Accelerating reionization constraints: An ANN-emulator framework for the SCRIPT Semi-numerical Model

TL;DR

This paper introduces an efficient neural network emulator framework for the SCRIPT semi-numerical model, significantly reducing computational costs in constraining the Epoch of Reionization with high accuracy.

Contribution

It presents a novel combination of coarse-resolution MCMC and adaptive sampling to train neural network emulators, enabling fast and accurate parameter inference for EoR models.

Findings

Achieves $R^2$ of 0.97-0.99 in predictions

Reduces simulation needs by a factor of 100

Lowers CPU cost by up to 70 times

Abstract

Constraining the Epoch of Reionization (EoR) with physically motivated simulations is hampered by the high cost of conventional parameter inference. We present an efficient emulator-based framework that dramatically reduces this bottleneck for the photon-conserving semi-numerical code SCRIPT. Our approach combines (i) a reliable coarse-resolution MCMC to locate the high-likelihood region (exploiting the large-scale convergence of SCRIPT) with (ii) an adaptive, targeted sampling strategy to build a compact high-resolution training set for an artificial neural network based emulator of the model likelihood. With only $\approx 10^3$ high-resolution simulations, the trained emulators achieve excellent predictive accuracy ($R^2 \approx 0.97-0.99$) and, when embedded within an MCMC framework, reproduce posterior distributions from full high-resolution runs. Compared to conventional MCMC, our pipeline reduces the number of expensive simulations by a factor of $\sim 100$ and lowers total CPU cost by up to a factor of $\sim 70$, while retaining statistical fidelity. This computational speedup makes inference in much higher-dimensional models tractable (e.g., those needed to incorporate JWST and upcoming 21 cm datasets) and provides a general strategy for building efficient emulators for next generation of EoR constraints.