, resulting in biases in the inferred physical parameters, and can even lead to a complete signal loss in extreme cases. Piled-up data are commonly discarded due to resulting intractability of the likelihood. As a result, a large number of archival observations remain underexplored. We present a machine learning solution to this problem, using a simulation-based inference framework that allows us to estimate posterior distributions of physical source parameters from piled-up eROSITA data. We show that a normalizing flow produces better-constrained posterior densities than traditional mitigation techniques, as more data can be leveraged. We consider model- and calibration-dependent uncertainties and the applicability of such an algorithm to real data in the eROSITA archive.

astro-ph.HE↗

arXiv2025

Learning Representations of Event Time Series with Sparse Autoencoders for Anomaly Detection, Similarity Search, and Unsupervised Classification

Event time series are sequences of discrete events occurring at irregular time intervals, each associated with a domain-specific observational modality. They are common in domains such as high-energy astrophysics, computational social science, cybersecurity, finance, healthcare, neuroscience, and seismology. Their unstructured and irregular structure poses significant challenges for extracting meaningful patterns and identifying salient phenomena using conventional techniques. We propose novel two- and three-dimensional tensor representations for event time series, coupled with sparse autoencoders that learn physically meaningful latent representations. These embeddings support a variety of downstream tasks, including anomaly detection, similarity-based retrieval, semantic clustering, and unsupervised classification. We demonstrate our approach on a real-world dataset from X-ray astronomy, showing that these representations successfully capture temporal and spectral signatures and isolate diverse classes of X-ray transients. Our framework offers a flexible, scalable, and generalizable solution for analyzing complex, irregular event time series across scientific and industrial domains.

cs.LG↗

arXiv2025

Representation Learning for Time-Domain High-Energy Astrophysics: Discovery of Extragalactic Fast X-ray Transient XRT 200515

We present a novel representation learning method for downstream tasks like anomaly detection, unsupervised classification, and similarity searches in high-energy data sets. This enabled the discovery of a new extragalactic fast X-ray transient (FXT) in Chandra archival data, XRT 200515, a needle-in-the-haystack event and the first Chandra FXT of its kind. Recent serendipitous discoveries in X-ray astronomy, including FXTs from binary neutron star mergers and an extragalactic planetary transit candidate, highlight the need for systematic transient searches in X-ray archives. We introduce new event file representations, E-t maps and E-t-dt cubes, that effectively encode both temporal and spectral information, enabling the seamless application of machine learning to variable-length event file time series. Our unsupervised learning approach employs PCA or sparse autoencoders to extract low-dimensional, informative features from these data representations, followed by clustering in the embedding space with DBSCAN. New transients are identified within transient-dominant clusters or through nearest-neighbour searches around known transients, producing a catalogue of 3559 candidates (3447 flares and 112 dips). XRT 200515 exhibits unique temporal and spectral variability, including an intense, hard <10s initial burst, followed by spectral softening in an ~800s oscillating tail. We interpret XRT 200515 as either the first giant magnetar flare observed at low X-ray energies or the first extragalactic Type I X-ray burst from a faint, previously unknown low-mass X-ray binary in the LMC. Our method extends to data sets from other observatories such as XMM-Newton, Swift-XRT, eROSITA, Einstein Probe, and upcoming missions like AXIS.

astro-ph.HE↗

arXiv2024

The Multimodal Universe: Enabling Large-Scale Machine Learning with 100TB of Astronomical Scientific Data

We present the MULTIMODAL UNIVERSE, a large-scale multimodal dataset of scientific astronomical data, compiled specifically to facilitate machine learning research. Overall, the MULTIMODAL UNIVERSE contains hundreds of millions of astronomical observations, constituting 100\,TB of multi-channel and hyper-spectral images, spectra, multivariate time series, as well as a wide variety of associated scientific measurements and "metadata". In addition, we include a range of benchmark tasks representative of standard practices for machine learning methods in astrophysics. This massive dataset will enable the development of large multi-modal models specifically targeted towards scientific applications. All codes used to compile the MULTIMODAL UNIVERSE and a description of how to access the data is available at https://github.com/MultimodalUniverse/MultimodalUniverse

astro-ph.IM↗

arXiv2024

Unsupervised Machine Learning for the Classification of Astrophysical X-ray Sources

The automatic classification of X-ray detections is a necessary step in extracting astrophysical information from compiled catalogs of astrophysical sources. Classification is useful for the study of individual objects, statistics for population studies, as well as for anomaly detection, i.e., the identification of new unexplored phenomena, including transients and spectrally extreme sources. Despite the importance of this task, classification remains challenging in X-ray astronomy due to the lack of optical counterparts and representative training sets. We develop an alternative methodology that employs an unsupervised machine learning approach to provide probabilistic classes to Chandra Source Catalog sources with a limited number of labeled sources, and without ancillary information from optical and infrared catalogs. We provide a catalog of probabilistic classes for 8,756 sources, comprising a total of 14,507 detections, and demonstrate the success of the method at identifying emission from young stellar objects, as well as distinguishing between small-scale and large-scale compact accretors with a significant level of confidence. We investigate the consistency between the distribution of features among classified objects and well-established astrophysical hypotheses such as the unified AGN model. This provides interpretability to the probabilistic classifier. Code and tables are available publicly through GitHub. We provide a web playground for readers to explore our final classification at https://umlcaxs-playground.streamlit.app.

astro-ph.IM↗

arXiv2023

Linking Anomalous Behaviour with Stellar Properties: An Unsupervised Exploration of TESS Light Curves

