Results for “Task Analysis” — Page 45

DOE OSTI2023

Iodine Air Sampling: Installation and Preliminary Results

The F-Area wetlands are a known sink for radioiodine generated at the Savannah River Site (SRS). Wastewater containing iodine-129 ( 129 I) was discharged into the F-Area Seepage Basins for disposal, but the acidity of the wastewater mobilized some of the contaminants from the basin soil through the vadose zone and into the groundwater; ultimately creating a groundwater plume that extends towards Fourmile Branch and its associated wetland areas. Dissolved radioiodine specifically has migrated to the nearby F-Area wetlands, where it persists as a contaminant of concern. Accumulation and resurfacing of 129 I in the wetlands and nearby areas creates a potential secondary source zone where changes in biogeochemical conditions could result in the release of this sequestered 129 I to the air. Monitoring data has indicated that 129 I has a seasonal behavior at several surface water stations, with high concentrations during summertime and low concentrations during wintertime. Still, it is not known which factors control the seasonal behavior of 129 I. Further, it has been reported that 129 I contributed approximately 23% to the 2019 SRS offsite air pathway dose to the representative person for that year (SRNS, 2020), but air measurements of 129 I have never been taken in the F-Area wetlands. Because air emissions of 129 I from the wetlands have never been investigated, it is not known if this could be a potential release pathway that needs to be included in the site conceptual model. To address these unknowns, the Savannah River National Laboratory (SRNL) has an applied research task to investigate whether 129 I in the wetlands is emitted to the air and, if so, whether air concentrations exhibit seasonal variation. This report presents information about the system recently installed in the F-Area wetlands for measuring 129 I, as well as analysis results for samples collected June through August 2023. Quantification of this constituent will provide a better understanding of the contribution of airborne 129 I from the F-Area wetlands to the offsite dose and better inform ongoing and future remedial actions.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2023

Results of FY 2023 Alloy 617 and Alloy 709 High-Temperature Crack-Growth Testing

This report summarizes the work performed at Idaho National Laboratory under the “Creep, fatigue and creep-fatigue crack growth tests” task of the “Long-Term VHTR Material Qualification – INL” work package. Work was performed this year to validate the crack growth monitoring setup used with the test frames against both continuous crack length monitoring using an optical camera, as well as post-mortem analysis of marker bands on the fracture surface. Delays prevented the use of a gauge to measure load-line displacement for early tests, and so the creep-fatigue crack growth setup was evaluated using the actuator displacement for a load-line displacement setup. While not ideal, this allowed examination of the shortcomings with the current software setup that was originally designed for performing stress corrosion crack growth rate studies. The method for data collection was modified to link the crack growth monitoring software with Instron’s Wave Matrix software. Once the load-line displacement gauge arrived, the crack growth equipment was successfully modified to permit continuous monitoring of both load-line displacement and crack length. This is critical for creep-fatigue and creep crack growth rate studies for ductile material, as it permits the C* and Ct analyses. Test results are shown for Alloy 617 fatigue and creep-fatigue (without the gauge for load-line displacement measurements), as well as creep-fatigue of Alloy 709, which was performed with the completed test setup, allowing for crack length and load-line displacement monitoring.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗

DOE OSTI2023

Efficient Subset Simulation using Hamiltonian Neural Network enhanced Markov Chain Monte Carlo Methods

The Monte Carlo method delivers an unbiased estimate of the probability of failure. However, the variance of the estimate depends on the number of evaluated samples. This number must be very large for estimations of a low probability of failure. If the evaluation of each sample is computationally expensive, the crude Monte Carlo simulation strategy is impracticable. Therefore, subset simulations are used to reduce the required number of evaluations. Subset simulations require a Markov Chain Monte Carlo sampler, such as the random walk Metropolis-Hastings algorithm. The algorithm, however, struggles with sampling in low-probability regions, especially if they are narrow. As a consequence, advanced Markov Chain Monte Carlo simulations have been developed. In particular, the Hamiltonian Monte Carlo method explores the target distribution rapidly. Driven by the idea of Hamiltonian dynamics, this sampler provides a non-random walk through the target distribution. The incorporation of subset simulation and Hamiltonian Monte Carlo methods has shown promising results for reliability analysis. One downside of the Hamiltonian Monte Carlo method is that gradient evaluations are computationally expensive, especially when dealing with high-dimensional problems and evaluating long trajectories. We show that integrating Hamiltonian neural networks in Hamiltonian Monte Carlo simulations significantly speeds up the sampling task. Furthermore, the enhancement of adaptive trajectory length within the Hamiltonian Monte Carlo results in the efficient proposal of the following states. Based on this recent enhancement, we provide a fast sampling strategy for subset simulations using Hamiltonian neural networks to replace the evaluation of the gradient and significantly speed up the Hamiltonian Monte Carlo simulation.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2025

Can Large Language Models Understand Intermediate Representations?

