Machine learning the apparent diffusion coefficient of Se(IV) in compacted bentonite

Subjects: Nuclear Science and Technology >> Radiation Physics and Technology submitted time 2024-05-22

Xiaoqiong Shi Junlei Tian Jiacong Shen Zhengye Feng Jiaxing Feng Tao Wu Qingfeng Li

Abstract： 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). 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.

Peer Review Status:Awaiting Review

 Hits 512  Downloads 104  Comment 0