The hunt for new pulsating ultraluminous X-ray sources: a clustering approach

2025-07-20

AI Summary

A class of ultraluminous X-ray sources (ULXs) remains unconfirmed as pulsating ULXs (PULXs), despite exhibiting characteristics suggestive of neutron-star accretors. Method: We propose a prior-informed unsupervised clustering framework that constructs a multidimensional feature space from time-domain and spectral properties extracted from XMM-Newton observations. Crucially, we leverage known PULXs as anchor points to adaptively determine cluster separation thresholds, enabling high-confidence identification of candidate pulsators without performing computationally intensive blind pulse searches. Contribution/Results: The method efficiently identifies 85 independent PULX candidates, ~85% of which possess multiple archival observations—substantially enhancing the efficiency and feasibility of follow-up high-precision timing analyses. Our results demonstrate the viability and frontier value of AI-driven “similarity-based prediction” for classification in high-energy astrophysics, establishing a novel paradigm for source characterization beyond traditional periodicity detection.

Technology Category

• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Humans and AI: Crowd Sourcing and Human Computation
• Natural Language Processing: Information Extraction

Application Category

• Web Mining and Content Analysis: Normalization, clustering, classification, and summarization of Web text
• User Modeling, Personalization and Recommendation: Psychology-informed user models and recommender systems
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

The discovery of fast and variable coherent signals in a handful of ultraluminous X-ray sources (ULXs) testifies to the presence of super-Eddington accreting neutron stars, and drastically changed the understanding of the ULX class. Our capability of discovering pulsations in ULXs is limited, among others, by poor statistics. However, catalogues and archives of high-energy missions contain information which can be used to identify new candidate pulsating ULXs (PULXs). The goal of this research is to single out candidate PULXs among those ULXs which have not shown pulsations due to an unfavourable combination of factors. We applied an AI approach to an updated database of ULXs detected by XMM-Newton. We first used an unsupervised clustering algorithm to sort out sources with similar characteristics into two clusters. Then, the sample of known PULX observations has been used to set the separation threshold between the two clusters and to identify the one containing the new candidate PULXs. We found that only a few criteria are needed to assign the membership of an observation to one of the two clusters. The cluster of new candidate PULXs counts 85 unique sources for 355 observations, with $sim$85% of these new candidates having multiple observations. A preliminary timing analysis found no new pulsations for these candidates. This work presents a sample of new candidate PULXs observed by XMM-Newton, the properties of which are similar (in a multi-dimensional phase space) to those of the known PULXs, despite the absence of pulsations in their light curves. While this result is a clear example of the predictive power of AI-based methods, it also highlights the need for high-statistics observational data to reveal coherent signals from the sources in this sample and thus validate the robustness of the approach.

Problem

• Identifying new candidate pulsating ULXs using AI clustering
• Overcoming poor statistics in discovering ULX pulsations
• Validating AI-based predictions with high-statistics observational data

Innovation

• AI clustering for ULX classification
• Unsupervised algorithm identifies PULX candidates
• Multi-dimensional phase space similarity analysis