Over the past half century, nuclear fuel characterization and behavior prediction have hit a ceiling as modeling and simulation insight exceeds that gained from experiments. The difficulty lies in the interpretation of complex fission products, caused by time-evolving system chemistry and extreme operating environments. Here, we apply a machine learning-enhanced approach that accelerates the characterization cycle and improves the accuracy of identifying the nanophase fission products and bubbles in spent nuclear fuels. This approach is used to analyze commercial, high-burnup, irradiated light-water reactor fuels, demonstrating the relationship between the fission product precipitates and fission gases. It also demonstrates the capability of dissecting the fission versus decay pathways of fission product precipitates observed across the radius of the fuel pellet. An unsupervised machine learning algorithm is provided for quantifying the chemical segregation of the fission products with respect to the high-burnup structure. This approach broadens the bandwidth of processing large analytical microscopy data volumes approaching the atomistic-scale and provides a faster route to achieve high-quality physics-based fuel performance modeling based on a rich microscopy database.

PCA results show both precipitates and Xe bubbles. Detailed X-ray intensity mapping of the Xe (Fig. 1) improves the visibility of fine Xe bubbles, which are invisible when using conventional TEM. Cs and Ba are not prevalent in the matrix. Figure 1b shows a higher magnification deconvolution map (a spectral simplicity–rotated abundance map and a spectral endmember pair) of intragranular Xe bubbles in another restructured grain of the Limerick fuel. In this particular instance, the PCA has been applied to greatly improve the relatively noisy and sparse dataset, into a series of low-rank, low-noise, image, and spectra vectors. Reducing the data into these components vastly improves the visibility of key features. In this instance, the PCA analysis revealed three primary components representing the three strongest spectrum-image pairs within this particular dataset. The three-component analysis revealed overlapping of Xe bubbles with the fission products. Each component was marked as endmember #0–#2, and an abundance map accompanies each endmember. Each X-ray (keV) peak labeled via the multivariate curve resolution-alternating least-squares method allows efficient identification of nanoscale Xe bubbles, and it also displays finer details of fission-product nanoclusters (Fig. 1c). The C–K and O-K lines are weak across the three components. Component 1 shows the U-M lines, which are weaker at the Xe bubbles than the matrix. Component 2 shows the stronger Mo-L and Ru-L signal and weaker Tc, Rh, Pd, and Ag signals, implying the combination of the β-Mo (Tc, Ru) and ϵ-Ru (Mo, Tc, Rh, Pd) phases. Component 3 shows stronger Xe-L lines than the Mo–Tc–Ru–Rh–Pd–Ag peaks. This demonstrates the fission-product nanocluster segregation is associated with nanoscale Xe bubbles. We also examined the HBS; no intragranular Xe bubbles were found. This ML-aided algorithm improves the accuracy and speed of locating fine Xe bubbles smaller than 5 nm.

To validate our ML-aided EDS approach, we extended the algorithm to the HBS in the H.B. Robinson fuel with a higher average burnup at approximately 72 MWd kgU⁻¹. Like in the HBS of the Limerick fuel, no intragranular Xe bubbles were observed. However, nanoscale Xe bubbles still exist intergranularly at the grain boundary in the HBS. The advantages gained from using the ML algorithms were validated (Fig. 2), and conventional TEM using the Fresnel contrast method was unable to capture finer features at a random high-angle grain boundary. After the ML reconstruction of the STEM-EDS data, intergranular Xe bubbles overlapping with the fission-product clusters were observed (Fig. 2b). The nanoscale Xe bubbles (≤4 nm) are presented as color mix maps in Fig. 2c, and the spectrum is labeled at low- (0–10 keV) and high-energy (10–20 keV) ranges. The ML decomposition of the X-ray spectrum at the low- and high-energy ranges in Fig. 2d demystifies the fission-product nanoclusters and Xe bubbles trapping at the grain boundary. In the low-energy range below 5 keV, the fission product precipitates are rich in Mo-L peak, and the Tc-L and Ru-L peaks are lower. The Xe bubbles are reflected by the Xe-Lα, accompanied by Xe-Lβ₁ overlapped with U-M₂N₄ and minor Xe-Lβ₂. The matrix is dominated by the U-Mγ line. At the high-energy range above 18 keV, a strong Mo-Kβ signal appears, along with Ru-Kα, Tc-Kα, Pd-K, and U-Lγ₁ peaks. The spectrum analysis showed that the fission product is the β-Mo (Tc, Ru) phase. In this scenario, the Xe-L line readings are lower than the spectra loadings of fission product precipitate L lines. However, the nanoscale Xe bubbles can be recognized with improved visibility over the conventional BFTEM and STEM methods.