Intermediate Representations (IRs) are essential in compiler design and program analysis, yet their comprehension by Large Language Models (LLMs) remains underexplored. This paper presents a pioneering empirical study to investigate the capabilities of LLMs, including GPT-4, GPT-3, Gemma 2, LLaMA 3.1, and Code Llama, in understanding IRs. We analyze their performance across four tasks: Control Flow Graph (CFG) reconstruction, decompilation, code summarization, and execution reasoning. Our results indicate that while LLMs demonstrate competence in parsing IR syntax and recognizing high-level structures, they struggle with control flow reasoning, execution semantics, and loop handling. Specifically, they often misinterpret branching instructions, omit critical IR operations, and rely on heuristic-based reasoning, leading to errors in CFG reconstruction, IR decompilation, and execution reasoning. The study underscores the necessity for IR-specific enhancements in LLMs, recommending fine-tuning on structured IR datasets and integration of explicit control flow models to augment their comprehension and handling of IR-related tasks.

Jiang, Hailong↗

DOE OSTI2025

AI foundation models for experimental fusion tasks

Artificial Intelligence (AI) foundation models, while successful in various domains of language, speech, and vision, have not been adopted in production for fusion energy experiments. This brief paper presents how AI foundation models can be used for fusion energy diagnostics, enabling, for example, visual automated logbooks to provide greater insights into chains of plasma events in a discharge, in time for between-shot analysis.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

DOE OSTI2022

Addressing Market Issues in Electrical Power Systems with Large Shares of Variable Renewable Energy

This paper reports recent findings from IEA Wind TCP Task 25, which compiles international experiences and research related to large-scale integration of wind and other renewable energy. In the paper, we address the main challenges for market integration of variable renewable energy, relating to price formation, cost recovery, balancing and other grid services. The paper gives an overview of recent scenario studies on electricity price impacts of (1) various generation, energy storage and demand types in different markets, and (2) different market designs and energy/climate policies. Studying markets with very high shares of variable renewable energy requires an improved set of analysis tools for forecasting market outcomes, estimating flexibility needs and sources, and assessing resource adequacy. Key market features need to be investigated within these improved analytical capabilities for systems transitioning to high shares of variable renewable energy, storage and flexible demand. System services that can be supported by markets will likely need to be revisited. Finally, this paper identifies open questions and suggested future market design work for supporting systems with very high shares of variable renewable energy, which are to be addressed in follow-up work of Task 25 collaborative research.

cost recovery↗

DOE OSTI2024

Analyzing the impact of design factors on solar module thermomechanical durability using interpretable machine learning techniques

Solar modules in utility-scale systems are expected to maintain decades of lifetime to rival conventional energy sources. However, cyclic thermomechanical loading often degrades their long-term performance, highlighting the importance of effective design to mitigate thermal expansion mismatches between module materials. Given the complex composition of solar modules, isolating the impact of individual components on overall durability remains a challenging task. In this work, we analyze a comprehensive data set that comprises bill-of-materials (BOM) and thermal cycling power loss from 251 distinct module designs to identify the predominant design factors and their impacts on the thermomechanical durability of modules. The methodology of our analysis combines machine learning modeling (random forest) and Shapley additive explanation (SHAP) to correlate design factors with power loss and interpret the model’s decision-making. The interpretation reveals that silicon type (monocrystalline or polycrystalline), encapsulant thickness, busbar numbers, and wafer thickness predominantly influence the degradation. With lower power loss of around 0.6% on average in the SHAP analysis, monocrystalline cells present better durability than polycrystalline cells. This finding is further substantiated by statistical testing on our raw data set. The SHAP analysis also demonstrates that while thicker encapsulants lead to reduced power loss, further increasing their thickness over around 0.6 to 0.7 mm does not yield additional benefits, particularly for the front side one. In addition, other important BOM features such as the number of busbars are analyzed. This study provides a blueprint for utilizing explainable machine learning techniques in a complex material system and can potentially guide future research on optimizing the design of solar modules.

