The nuclear industry uses fuel performance codes to demonstrate integrity preservation of fuel rods. These codes include a complex system of models with empirical constants that one needs to calibrate for best estimates and uncertainties. However, deriving the appropriate level of uncertainty is often challenging due to model inadequacies.This paper presents a method to address model inadequacies by adapting the mean and covariance of the model parameters so that the propagated uncertainty conforms with the spread of the residuals rather than calibrating the model parameters directly.We demonstrate the method on synthetic data sets from an artificial test-bed containing a cladding oxidation and a hydrogen pick-up model. A repeated validation using many synthetic data sets shows that the method is robust and handles model inadequacies appropriately in most cases. Furthermore, we compare with traditional calibration and show model inadequacy leads to underestimation of uncertainties if not addressed.

Fuel performance codes are used to forecast fuel behavior and ensure safe operation. These analyses must typically include prediction uncertainties, and fuel performance models need calibration. Consequently, code calibration must derive the best estimates and corresponding uncertainties of model parameters for subsequent propagation.

Bayesian calibration is popular for generating the probability distribution of model parameters. However, model inadequacy disrupts these techniques, typically resulting in underestimated uncertainties. Earlier research showcased the incorporation of model inadequacy by model parameter inflation. The method demands cheap code predictions and derivatives, which required further research to develop differentiated Gaussian process surrogates.

This work combines those techniques into a complete methodology. We demonstrate it by calibrating Transuranus against fission gas release and cladding oxidation data. The result is model parameter uncertainties that primarily explain the discrepancies between the predictions and corresponding measurements, except when the output behaves highly non-linearly.

Fuel performance codes, such as Transuranus, predict fuel behavior and are used to ensure the safe operation of nuclear reactors. These codes are moderately time-consuming and affordable in many applications but may be limited in others, primarily when many fuel rods must be evaluated simultaneously. This work presents how the temporal neural network techniques, Temporal Convolutional Networks, and a Fourier Neural Operator can be combined to form a deep heterogeneous joint architecture as a surrogate model for fuel performance modeling in time-critical situations. We train the model using realistic power histories and corresponding outputs generated using the fuel performance code Transuranus. The ultimate result is a surrogate model for use in time-critical situations that take milliseconds to evaluate for thousands of fuel rods and have a mean test error of unseen data around a few percent.