Prediction of Half-Value Layer of glass-based materials using machine learning algorithms

Abstract

Accurate prediction of the half-value layer (HVL) in radiation shielding materials is essential for optimizing their composition and performance. In this study, we employ four ensemble machine learning models XGBoost, LightGBM, Gradient Boosting Regressor (GBR), and Random Forest to predict HVL based on the chemical composition of glass-based materials. Each model was fine-tuned using Optuna’s Bayesian optimization and evaluated through 5-fold cross-validation and a separate testing phase using metrics including R2 , RMSE, MAE, and MAPE. All models demonstrated high predictive performance (R2>0.996), with the GBR model achieving the best results (R2=0.999, RMSE=0.0772, MAPE=0.09%). XGBoost also performed competitively, offering a balance between accuracy and computational efficiency. These results highlight the potential of gradient boosting approaches to speed up the design and study of radiation shielding materials and show how effective they are at identifying intricate nonlinear correlations within material databases.