14 SOLAR ENERGY↗

DOE OSTI2026

Dara: Automated Multiple-Hypothesis Phase Identification and Refinement from Powder X-ray Diffraction

Powder X-ray diffraction (XRD) is a foundational technique for characterizing crystalline materials. However, the reliable interpretation of XRD patterns, particularly in multiphase systems, remains a manual and expertise-demanding task. As a characterization method that only provides structural information, multiple reference phases can often be fit to a single pattern, leading to potential misinterpretation when alternative solutions are overlooked. To ease humans’ efforts and address the challenge, we introduce Dara (data-driven automated Rietveld analysis), a framework designed to automate the robust identification and refinement of multiple phases from powder XRD data. Dara performs an exhaustive tree search over all plausible phase combinations within a given chemical space and validates each hypothesis using the BGMN Rietveld refinement routine. Key features include structural database filtering, automatic clustering of isostructural phases during tree expansion, and peak-matching-based scoring to identify promising phases for refinement. When ambiguity exists, Dara generates multiple hypothesis which can then be decided between by human experts or with further characterization tools. By enhancing the reliability and accuracy of phase identification, Dara enables scalable analysis of realistic complex XRD patterns and provides a foundation for integration into multimodal characterization workflows, moving toward fully self-driving materials discovery.

Biological databases↗

DOE OSTI2024

PhysBERT: A text embedding model for physics scientific literature

The specialized language and complex concepts in physics pose significant challenges for information extraction through Natural Language Processing (NLP). Central to effective NLP applications is the text embedding model, which converts text into dense vector representations for efficient information retrieval and semantic analysis. In this work, we introduce PhysBERT, the first physics-specific text embedding model. Pre-trained on a curated corpus of 1.2 × 106 arXiv physics papers and fine-tuned with supervised data, PhysBERT outperforms leading general-purpose models on physics-specific tasks, including the effectiveness in fine-tuning for specific physics subdomains.

Hellert, Thorsten (ORCID:0000000227970926)↗

DOE OSTI2021

Creep-fatigue Behavior and Damage Accumulation of a Candidate Structural Material for Concentrating Solar Power Solar Thermal Receiver (Final Technical Report)

Creep-fatigue deformation is an important consideration for a thermal receiver in Concentrating Solar Power systems due to the constant static stress or pressure, diurnal cycling, and elevated service temperatures required for efficient operation. An accurate description of the creep-fatigue behavior, not available for five of the six candidate materials, is important for assessment of preliminary designs. This project has provided a detailed analysis of the creep-fatigue behavior and damage accumulation of Alloy 740H, a candidate structural material for a CSP solar thermal receiver to address a critical knowledge barrier for receiver designs identified in the CSP Gen3 Demonstration Roadmap. This project was divided in to three tasks, split between two general categories: Experimental and design methodology. Tasks 1 and 3, relating to the collection of data on Alloy 740H plate and sheet forms, respectively, were performed at the Idaho National Laboratory and used as input to Task 2, the development of design methodology performed at Argonne National Laboratory. Experimental work covered limited tensile and creep testing to fill gaps in available data that is currently available and to demonstrate how the plate of Alloy 740H tested in this work compared to historical data. A more substantial testing program for fatigue and creep-fatigue was performed, with particular emphasis on creep-fatigue as there is little available data and it is necessary to understand the creep-fatigue interaction and develop related design models. This effort includes the development of rules for the design of solar receiver components against high temperature creep-fatigue and ratcheting failure modes. The ASME Code rules for high temperature nuclear components was used to the basis of the method but adjustments will be made to reflect the generally shorter, diurnal operating cycles of thermal receivers and the relative consequences of failure, comparing nuclear to solar components. This work has provided guidance for the design of components for concentrating power facilities operating at high temperatures and undergoing high, secondary thermal stresses relative to the applied primary pressure stress. The design rules were developed for the design of Generation 3 CSP tubular receivers manufactured from Alloy 740H, but are generally applicable to a wide range of component types undergoing similar loads. Procedural design rules for components to be used in conjunction with the 2019 edition of the ASME Boiler & Pressure Vessel Code and the corresponding design data for Alloy 740H have been developed. A commentary describing the rationale behind the design rules and the data underlying the design material properties, as well as an extensive set of worked sample problems detailing the application of the rules to CSP components were developed as a part of this project, with a separate report covering these aspects in detail and included in the Appendix of this report.

