Explainable machine learning classification of \textit{Chandra} X-ray sources: SHAP analysis of multi-wavelength features

TL;DR

This paper applies explainable machine learning, specifically SHAP analysis, to classify Chandra X-ray sources and interpret feature contributions, revealing decision boundaries for different astronomical object classes.

Contribution

It introduces the use of SHAP for interpreting ML classifications of large-scale astronomical data, providing insights into feature importance and decision boundaries.

Findings

Infrared-optical and X-ray boundaries distinguish AGN and stars.

Infrared-X-ray boundaries help identify YSOs.

The study demonstrates the effectiveness of XAI in astrophysical data analysis.

Abstract

Extensive astronomical surveys, like those conducted with the {\em Chandra} X-ray Observatory, detect hundreds of thousands of unidentified cosmic sources. Machine learning (ML) methods offer an efficient, probabilistic approach to classify them, which can be useful for making discoveries and conducting deeper studies. In earlier work, we applied the LightGBM (ML model) to classify 277,069 {\em Chandra} point sources into eight categories: active galactic nuclei (AGN), X-ray emitting stars, young stellar objects (YSO), high-mass X-ray binaries, low-mass X-ray binaries, ultraluminous X-ray sources, cataclysmic variables, and pulsars. In this work, we present the classification table of 54,770 robustly classified sources (over $3\sigma$ confidence), including 14,066 sources at $>4\sigma$ significance. To ensure classification reliability and gain a deeper insight, we investigate the multiwavelength feature relationships learned by the LightGBM model, focusing on AGNs, Stars, and YSOs. We employ Explainable Artificial Intelligence (XAI) techniques, specifically, SHapley Additive exPlanations (SHAP), to quantify the contribution of individual features and their interactions to the predicted classification probabilities. Among other things, we find infrared-optical and X-ray decision boundaries for separating AGN/Stars, and infrared-X-ray boundaries for YSOs. These results are crucial for estimating object classes even with limited multiwavelength data. This study represents one of the earliest applications of XAI to large-scale astronomical datasets, demonstrating ML models' potential for uncovering physically meaningful patterns in data in addition to classification. Finally, our publicly available, extensive, and interactive catalogue will be helpful to explore the contributions of features and their combinations in greater detail in the future.