Prediction of spectral characteristics of lithium-like ions by artificial neural network

Abstract

An Artificial Neural Network has been employed to calculate spectral characteristics of lithium-like Beryllium (Be II), Boron (B III), Carbon (C 1V), and Nitrogen (N V) ions. The base data (input parameters) consisted of quantum defects and the inverse square of the principal quantum number of lithium atoms for calculating quantum defects and energies of lithium-like ions. The study has two parts; in the first part, the quantum defects of Lithium and lithium-like ions (Be II, B III, C 1V, and N V) were calculated using Quantum Defect Theory (QDT). In the second part, an Artificial Neural Network (ANN) with a single hidden layer and five neurons was utilized to predict lithium-like quantum defects. 70% of the data was used to train the network, and 15% was used for testing and validating the values of quantum defects up to n = 100 for each atom and ion. The extended Rydberg–Ritz formula was used to calculate the energies of the lithium-like elements.