Towards Informatics-Driven Design of Nuclear Waste Forms

TL;DR

This paper advocates for an informatics-driven, system design approach integrating machine learning, simulations, and experiments to efficiently develop and validate novel nuclear waste forms, exemplified by phosphate-based ceramics.

Contribution

It introduces a comprehensive framework combining data-driven methods, physics simulations, and experimental validation for nuclear waste form design, emphasizing domain knowledge integration.

Findings

Successful design and validation of Na- and Nd-containing phosphate waste forms

Demonstration of a closed-loop sequential learning framework

Discussion of challenges and future outlook for informatics in nuclear waste management

Abstract

Informatics-driven approaches, such as machine learning and sequential experimental design, have shown the potential to drastically impact next-generation materials discovery and design. In this perspective, we present a few guiding principles for applying informatics-based methods towards the design of novel nuclear waste forms. We advocate for adopting a system design approach, and describe the effective usage of data-driven methods in every stage of such a design process. We demonstrate how this approach can optimally leverage physics-based simulations, machine learning surrogates, and experimental synthesis and characterization, within a feedback-driven closed-loop sequential learning framework. We discuss the importance of incorporating domain knowledge into the representation of materials, the construction and curation of datasets, the development of predictive property models, and the design and execution of experiments. We illustrate the application of this approach by successfully designing and validating Na- and Nd-containing phosphate-based ceramic waste forms. Finally, we discuss open challenges in such informatics-driven workflows and present an outlook for their widespread application for the cleanup of nuclear wastes.