Machine learning-enabled prediction of chemical durability of A2B2O7 pyrochlore and fluorite

Pyrochlore-structure type and its derivative in a general formula A2B2O7 (A = rare earth elements and actinides; B = Ti, Sn, Zr, Hf, Pb, Si, etc.) display excellent structural flexibility and rich crystal chemistry as promising nuclear waste form materials capable of immobilizing actinides and fission products. It is essential to understand these materials' chemical durability and element release of radionuclides in order to evaluate their performance in near-field environment. However, it is a formidable grand technological challenge to experimentally perform durability testing across hundreds of thousands of possibilities resulting from their extreme compositional complexities due to cation substitutions at both A and B-sites. In this work, we demonstrate a machine learning approach to determine the key materials parameters and structural characteristics governing the leaching behaviors from a small set of selected compositions as model systems, enabling a science-based prediction of their chemical durability that can be extended to a wide range of chemical compositions. The combination of four key structural characteristics and materials parameters, including ionic radius size difference rA_B, ionic potential difference EB_A, electronegativity difference chi B_A, and lattice parameter alpha, creates features an optimized prediction of the chemical durability. Two machine learning models, linear regression and Kernel ridge regression models, are trained on the randomly-split training dataset derived from the experimentally-determined elemental release rates, and subsequently tested on the testing dataset. The predicted leaching rates from both machine learning models show an excellent agreement with the experimental data, demonstrating the feasibility of rapidly evaluating the material properties of new compositions. These results highlight the immense potential of synergizing informatics through machine learning-based models and well-controlled experiments of selected model systems to accelerate materials design and discovery with optimized compositions and performance of promising materials for effective nuclear waste management.

Automated summary

The pyrochlore-structure type and its derivatives show promising potential as materials for immobilizing actinides and fission products, but the complexity of their compositions poses a significant challenge for experimental durability testing. In this study, machine learning was employed to identify key materials parameters influencing chemical durability, allowing for accurate prediction of leaching behaviors and enabling rapid evaluation of new compositions. The results demonstrate the feasibility of combining informatics and experiments to accelerate materials design for effective nuclear waste management.