14 SOLAR ENERGY↗

DOE OSTI2021

FY21 Report on Activities for EBS International

This report summarizes the FY21 Activities for EBS International Collaborations Work Package. The international collaborations work packages aim to leverage knowledge, expertise, and tools from the international nuclear waste community, as deemed relevant according to SFWST “roadmap” priorities. This report describes research and development (R&D) activities conducted during fiscal year 2021(FY21) specifically related to the Engineered Barrier System (EBS) R&D Work Package in the Spent Fuel and Waste Science and Technology (SFWST) Campaign supported by the United States (U.S.) Department of Energy (DOE). It fulfills the SFWST Campaign deliverable M4SF- 21SN010308062. The R&D activities described in this report focus on understanding EBS component evolution and interactions within the EBS, as well as interactions between the host media and the EBS. A primary goal is to advance the development of process models that can be implemented directly within the Generic Disposal System Analysis (GDSA) platform or that can contribute to the safety case in some manner such as building confidence, providing further insight into the processes being modeled, establishing better constraints on barrier performance, etc. Sandia National Laboratories is participating in THM modeling in the international projects EBS Task Force and DECOVALEX 2023. EBS Task Force, Task 11 is on modeling of laboratory-scale High Temperature Column Test conducted at Lawrence Berkeley National Laboratory. DECOVALEX 2023, Task C is on THM modeling of the full-scale emplacement experiment (FE experiment) at the Mont Terri Underground Rock Laboratory, Switzerland. This report summarizes Sandia’s progress in the modeling studies of DECOVALEX 2023, Task C. Modeling studies related to the High Temperature Column Test will be documented in future reports.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗

DOE OSTI2026

Scaling Spectroradiometric Monitoring to an Algal Factory Farm

This report briefly summarizes the spectroradiometric approach adapted and deployed as part of Task 4.2 within the BETO-funded D evelopment of I ntegrated S creening, C ultivar O ptimization, and V erification R esearch (DISCOVR) project, specifically task 4, “Increase crop protection and culture stability.” The goals of this subtask were to monitor ponds cultivating a variety of DISCOVR strains at the Arizona Center for Algae Technology and Innovation (AzCATI) with spectroradiometric technology to: • Predict biomass concentrations with high temporal frequency. • Optimize automated analysis methods that enabled feedback for pond automation strategies • Identify pond crash indicators from primary (pest/predator) and indirect (change in algal host) spectroscopic signals with potential for early treatment/intervention • Provide recommendations for technology deployment at scale. This report fulfills the deliverable requirement for the final bullet “provide recommendations for technology deployment at scale”.

09 BIOMASS FUELS↗

DOE OSTI2026

Optimizing Neutrino Flavor Conversion Measurements through Machine Learning

The phenomenon of neutrino flavor conversion whereby the flavor of a neutrino particle can change between its time of production and later detection was the first definitive evidence of physics beyond the Standard Model. Some of the oscillation parameters used to describe this conversion are not yet well measured, leaving important questions still open regarding flavor conversion both in vacuum and as neutrinos travel through matter. NOvA is a long-baseline neutrino oscillation experiment that uses Fermilab's predominantly $\nu_\mu$ NuMI beam. A 14 kton oil-based liquid scintillator far detector 810 km away is used to measure neutrino oscillation through the $\nu_\mu$ disappearance and $\nu_e$ appearance channels. Super-K is a 50 kton water Cherenkov detector, which measures the disappearance of $\nu_e$ produced during solar fusion. The high density environment of the sun decreases the $\nu_e$ survival probability at higher energies observable in Super-K compared to the vacuum-dominated oscillations at lower energies. However, the transition region is overshadowed by radioactive background in the detector. In both of these experiments, the separation of neutrino detection events from background and classification of neutrino flavor are crucial tasks that benefit from the introduction of machine learning. Chapter 1 gives an overview of neutrinos and the context under which flavor conversion is measured in this dissertation. Chapters 2-7 present the results of a Bayesian sampling approach for the latest NOvA 3-flavor oscillation analysis with $26.6 \times 10^{20}$ protons on target in neutrino mode and $12.5 \times 10^{20}$ in antineutrino mode collected over 10 years. Chapters 8-13 present the results of extending the Super-K solar analysis to lower energies during its fourth phase with 2970 days of livetime.