In addition to the qualification of fission products, ML can be applied to quantify the composition of each individual fission-product precipitate. Figure 3a displays the composition of small-scale metallic fission-product precipitates (<100 nm) in the HBS as a heatmap along the radial position of the Limerick fuel segment. The heatmap was calculated from normalized atomic percent (at. %) for Xe, U, Te, Tc, Ag, Ru, Rh, Pu, Pd, Mo, Cs, and Ba with acquired data from STEM-EDS maps. Red indicates high levels of concentration, whereas blue and green indicate low concentration levels. The precipitates primarily consist of Mo, Tc, Ru, Rh, and Pd, with minor Ag contributions; Te, Ba, Cs, and Xe are present in lower concentrations. The phase identification of these fission-product precipitates was not apparent, so clustering analysis was applied on the chemical mapping based on the k-means clustering algorithm. PCA on the elemental concentration determines the sizes of five clusters (blue: cluster 1; red: cluster 2; orange: cluster 3; green: cluster 4; purple: cluster 5) for the k-means clustering method. The two-component (Fig. 3b) and three-component (Fig. 3c) PCA decomposition were plotted by using the k-means clustering method. The relationship between each fission-product element and the U content (at. %) was then plotted, shown in Fig. 3d. The major elements Mo, Tc, Ru, Rh, and Pd indicate a strongly negative correlation to the U content. Figure 3e provides the scatter plot of the ternary phase diagram for each predicted fission-product phase, and individual metallic precipitate compositions were derived from clustering analysis of the STEM-EDS dataset. The α phase diagram distinguishes cluster 1 from the others, showing that it has a higher average Pd percentage. The divergence of the scatter data indicates that the α phase may not be a predominant solid solution path. The β phase diagram indicates a strong concentration of the data, and each grouped cluster is closer in the composition spacing, which indicates that most of the fission products are β phase. The ϵ phase diagram resolved the uncertainty in the α phase diagram, indicating that cluster 1 is closer to the ϵ phase, with a Mo content less than 50 at. %. Cluster 2 partially shows the nature of ϵ phase, with a (Ru + Tc) content higher than 75 at. %. Clusters 4 and 5 may also belong to the ϵ phase, with Mo contents lower than 50 at.%. In all the three phase diagrams, cluster 3 is less prevalent than the other clusters, which reverifies the relationship between the clusters and Xe established by the regression plot in Fig. 3d.

We developed a high-quality ML-enhanced microscopy method for applications in nuclear fuel analysis. This approach was demonstrated on high-burnup spent nuclear fuels, and it offers novel insights compared to the common notions on obscure nanostructures. Compared with the conventional electron microscopy data collection, this advanced augmented approach accelerates the pace of both post irradiation examination characterization and analysis. It also reveals the detailed nanoclusters with respect to the fission-product precipitates and Xe bubbles associated with the potential onset of the HBS formation. This study highlights the data mining of precipitates chemistry and provides evidence of the ability to extract segregation information from unknown precipitation clusters, addressing the need for precise separation of the elements from analytical spectroscopy for fission products. Based on the insights from the abundance of materials informatics, it is beneficial to leverage such methods to establish a database to reduce uncertainty in fuel-performance modeling, which is also of great importance to the numerous microscopy characterization efforts in interdisciplinary research fields.