Quantifying Uncertainty in Void Swelling Prediction: A Conformal Prediction Framework for Reactor Safety Margins

2026-03-02

AI Summary

This study addresses the lack of reliable uncertainty quantification in predicting irradiation-induced void swelling, a critical limitation for nuclear reactor material qualification and safety assessment. For the first time, conformal prediction is introduced into nuclear material swelling modeling, integrated with ensemble machine learning, log-transformation, and heteroscedasticity-aware modeling to construct a framework that yields statistically calibrated prediction intervals. The approach effectively captures the evolution of variance across swelling stages—from nucleation to steady-state growth—and maintains empirical coverage consistency at the target confidence level even under sparse data conditions. This provides a probabilistic risk assessment tool for high-dose reactor internals that surpasses traditional conservative upper-bound curves in both rigor and practical utility.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Uncertainty Representations
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning

Application Category

• User Modeling, Personalization and Recommendation: User model development and evaluation
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs

Abstract

Irradiation-induced void swelling is a critical degradation mechanism for structural materials in nuclear reactors, dictating component operational lifespan and safety. While recent machine learning (ML) approaches have improved the accuracy of swelling rate predictions, they often fail to account for the inherent stochasticity of radiation damage, providing point estimates without rigorous uncertainty quantification. This lack of probabilistic context limits their applications in materials qualification, reactor licensing and risk assessment. In this work, we develop a framework that integrates ensemble ML models with Conformal Prediction (CP) to generate statistically calibrated prediction intervals. Unlike standard error estimation or Bayesian methods that often rely on rigid distributional assumptions, this approach specifically addresses the physical heteroscedasticity of swelling data, where variance transitions from the nucleation-dominated incubation regime to the growth-dominated steady-state regime. We demonstrate that log-transformed conformal prediction inference provides valid empirical coverage consistent with target confidence levels even in sparse data regimes. This framework offers a pathway to replace overly conservative upper-bound curves with Probabilistic Risk Assessment (PRA) tools for high-dose reactor core internals.

Problem

• void swelling
• uncertainty quantification
• irradiation damage
• reactor safety
• prediction intervals

Innovation

• Conformal Prediction
• Uncertainty Quantification
• Void Swelling
• Heteroscedasticity
• Probabilistic Risk Assessment