Probing of Gamma Attenuation Coefficient Using Artificial Neural Networks

Since ionization radiation is fraught with significant risks and challenges, there has been a growing concern for radiation shielding. This paper reports on the use of artificial neural networks in predicting the gamma-ray attenuation coefficient, which is important when it comes to radiation shielding and maintaining nuclear safety in medical imaging. Traditional methods used to determine this coefficient are experimental measurements based or theoretical calculations that are time consuming and dependent on material properties. An artificial neural network model is described in this work developed from a dataset consisting of the various physical properties of different materials and their corresponding attenuation coefficients. The model is then tested against established methods for its ability to predict accurately, indicating its potential for quick, dependable as well as generalized prediction for many kinds of materials. The results indicate that neural network can be effectively utilized in investigating gamma-ray attenuation coefficients since they greatly reduce computational efforts, thereby helping researchers to move forward in areas where precise knowledge about radiation interactions is highly needed.