@article{alsafadi_wu_2023, title={Deep generative modeling-based data augmentation with demonstration using the BFBT benchmark void fraction datasets}, volume={415}, ISSN={["1872-759X"]}, url={https://doi.org/10.1016/j.nucengdes.2023.112712}, DOI={10.1016/j.nucengdes.2023.112712}, abstractNote={Deep learning (DL) has achieved remarkable successes in many disciplines such as computer vision and natural language processing due to the availability of “big data”. However, such success cannot be easily replicated in many nuclear engineering problems because of the limited amount of training data, especially when the data comes from high-cost experiments. To overcome such a data scarcity issue, this paper explores the applications of deep generative models (DGMs) that have been widely used for image data generation to scientific data augmentation. DGMs, such as generative adversarial networks (GANs), normalizing flows (NFs), variational autoencoders (VAEs), and conditional VAEs (CVAEs), can be trained to learn the underlying probabilistic distribution of the training dataset. Once trained, they can be used to generate synthetic data that are similar to the training data and significantly expand the dataset size. By employing DGMs to augment TRACE simulated data of the steady-state void fractions based on the NUPEC Boiling Water Reactor Full-size Fine-mesh Bundle Test (BFBT) benchmark, this study demonstrates that VAEs, CVAEs, and GANs have comparable generative performance with similar errors in the synthetic data, with CVAEs achieving the smallest errors. The findings shows that DGMs have a great potential to augment scientific data in nuclear engineering, which proves effective for expanding the training dataset and enabling other DL models to be trained more accurately.}, journal={NUCLEAR ENGINEERING AND DESIGN}, author={Alsafadi, Farah and Wu, Xu}, year={2023}, month={Dec} }
 @article{abu saleem_alsafadi_al-abidah_2022, title={Effect of mesh refinement on the solution of the inverse uncertainty quantification problem for transient physics}, volume={152}, ISSN={["1878-4224"]}, DOI={10.1016/j.pnucene.2022.104360}, abstractNote={In this paper, effect of mesh refinement on the solution of the IUQ problem for transient physics was studied. Two mathematical formulations, the Maximum Likelihood Estimate (MLE) and the Maximum A Posterior (MAP), were adopted to solve the IUQ problem. Global Sensitivity Analysis (GSA) and Local Sensitivity Analysis (LSA) were performed to provide the necessary data for MLE and MAP implementation. TRACE models with three different mesh numbers based on the transient Flooding Experiment with Blocked Array (FEBA) benchmark were developed. Results of this analysis show that statistical expectation of the physical models (statistical mean) tends to shift towards a certain value with mesh refinement. This shifting behavior can be related to the decrease in the truncation error resulting from numerical discretization due to mesh refinement, consequently, compensating for the mismatch between experimental data and code prediction results that may be falsely credited to the uncertainties inherent in the physical models. Moreover, the results show that the relative absolute error between experimental data and code prediction results was decreased upon incorporating the input parameter uncertainties that were determined based on MLE and MAP formulations. In all cases, the error was smallest for the most refined mesh.}, journal={PROGRESS IN NUCLEAR ENERGY}, author={Abu Saleem, Rabie A. and Alsafadi, Farah R. and Al-Abidah, Nadeen}, year={2022}, month={Oct} }
 @article{wu_xie_alsafadi_kozlowski_2021, title={A comprehensive survey of inverse uncertainty quantification of physical model parameters in nuclear system thermal-hydraulics codes}, volume={384}, ISSN={["1872-759X"]}, DOI={10.1016/j.nucengdes.2021.111460}, abstractNote={Uncertainty Quantification (UQ) is an essential step in computational model validation because assessment of the model accuracy requires a concrete, quantifiable measure of uncertainty in the model predictions. The concept of UQ in the nuclear community generally means forward UQ, in which the information flow is from the inputs to the outputs. Inverse UQ, in which the information flow is from the model outputs and experimental data to the inputs, is an equally important component of UQ but has been significantly underrated until recently. Forward UQ requires knowledge in the input uncertainties which has been specified by expert opinion or user self-evaluation. Inverse UQ is defined as the process to inversely quantify the input uncertainties based on experimental data. This review paper aims to provide a comprehensive and comparative discussion of the major aspects of the inverse UQ methodologies that have been used on the physical models in system thermal–hydraulics codes. Inverse UQ methods can be categorized by three main groups: frequentist (deterministic), Bayesian (probabilistic), and empirical (design-of-experiments). We used eight metrics to evaluate an inverse UQ method, including solidity, complexity, accessibility, independence, flexibility, comprehensiveness, transparency, and tractability. Twelve inverse UQ methods are reviewed, compared, and evaluated based on these eight metrics. Such comparative evaluation is intended to provide a good guidance for users to select a proper inverse UQ method based on the problem under investigation.}, journal={NUCLEAR ENGINEERING AND DESIGN}, author={Wu, Xu and Xie, Ziyu and Alsafadi, Farah and Kozlowski, Tomasz}, year={2021}, month={Dec} }
 @article{xie_alsafadi_wu_2021, title={Towards improving the predictive capability of computer simulations by integrating inverse Uncertainty Quantification and quantitative validation with Bayesian hypothesis testing}, volume={383}, ISSN={["1872-759X"]}, DOI={10.1016/j.nucengdes.2021.111423}, abstractNote={The Best Estimate plus Uncertainty (BEPU) approach for nuclear systems modeling and simulation requires that the prediction uncertainty must be quantified in order to prove that the investigated design stays within acceptance criteria. A rigorous Uncertainty Quantification (UQ) process should simultaneously consider multiple sources of quantifiable uncertainties: (1) parameter uncertainty due to randomness or lack of knowledge; (2) experimental uncertainty due to measurement noise; (3) model uncertainty caused by missing/incomplete physics and numerical approximation errors, and (4) code uncertainty when surrogate models are used. In this paper, we propose a comprehensive framework to integrate results from inverse UQ and quantitative validation to provide robust predictions so that all these sources of uncertainties can be taken into consideration. Inverse UQ quantifies the parameter uncertainties based on experimental data while taking into account uncertainties from model, code and measurement. In the validation step, we use a quantitative validation metric based on Bayesian hypothesis testing. The resulting metric, called the Bayes factor, is then used to form weighting factors to combine the prior and posterior knowledge of the parameter uncertainties in a Bayesian model averaging process. In this way, model predictions will be able to integrate the results from inverse UQ and validation to account for all available sources of uncertainties. This framework is a step towards addressing the ANS Nuclear Grand Challenge on "Simulation/Experimentation" by bridging the gap between models and data.}, journal={NUCLEAR ENGINEERING AND DESIGN}, author={Xie, Ziyu and Alsafadi, Farah and Wu, Xu}, year={2021}, month={Nov} }