Search arXivSearch

arXiv · 2510.14102

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

Abstract

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.

Explore related subjects

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Nicolò Oreste Pinciroli Vago, Juan Rafael Martínez-Galarza, Roberta Amato. 2026-05-17. Extracting latent representations from X-ray spectra. Classification, regression, and accretion signatures of Chandra sources. https://doi.org/10.1051/0004-6361%2F202557384

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

Performance characterization of a new Structural and Thermal Architecture for a future spaceborne Closed-Cycle Dilution Refrigerator

A Structural and Thermal Model (STM) has been developed to support the new spaceborne Closed-Cycle Dilution Refrigerator (CCDR), which aims to provide continuous cooling at 100~mK for long-duration astrophysical missions. The STM is based on a hexapod architecture that ensures both thermal decoupling and mechanical robustness during launch. In this paper, we present the characterization of its thermal and mechanical performances. A dedicated experimental setup was used to investigate the thermal behavior of the STM across a broad temperature range. The study reveals limitations of the collar design, with incomplete power interception from thermal boundary resistances and vibration test failure traced to defective strut gluing. These results guide the next STM iteration with optimized collar and strut assembly for reliable CCDR operation in space.

astro-ph.IM

The Simons Observatory: Development of a Pipeline to Detect Rapid Transients in Time-Ordered Data

We introduce a method for detecting astrophysical transients evolving on timescales of milliseconds to minutes using cosmic microwave background (CMB) survey telescopes. While previous transient searches in CMB data operate in map space, our pipeline directly processes the raw time-ordered data, enabling sensitivity to fast, dynamic signals. We integrate our detection approach into the Simons Observatory time-domain pipeline and assess the performance by injecting symmetric, stellar flare-like light curves into simulated observations. For events flaring with a timescale of 0.5 s, the pipeline detects $\gtrsim90$ % of events at flux densities of 800, 1150, 1650, and 4250\,mJy when measured in the 93, 145, 225, and 280 GHz bands respectively. At a fixed peak flux density, the pipeline more readily detects longer flares. The limiting flux density for 90 % completeness is four times lower for a $\ge5$ s flare than for a 0.5 s flare, while the flux density limits for $\gtrsim50$ % detection efficiency are comparable to the rms noise of the time-ordered data. We are able to determine the position of detected events in each observing band, with a positional uncertainty at the detection threshold comparable to the telescope resolution at that band. These results demonstrate the readiness of this pipeline for incorporation into upcoming Simons Observatory data analyses.

astro-ph.IM

Thermal conductivity of various CFRPs from 100 mK to 20 K

Carbon-fiber-reinforced polymers (CFRPs) are some of the most useful materials for building spacecraft and aerospace tools. They are especially valuable for systems that work at extremely cold (cryogenic) temperatures because they are strong, lightweight, and don't transfer heat easily. In this study, researchers measured how well heat moves through several different types of carbon fiber samples, specifically T300, T700, HS40, M55J, and IMA, at different fiber layouts and densities. These measurements were taken at ultra-cold temperatures ranging from 100 mK to 20 K. The team used a newly developed analysis method to calculate the thermal conductivity for each sample. Finally, they shared how each material behaved at different temperatures and compared their findings to previous research.

astro-ph.IM