Yankelevich, Alejandro Jaime [UC, Irvine]↗

DOE OSTI2026

Optimizing Neutrino Flavor Conversion Measurements through Machine Learning

The phenomenon of neutrino flavor conversion whereby the flavor of a neutrino particle can change between its time of production and later detection was the first definitive evidence of physics beyond the Standard Model. Some of the oscillation parameters used to describe this conversion are not yet well measured, leaving important questions still open regarding flavor conversion both in vacuum and as neutrinos travel through matter. NOvA is a long-baseline neutrino oscillation experiment that uses Fermilab's predominantly $\nu_\mu$ NuMI beam. A 14 kton oil-based liquid scintillator far detector 810 km away is used to measure neutrino oscillation through the $\nu_\mu$ disappearance and $\nu_e$ appearance channels. Super-K is a 50 kton water Cherenkov detector, which measures the disappearance of $\nu_e$ produced during solar fusion. The high density environment of the sun decreases the $\nu_e$ survival probability at higher energies observable in Super-K compared to the vacuum-dominated oscillations at lower energies. However, the transition region is overshadowed by radioactive background in the detector. In both of these experiments, the separation of neutrino detection events from background and classification of neutrino flavor are crucial tasks that benefit from the introduction of machine learning. Chapter 1 gives an overview of neutrinos and the context under which flavor conversion is measured in this dissertation. Chapters 2-7 present the results of a Bayesian sampling approach for the latest NOvA 3-flavor oscillation analysis with $26.6 \times 10^{20}$ protons on target in neutrino mode and $12.5 \times 10^{20}$ in antineutrino mode collected over 10 years. Chapters 8-13 present the results of extending the Super-K solar analysis to lower energies during its fourth phase with 2970 days of livetime.

Yankelevich, Alejandro Jaime [UC, Irvine]↗

DOE OSTI2026

Optimizing Neutrino Flavor Conversion Measurements through Machine Learning

The phenomenon of neutrino flavor conversion whereby the flavor of a neutrino particle can change between its time of production and later detection was the first definitive evidence of physics beyond the Standard Model. Some of the oscillation parameters used to describe this conversion are not yet well measured, leaving important questions still open regarding flavor conversion both in vacuum and as neutrinos travel through matter. NOvA is a long-baseline neutrino oscillation experiment that uses Fermilab's predominantly $\nu_\mu$ NuMI beam. A 14 kton oil-based liquid scintillator far detector 810 km away is used to measure neutrino oscillation through the $\nu_\mu$ disappearance and $\nu_e$ appearance channels. Super-K is a 50 kton water Cherenkov detector, which measures the disappearance of $\nu_e$ produced during solar fusion. The high density environment of the sun decreases the $\nu_e$ survival probability at higher energies observable in Super-K compared to the vacuum-dominated oscillations at lower energies. However, the transition region is overshadowed by radioactive background in the detector. In both of these experiments, the separation of neutrino detection events from background and classification of neutrino flavor are crucial tasks that benefit from the introduction of machine learning. Chapter 1 gives an overview of neutrinos and the context under which flavor conversion is measured in this dissertation. Chapters 2-7 present the results of a Bayesian sampling approach for the latest NOvA 3-flavor oscillation analysis with $26.6 \times 10^{20}$ protons on target in neutrino mode and $12.5 \times 10^{20}$ in antineutrino mode collected over 10 years. Chapters 8-13 present the results of extending the Super-K solar analysis to lower energies during its fourth phase with 2970 days of livetime.

Yankelevich, Alejandro Jaime [UC, Irvine] (ORCID:0↗

DOE OSTI2023

Using Host Galaxy Photometric Redshifts to Improve Cosmological Constraints with Type Ia Supernovae in the LSST Era

