CTF4Nuclear: Common Task Framework for Nuclear Fission and Fusion Models

2026-05-15

AI Summary

This study addresses longstanding challenges in modeling nuclear fission and fusion systems—namely, the prohibitive cost of high-fidelity simulations, significant inaccuracies introduced by simplifying assumptions in conventional models, and the absence of standardized evaluation frameworks for machine learning approaches. To overcome these limitations, the work introduces the first Common Task Framework (CTF) tailored for nuclear engineering, integrating multi-physics datasets from nuclear systems and proposing a novel paradigm for system monitoring under sparse measurements. It further establishes a rigorous, reproducible benchmark by evaluating diverse machine learning methods against twelve standardized metrics. This effort not only exposes critical shortcomings of current techniques in nuclear system modeling but also delivers the first standardized assessment platform, substantially enhancing the rigor and comparability of scientific machine learning in safety-critical domains.

Abstract

The demand for clean energy is ever increasing, with new nuclear technologies presenting a complementary solution to renewable energies. However, designing and operating these systems is exceptionally difficult, given the complexity of the physical phenomena that interact to form the system dynamics. While high-fidelity simulations help to understand the non-linear, multi-physics interactions within a reactor, they are computationally expensive and rarely suitable for real-time applications. Furthermore, model-based approaches are inherently sensitive to simplifying assumptions required to derive their governing equations and parameters, leading to inevitable discrepancies with real-world measurements. In contrast, Machine Learning (ML) methods have the potential to generate reliable surrogate models which may be able to quickly predict the system's behaviour. However, the number of data-driven methods that can potentially be used for this task is large and diverse. In a safety-critical setting such as nuclear engineering, a fair comparison of different ML methods, and a clear understanding of their advantages and limitations, is of paramount importance. To address this, we introduce a Common Task Framework (CTF) for ML in nuclear engineering, building upon previous efforts in dynamical systems and seismology. This CTF considers a curated set of datasets from different nuclear and nuclear-adjacent systems. The CTF evaluates the performance of a method on 12 established metrics, alongside a new paradigm focused on system monitoring from sparse measurements only. We illustrate the framework by benchmarking standard ML baselines against these datasets, revealing current method limitations. Our vision is to replace ad hoc comparisons with standardized evaluations on hidden test sets, raising the bar for rigour and reproducibility in scientific ML for the nuclear industry.

Problem

• nuclear engineering
• machine learning
• benchmarking
• surrogate modeling
• Common Task Framework

Innovation

• Common Task Framework
• machine learning benchmarking
• nuclear fission and fusion
• sparse measurements
• scientific reproducibility