Deep Learning-Based Approaches for Prediction of Binary Star Parameters

The precise computation of binary star parameters is crucial for understanding their formation, evolution, and dynamics. However, large datasets of available astronomical measurements require substantial effort for computing using classic astronomical methods. Deep learning (DL) is a promising approach that can provide a proper solution for estimating the parameters and reducing the burden of the lengthy procedures of astronomical computations. This study proposes two DL-based models for estimating binary star parameters. The first is the well-known multi-layer perceptron (MLP) model, whereas the second is based on long short-term memory (LSTM). We rely on databases, such as large sky multi-object fiber spectroscopic telescope area (LAMOST), to train the proposed models. In addition, we verify the training ratio showing that the performance of both models at a low training ratio of 30%, based on the mean square error (MSE), results in acceptable performance, reaching 0.093 and 0.085 for MLP and LSTM models, respectively. Furthermore, the LSTM-based DL model outperforms the conventional MLP for different training ratios.