With the upcoming plethora of astronomical time-domain datasets and surveys, anomaly detection as a way to discover new types of variable stars and transients has inspired a new wave of research. Yet, the fundamental definition of what constitutes an anomaly and how this depends on the overall properties of the population of light curves studied remains a discussed issue. Building on a previous study focused on Kepler light curves, we present an analysis that uses the Unsupervised Random Forest to search for anomalies in TESS light curves. We provide a catalogue of anomalous light curves, classify them according to their variability characteristics and associate their anomalous nature to any particular evolutionary stage or astrophysical configuration. For anomalies belonging to known classes (e.g. eclipsing binaries), we have investigated which physical parameters drive the anomaly score. We find a combination of unclassified anomalies and objects of a known class with outlying physical configurations, such as rapid pulsators, deep eclipsing binaries of long periods, and irregular light curves due to obscuration in YSOs. Remarkably, we find that the set of anomalous types differ between the Kepler and TESS datasets, indicating that the overall properties of the parent population are an important driver of anomalous behaviour.

astro-ph.SR↗

arXiv2021

A method for finding anomalous astronomical light curves and their analogs

Our understanding of the Universe has profited from deliberate, targeted studies of known phenomena, as well as from serendipitous, unexpected discoveries, such as the discovery of a complex variability pattern in the direction of KIC 8462852 (Boyajian's star). Upcoming surveys, such as the Vera C. Rubin Observatory Legacy Survey of Space and Time (LSST), will explore the parameter space of astrophysical transients at all time scales, and offer the opportunity to discover even more extreme examples of unexpected phenomena. We investigate strategies to identify novel objects and to contextualize them within large time-series data sets in order to facilitate the discovery of new classes of objects, as well as the physical interpretation of their anomalous nature. We develop a method that combines tree-based and manifold-learning algorithms for anomaly detection in order to perform two tasks: 1) identify and rank anomalous objects in a time-domain dataset; and 2) group those anomalies according to their similarity in order to identify analogs. We achieve the latter by combining an anomaly score from a tree-based method with a dimensionality manifold-learning reduction strategy. Clustering in the reduced space allows for the successful identification of anomalies and analogs. We also assess the impact of pre-processing and feature engineering schemes and investigate the astrophysical nature of the objects that our models identify as anomalous by augmenting the Kepler data with Gaia color and luminosity information. We find that multiple models, used in combination, are a promising strategy to identify novel light curves and light curve families.

astro-ph.SR↗

arXiv2018

The Photometric LSST Astronomical Time-series Classification Challenge (PLAsTiCC): Data set

The Photometric LSST Astronomical Time Series Classification Challenge (PLAsTiCC) is an open data challenge to classify simulated astronomical time-series data in preparation for observations from the Large Synoptic Survey Telescope (LSST), which will achieve first light in 2019 and commence its 10-year main survey in 2022. LSST will revolutionize our understanding of the changing sky, discovering and measuring millions of time-varying objects. In this challenge, we pose the question: how well can we classify objects in the sky that vary in brightness from simulated LSST time-series data, with all its challenges of non-representativity? In this note we explain the need for a data challenge to help classify such astronomical sources and describe the PLAsTiCC data set and Kaggle data challenge, noting that while the references are provided for context, they are not needed to participate in the challenge.

astro-ph.IM↗

arXiv2018

The AGN Luminosity Fraction in Merging Galaxies

Galaxy mergers are key events in galaxy evolution, often causing massive starbursts and fueling active galactic nuclei (AGN). In these highly dynamic systems, it is not yet precisely known how much starbursts and AGN respectively contribute to the total luminosity, at what interaction stages they occur, and how long they persist. Here we estimate the fraction of the bolometric infrared (IR) luminosity that can be attributed to AGN by measuring and modeling the full ultraviolet to far-infrared spectral energy distributions (SEDs) in up to 33 broad bands for 24 merging galaxies with the Code for Investigating Galaxy Emission. In addition to a sample of 12 confirmed AGN in late-stage mergers, found in the $Infrared$ $Array$ $Satellite$ Revised Bright Galaxy Sample or Faint Source Catalog, our sample includes a comparison sample of 12 galaxy mergers from the $Spitzer$ Interacting Galaxies Survey, mostly early-stage. We perform identical SED modeling of simulated mergers to validate our methods, and we supplement the SED data with mid-IR spectra of diagnostic lines obtained with $Spitzer$ InfraRed Spectrograph. The estimated AGN contributions to the IR luminosities vary from system to system from 0% up to 91% but are significantly greater in the later-stage, more luminous mergers, consistent with what is known about galaxy evolution and AGN triggering.

astro-ph.GA↗

arXiv2014

The total infrared luminosity may significantly overestimate the star formation rate of recently quenched galaxies

The total infrared (IR) luminosity is very useful for estimating the star formation rate (SFR) of galaxies, but converting the IR luminosity into an SFR relies on assumptions that do not hold for all galaxies. We test the effectiveness of the IR luminosity as an SFR indicator by applying it to synthetic spectral energy distributions generated from three-dimensional hydrodynamical simulations of isolated disc galaxies and galaxy mergers. In general, the SFR inferred from the IR luminosity agrees well with the true instantaneous SFR of the simulated galaxies. However, for the major mergers in which a strong starburst is induced, the SFR inferred from the IR luminosity can overestimate the instantaneous SFR during the post-starburst phase by greater than two orders of magnitude. Even though the instantaneous SFR decreases rapidly after the starburst, the stars that were formed in the starburst remain dust-obscured and thus produce significant IR luminosity. Consequently, use of the IR luminosity as an SFR indicator may cause one to conclude that post-starburst galaxies are still star-forming, whereas in reality, star formation was recently quenched.

astro-ph.GA↗