Prediction of post-irradiation swelling rate of 316L stainless steel based on Variational Autoencoders and interpretable machine learning

• ETR achieved best performance in swelling rate prediction: R 2 = 0.79, RMSE = 1.65% (test set). • VAE-augmented data improved model: R 2 = 0.91, RMSE = 1.11%. • Optimal features (Si, C, IrF, T, Dd) identified for swelling rate prediction. • SHAP analysis clarified feature effects on swelling rate and irradiated material behavior. In the field of materials science, accurately predicting the swelling rate of materials in irradiated environments is crucial for ensuring safety and reliability. This study aims to enhance the predictive accuracy of the swelling rate of irradiated 316L stainless steel, particularly in high-tech applications such as nuclear energy. By comparing various machine learning models, it was found that the Extreme Trees Regression (ETR) model performed best on the test set, achieving an R 2 of 0.79 and a Root Mean Square Error (RMSE) of 1.65 %. Although it demonstrated strong generalization capabilities, the limited data volume restricted its predictive accuracy. To address this issue, the study employed Variational Autoencoders (VAEs) for data augmentation, generating an additional 400 synthetic data points to expand the original dataset. This enhancement increased the R 2 on the test set to 0.91 and reduced the RMSE to 1.11 %. Following data augmentation, feature selection was conducted, resulting in Si, C, IrF, T, and Dd being identified as the optimal feature combination. SHapley Additive exPlanations (SHAP) was then utilized for interpretability analysis, revealing the significant effects of these features on the swelling rate. The findings provide essential insights for understanding and optimizing the swelling behavior of materials following irradiation.