Thermophysical properties of spark plasma sintered UCo: a comparison with machine learning predictions

TL;DR

This study experimentally validates a prior ML screening workflow for high-thermal-conductivity uranium compounds by fabricating and characterizing UCo. Using arc melting and spark plasma sintering, the authors measure high-temperature thermophysical properties and decompose κ into lattice and electronic contributions via the Wiedemann–Franz law. The ML classifier predicts κ > 15 W/mK for UCo across 300–1000 K, with SHAP analysis indicating physically meaningful feature drivers, though quantitative overestimation occurs below ~700 K. The work demonstrates that ML-guided screening can be qualitatively reliable for ATF-relevant uranium compounds and highlights the need for broader validation on chemically complex systems to improve predictive accuracy.

Abstract

Uranium dioxide has been widely used as a nuclear fuel in commercial light water reactors due to its high uranium density and chemical stability. However, its relatively low thermal conductivity is not optimal from the viewpoints of fuel integrity and safety margins, particularly during loss-of-coolant accidents. Although the development of accident-tolerant fuels with higher thermal conductivity is strongly desired, many potential uranium compounds remain unexplored due to constraints associated with handling radioactive materials. To efficiently screen promising uranium compounds with high thermal conductivity, past studies have leveraged machine-learning models to accelerate the discovery process. In this study, we experimentally examine the model's predictions by fabricating UCo and measuring its high-temperature thermophysical properties. Our results show that the thermal conductivity of UCo predicted by machine learning is in good agreement with the experimental measurements. Despite slight discrepancies, additional SHAP analysis suggests that the model's decision logic is consistent with known physical trends. Overall, this study fills a gap in reported thermophysical properties of UCo and provides experimental support for machine-learning-assisted screening of uranium compounds relevant to advanced fuel development.

Figures (7)

• Figure 1: XRD pattern of the prepared UCo sample after SPS, along with reference patterns for UCo baenziger1950compounds and UCo2smith1975icdd.
• Figure 2: SEM-EDS images of the prepared UCo sample after SPS.
• Figure 3: (a) Thermal conductivity and (b) electrical conductivity of the prepared UCo bulk sample. The arrow in (b) highlights that the electrical conductivity approaches a plateau as the temperature increases above 500 K.
• Figure 4: Temperature dependence of thermal conductivity $\kappa_{\mathrm{total}}$, electronic thermal conductivity $\kappa_{\mathrm{ele}}$, and lattice thermal conductivity $\kappa_{\mathrm{lat}}$ of the prepared UCo sample.
• Figure 5: Comparison of the Vickers hardness of UCo with that of other uranium compounds at various indentation loads. The inset shows a Vickers indentation on the UCo sample under a load of 9.807 N.