Predicting Nepheline Formation in Nuclear Waste Glasses Using Machine Learning With Uncertainty Quantification
International Journal of Applied Glass Science · 2026-10 · 17 (4)
DOI: 10.1111/ijag.70062 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Applied Glass Science, online erschienen am 17.09.2026. Verfasst von Mayra Diaz‐Acevedo und 5 weiteren Autor:innen. Die Arbeit nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: U.S. Department of Energy.
Abstract (Originalsprache)
The vitrification of high‐level waste (HLW) into borosilicate glass is a cornerstone of nuclear waste management, yet one of the key challenges in glass formulation for high‐aluminum‐containing waste streams is the precipitation of nepheline during the canister cooling stage. Excessive nepheline formation compromises glass durability, threatening the long‐term stability of vitrified waste. Thus, predictive models capable of accurately anticipating nepheline formation from glass composition are critical for waste glass formulation and optimizing stability and durability. Various methods such as discriminators and sub‐mixture models have been developed to determine nepheline precipitation; however, they tend to be overly conservative and unnecessarily limit achievable glass compositions. Building on previous works, we explore the application of several classical machine learning models—Gaussian Processes, Gradient Boosting, and Random Forest—alongside Bayesian methods, including fully Bayesian Gaussian Processes and Partial Bayesian Neural Networks, to address the challenges posed by limited datasets and prediction uncertainties intrinsic to this problem. Furthermore, we introduce a dual‐head partially Bayesian neural network with scaled regression loss, validated through ablation, to directly predict nepheline precipitation. Notably, this regression‐based strategy enables the use of practical nepheline tolerance thresholds, substantially reducing false positives compared with existing binary nepheline discriminator approaches that cannot distinguish between trace and significant nepheline formation—expanding access to novel compositional regions for waste glass design. By balancing explainability, uncertainty quantification, and accuracy, our results lay the foundation for more efficient optimization of HLW vitrification processes and contribute to the broader goal of improving nuclear waste management strategies.
Förderung
- U.S. Department of Energy
Zitieren
APA
Diaz‐Acevedo, M., Curry, C. E., Lu, X., Chong, S., Allec, S. I., & Vienna, J. D. (2026). Predicting Nepheline Formation in Nuclear Waste Glasses Using Machine Learning With Uncertainty Quantification. International Journal of Applied Glass Science, 17(4). https://doi.org/10.1111/ijag.70062
Vancouver
Diaz‐Acevedo M, Curry CE, Lu X, Chong S, Allec SI, Vienna JD. Predicting Nepheline Formation in Nuclear Waste Glasses Using Machine Learning With Uncertainty Quantification. International Journal of Applied Glass Science. 2026;17(4). doi:10.1111/ijag.70062
BibTeX
@article{DiazAcevedo2026,
author = {Diaz‐Acevedo, Mayra and Curry, Chloe E. and Lu, Xiaonan and Chong, Saehwa and Allec, Sarah I. and Vienna, John D.},
title = {Predicting Nepheline Formation in Nuclear Waste Glasses Using Machine Learning With Uncertainty Quantification},
journal = {International Journal of Applied Glass Science},
year = {2026},
volume = {17},
number = {4},
doi = {10.1111/ijag.70062}
}
EUVIMED