Neural network-based preprocessing to estimate the parameters of the X-ray emission of a single-temperature thermal plasma

TL;DR

This paper introduces a neural network method for estimating X-ray emission parameters of thermal plasmas, achieving high accuracy and reducing preprocessing efforts for spectral data analysis.

Contribution

The study develops a neural network trained on simulated spectra to accurately estimate plasma parameters, demonstrating its effectiveness on real observational data.

Findings

Neural network predicts plasma parameters with a few percent uncertainty.

Application to Hitomi data yields results consistent with known parameters within 10%.

Method reduces human effort in spectral data preprocessing.

Abstract

We present data preprocessing based on an artificial neural network to estimate the parameters of the X-ray emission spectra of a single-temperature thermal plasma. The method finds appropriate parameters close to the global optimum. The neural network is designed to learn the parameters of the thermal plasma (temperature, abundance, normalisation, and redshift) of the input spectra. After training using 9000 simulated X-ray spectra, the network has grown to predict all the unknown parameters with uncertainties of about a few percent. The performance dependence on the network structure has been studied. We applied the neural network to an actual high-resolution spectrum obtained with {\it Hitomi}. The predicted plasma parameters agreed with the known best-fit parameters of the Perseus cluster within $\lesssim10$\% uncertainties. The result shows a possibility that neural networks trained by simulated data can be useful to extract a feature built in the data, which would reduce human-intensive preprocessing costs before detailed spectral analysis, and help us make the best use of large quantities of spectral data coming in the next decades.