Estimation of electron screening potential in the 6Li(d, [formula omitted])4He reaction using multi-layer perceptron neural network

Reactions between light charged nuclei at sub-Coulomb energies are crucial in astrophysical environments, but accurate cross-section measurements are hindered by electron screening. Conventional approaches, such as polynomial extrapolation and the Trojan Horse Method, frequently predict screening potentials that exceed adiabatic estimates. Building on the success of a Multi-Layer Perceptron (MLP)-based Artificial Neural Network (ANN) for the 6Li(p,α)3He reaction (Chattopadhyay, 2024), this work applies the same methodology to the 6Li(d,α)4He reaction. The experimental data on the astrophysical S-factor from the literature are reanalyzed using the ANN to model the energy dependence of the S-factor. The bare S-factor is extracted from data above 70 keV, where screening effects are minimal, and the screening potential is determined by comparing it with the screened S-factor in the low-energy region. The resulting screening potential is 147.95 ± 13 eV, demonstrating the effectiveness and robustness of ANN-based methods for evaluating electron screening in low-energy nuclear reactions involving light nuclei.