We perform a rigorous cosmology analysis on simulated Type Ia supernovae (SNe Ia) and evaluate the improvement from including photometric host galaxy redshifts compared to using only the "z spec " subset with spectroscopic redshifts from the host or SN. We use the Deep Drilling Fields (~50 deg 2 ) from the Photometric LSST Astronomical Time-Series Classification Challenge (PLAsTiCC) in combination with a low-z sample based on Data Challenge2. The analysis includes light-curve fitting to standardize the SN brightness, a high-statistics simulation to obtain a bias-corrected Hubble diagram, a statistical+systematics covariance matrix including calibration and photo-z uncertainties, and cosmology fitting with a prior from the cosmic microwave background. Compared to using the z spec subset, including events with SN+host photo-z results in (i) more precise distances for z > 0.5, (ii) a Hubble diagram that extends 0.3 further in redshift, and (iii) a 50% increase in the Dark Energy Task Force figure of merit (FoM) based on the w 0 w a CDM model. Analyzing 25 simulated data samples, the average bias on w 0 and w a is consistent with zero. The host photo-z systematic of 0.01 reduces FoM by only 2% because (i) most z < 0.5 events are in the z spec subset, (ii) the combined SN+host photo-z has ×2 smaller bias, and (iii) the anticorrelation between fitted redshift and color self-corrects distance errors. To prepare for analyzing real data, the next SN Ia cosmology analysis with photo-zs should include non–SN Ia contamination and host galaxy misassociations.

79 ASTRONOMY AND ASTROPHYSICS↗

DOE OSTI2022

Analysis of Data Fusion Between Waveform Events and Radionuclide Detections Reported in 2021 by the International Data Centre

During this project, we assessed the percentage of events reported by the International Data Centre (IDC) that are candidates for evaluation using data fusion methods. We calculated the percentage of waveform (seismic, hydroacoustic, infrasound, SHI) events that may be associated with radionuclide (RN) detections and vice versa. For this task, data fusion means identifying RN detections that may be associated with SHI events. The task of producing a fused SHI and RN bulletin is included in the IDC operational manual. As of 2022, the production of a fused event bulletin remains incomplete, largely because methods for producing the bulletin are under development. Nonetheless, simple methods for data fusion have been developed and preliminary software tools are available at the IDC to associate SHI events and RN detections. This report is a first look at the percentage of SHI events that may be candidates for fusion with RN detections or bulletins. One year of IDC bulletin data (2021) is considered in this report. It is important to note that there were no known nuclear explosions during this time period. Hence, we expect that events during this time period would generate SHI and RN signals. If many SHI events are candidates for fusion with RN data, greater priority should be placed on establishing screening procedures before and/or during the fusion process. By contrast, if the number of candidate events is diminishingly small, then data fusion is not a driver for further development of event or detection screening at the IDC. LLNL reviewed the events reported in the Standard Event Bulletin (SEB) and determined which events are candidates for fusion with the Reviewed Radionuclide Reports (RRR). Much of the work involves establishing a metric or metrics for determining whether a Reviewed Event Bulletin (REB) event is a candidate for data fusion.

58 GEOSCIENCES↗

DOE OSTI2025

A hybrid surrogate modeling framework for the Digital Twin of a Fluoride-salt-cooled High-temperature Reactor (FHR)

While nuclear energy is a non-greenhouse-gas emitting energy source, expensive operational costs due to the high-level of safety requirements decreases their competitiveness in the sustainable energy market. Advanced reactor concepts paired with Digital Twins aim to increase the commercialization gains of nuclear energy by reducing operational costs, increasing reactor reliability and enhancing power generation. To support Digital Twin tasks such as real-time autonomous control, proactive maintenance monitoring or optimizing power demand operations, a fast and accurate virtual representation of the Nuclear Power Plant (NPP) is required. The computational cost of high-fidelity, physics-based models are unsuitable for real-time analysis or scalability. Here, in this work, a hybrid surrogate modeling framework is developed fora Fluoride-salt-cooled High-temperature Reactor (FHR) that leverages physics-inspired models for key reactor components and uses data-driven methods for rapid system state space prediction. The Xenon reactivity feedback model is integrated to inform the surrogate model about the reactor core and the homologous pump theory model is the basis for representing pump degradation. Using a detailed, two dimensional thermal hydraulics model to generate data on the FHR, we train a network of Vectorized Autoregressive Moving-Average with eXogenous input (VARMAX) models to predict the remaining state values. The result is a surrogate model that provides a detailed reactor state representation of 41 system states and a pump degradation analysis. The framework is applied to Load Follows profiles, yielding high accuracy and a speedup that is more than 4000x faster compared to the higher- fidelity thermal hydraulics model, enabling real-time operational intelligence and applications in long horizon predictions. While the surrogate model framework is demonstrated for the particular case of FHR, the hybrid physical/data-driven modeling approach including the network of surrogates and the underlying modularity has the potential to be applied to other physical asset systems.

Digital Twins↗