Application of machine learning in predicting the apparent diffusion coefficient of Se(IV) in compacted bentonite

Light Gradient Boosting Machine (LightGBM) and Random Forest (RF) algorithms were used to predict the apparent diffusion coefficient of Se(IV) in compacted bentonite. Seven instances of Se(IV) were measured using through-diffusion method. LightGBM (R2 = 0.98 and RMSE = 0.025) exhibited superior predictive accuracy with a training dataset consisting of 956 instances and eight input features from Japan Atomic Energy Agency (JAEA-DDB) and literatures. Shapley Additive Explanation and Partial Dependence Plots analyses revealed valuable insights into the diffusion mechanism of adsorbed anion obtained by evaluating the relationships between the apparent diffusion coefficient and the dependency of each input feature.