A Learning Model Applied to the Calculation of the Velocities of 20 Stars Relative to the Sun

TL;DR

This paper presents a learning model applied to calculate the velocities of 20 stars relative to the Sun, using astronomical data and validating the approach in an applied astronomy context.

Contribution

It introduces a learning model tailored for astronomical velocity calculations and demonstrates its application to real star data, bridging machine learning and astronomy.

Findings

The model successfully calculates star velocities relative to the Sun.

Validation shows the model's effectiveness in an applied astronomy case.

The approach integrates socio-critical and positivist paradigms.

Abstract

We aim to explain the paradigm of a learning model, as well as to validate it in an applied case of an astronomy problem where the data used are declination, parallax, radial velocity of a star, as well as its annual variation in right ascension and declination. This study is based on a socio critical and positivist paradigm in the context of basic and applied science; algorithms and astronomical models were used as an instrument, which allowed us to address a specific case such as the calculation of the velocity of a star relative to the Sun.