Semi-supervised Learning for Detecting Inverse Compton Emission in Galaxy Clusters

TL;DR

This paper introduces a semi-supervised deep learning method using a conditional autoencoder to detect inverse Compton emission in galaxy clusters, outperforming traditional spectral fitting in identifying non-thermal IC signals.

Contribution

The study presents a novel semi-supervised deep learning approach with a conditional autoencoder trained on synthetic spectra to detect IC emission, addressing degeneracy issues in spectral analysis.

Findings

The method achieves a balanced accuracy of 0.64 in detecting IC emission.

It outperforms traditional spectral fitting and autoencoders in anomaly detection.

The approach provides a complementary tool to spectral fitting for IC detection.

Abstract

Inverse Compton (IC) emission associated with the non-thermal component of the intracluster medium (ICM) has been a long sought phenomenon in cluster physics. Traditional spectral fitting often suffers from the degeneracy between the two-temperature thermal spectrum (2T) and the one-temperature plus IC power-law spectrum (1T+IC). We present a semi-supervised deep learning approach to search for IC emission in galaxy clusters. We employ a conditional autoencoder (CAE), which is based on an autoencoder with latent representations trained to constrain the thermal parameters of the ICM. The algorithm is trained and tested using synthetic NuSTAR X-ray spectra with instrumental and astrophysical backgrounds included. The training data set only contains 2T spectra, which is more common than 1T+IC spectra. Anomaly detection is performed on the validation and test datasets, consisting of 2T spectra as the normal set and 1T+IC spectra as anomalies. With a threshold anomaly score, chosen based on cross-validation, our algorithm is able to identify spectra that contain an IC component in the test dataset, with a balanced accuracy (BAcc) of 0.64, which outperforms traditional spectral fitting (BAcc = 0.55) and ordinary autoencoder (BAcc = 0.55). Traditional spectral fitting is better at identifying IC cases among true IC spectra (a better recall), while IC predictions made by CAE have a higher chance of being true IC cases (a better precision), demonstrating their mutual complement to each other.