Stacked Hybrid RNN-CNN Reconstruction of X-ray Influence on 21-cm Brightness Temperature

TL;DR

This paper introduces a hybrid RNN-CNN model that efficiently simulates the impact of X-ray flux on the 21-cm brightness temperature during the Epoch of Reionization, significantly reducing computation time while maintaining high accuracy.

Contribution

The paper presents a novel stacked hybrid RNN-CNN emulator that accurately predicts X-ray effects on 21-cm signals, enabling rapid exploration of high-dimensional astrophysical parameter spaces.

Findings

Reduces simulation time by a factor of one million.

Achieves prediction accuracy of 99.93%.

Errors are less than 0.35 mK.

Abstract

The X-ray photons substantially affect the thermal and ionization states of the intergalactic medium (IGM) during the Epoch of Reionization (EoR), thereby significantly influencing the 21-cm line observables such as its sky-averaged (global) brightness temperature. Nevertheless, the complicated dependency of astrophysical processes on a broad spectrum of parameters, including X-ray efficiency, spectral characteristics, and gas dynamics, makes precisely simulating the effect of X-ray flux challenging. Traditional approaches, including N-body and hydrodynamical simulations, are computationally intensive and struggle to explore high-dimensional parameter spaces efficiently. We present a stacked hybrid model trained on a specific simulation intended to reconstruct the effect of X-ray flux on the global 21-cm brightness temperature during the EoR. Along with Convolutional Neural Networks (CNNs), this architecture combines two substantial forms of recurrent neural networks (RNNs), Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU), therefore enabling fast adaptation to several X-ray flux levels. Without demanding repeated simulations, this emulator preserves temporal and spatial dependencies and generalizes to unseen parameter combinations. This matter reduces computation time by a factor of one million while preserving excellent prediction accuracy of 99.93\%, facilitating studies on high-dimensional parameter inference and sensitivity with an error margin of less than 0.35 mK. Our LSTM-GRU-CNN emulator combines recurrent and convolutional architectures to enable a robust and scalable analysis of X-ray heating effects on the global 21-cm brightness temperature during the EoR.