Search NASA⌕ Search

SEARCH · Search NASA

Results for “Reduced Order”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 955 records · Page 53

Data-Driven Analysis of Multipactor Dynamics via Dynamic Mode Decomposition

Multipactor effect is a performance-limiting kinetic plasma effect that can occur in high-power microwave and radio frequency (RF) devices. Multipactor effect is of special concern in vacuum or near-vacuum conditions such as those in particle accelerators and spaceborne devices. In this work, we present a data-driven reduced-order model (ROM) based on dynamic mode decomposition (DMD) for modeling of multipactor effects. We study multipactor effects and the resulting nonlinear harmonic generation by processing high-fidelity data generated from electromagnetic particle-in-cell (EMPIC) simulations using the DMD algorithm. We also investigate time-delay embedding extensions of DMD with improved generalizability and accuracy for modeling the electron plasma current density behavior. Here, the results show that DMD provides valuable insights into multipactor phenomena by extracting relevant modal spatiotemporal patterns and frequencies. In addition, DMD offers the potential to time extrapolate EMPIC simulations at a minimal cost, thereby reducing overall simulation time.

43 PARTICLE ACCELERATORS↗

Variational encoder geostatistical analysis (VEGAS) with an application to large scale riverine bathymetry

Estimation of riverbed profiles, also known as bathymetry, plays a vital role in many applications, such as safe and efficient inland navigation, prediction of bank erosion, land subsidence, and flood risk management. The high cost and complex logistics of direct bathymetry surveys, i.e, depth imaging, have encouraged the use of indirect measurements such as surface flow velocities. However, estimating high-resolution bathymetry from indirect measurements is an inverse problem that can be computationally challenging. Here, we propose a reduced-order model (ROM) based approach that utilizes a variational autoencoder (VAE), a type of deep neural network with a narrow layer in the middle, to compress bathymetry and flow velocity information and accelerate bathymetry inverse problems from flow velocity measurements. In our application, the shallow-water equations (SWE) with appropriate boundary conditions (BCs), e.g., the discharge and/or the free surface elevation, constitute the forward problem, to predict flow velocity. Then, ROMs of the SWEs are constructed on a nonlinear manifold of low dimensionality through a variational encoder and the bathymetry inversion problem is derived on the low-dimensional latent space in a Hierarchical Bayesian setting. Further, the reformulation allows variational inference with a small number (e.g., $\mathscr{O}$ (100) of ROM runs and efficient uncertainty quantification. We have tested our inversion approach on a one-mile reach of the Savannah River, GA, USA. Once the neural network is trained (offline stage), the proposed technique can perform the inversion operation orders of magnitude faster than traditional inversion methods that are commonly based on linear projections, such as principal component analysis (PCA), or the principal component geostatistical approach (PCGA). Furthermore, tests show that the algorithm can estimate the bathymetry with good accuracy even with sparse flow velocity measurements.

54 ENVIRONMENTAL SCIENCES↗

From Machine Learning to Nuclear Digital Twins

This presentation provides multiple case studies of Machine Learning, Uncertainty Quantification, Reduced Order Modeling, to achieve digital transformation and provide the components for nuclear digital twinning. The presentation is for an international virtual event titled: Consultancy Meeting on Applications of AI and Pattern Recognition Techniques for Uncertainty Quantification in Nuclear Power Modelling and Simulation held Oct 21-22, 2021.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗

Physics-Informed Active Learning With Simultaneous Weak-Form Latent Space Dynamics Identification

The parametric greedy latent space dynamics identification (gLaSDI) framework has demonstrated promising potential for accurate and efficient modeling of high-dimensional nonlinear physical systems. However, it remains challenging to handle noisy data. Here, to enhance robustness against noise, we incorporate the weak-form estimation of nonlinear dynamics (WENDy) into gLaSDI. In the proposed weak-form gLaSDI (WgLaSDI) framework, an autoencoder and WENDy are trained simultaneously to discover intrinsic nonlinear latent-space dynamics of high-dimensional data. Compared with the standard sparse identification of nonlinear dynamics (SINDy) employed in gLaSDI, WENDy enables variance reduction and robust latent space discovery, therefore leading to more accurate and efficient reduced-order modeling. Furthermore, the greedy physics-informed active learning in WgLaSDI enables adaptive sampling of optimal training data on the fly for enhanced modeling accuracy. The effectiveness of the proposed framework is demonstrated by modeling various nonlinear dynamical problems, including viscous and inviscid Burgers' equations, time-dependent radial advection, and the Vlasov equation for plasma physics. With data that contains 5%–10% Gaussian white noise, WgLaSDI outperforms gLaSDI by orders of magnitude, achieving 1%–7% relative errors. Compared with the high-fidelity models, WgLaSDI achieves 121 to 1779x speed-up.

97 MATHEMATICS AND COMPUTING↗

Genetic programming for the nuclear many-body problem: a guide

Genetic Programming (GP) is an evolutionary algorithm that generates computer programs, or mathematical expressions, to solve complex problems. In this Guide, we demonstrate how to use GP to develop surrogate models to mitigate the computational costs of modeling atomic nuclei with ever increasing complexity. The computational burden escalates when uncertainty quantification is pursued, or when observables must be globally computed for thousands of nuclei. By studying three models in which the mean field depends on the total particle density self-consistently, we show that by constructing reduced order models supported by GP one can speed up many-body computations by several orders of magnitude with a negligible loss in accuracy.

dimensionality reduction↗

Sensor enabled data-driven predictive analytics for modeling and control with high penetration of DERs in distribution systems

The electric power grid is undergoing a tremendous transformation due to the increasing penetration of renewable energy resources beginning with wind and more recently with the distributed energy resources (DERs) such as solar and battery storage. DERs have dramatically changed the role of the distribution systems in the overall power grid, and they are expected to contribute a significant portion of power generation in the future. If current trends for DERs continue, system operation and control will need to change dramatically for improved grid reliability and resiliency. As renewable resources increase in penetration, new and challenging operational, planning, and design problems are expected to emerge. Some of the key challenges that arise in the planning and operation of the future grid are: 1) Quantifying the impact of high DER penetration in distribution systems on bulk grid behavior over multiple time scales. 2) Identifying whether a particular DER configuration/settings have a large impact on the overall grid behavior. These challenges can be addressed in an offline manner using detailed T&D grid models and they can also be addressed in an online manner using sensor measurements. In particular, the advancement and planned growth in sensor technology in power grid over various voltage levels provide us with a unique opportunity to tackle these challenges from a data analytic perspective without needing detailed T&D grid models. A few questions that naturally arise when addressing the challenges from DERs using sensor data are: 1) How can we use limited sensor measurements to monitor & control voltage stability and small signal stability of the bulk system? 2) How can we ensure that the developed data analytic methods are robust to data availability and quality issues? 3) How can we compute the developed analytics in a scalable manner using streaming measurements? In this project, we addressed the aforementioned challenges arising from DERs and answered the questions raised above on how to effectively use the sensor measurements to enhance the reliability and performance of the electric grid. Thus, the overarching goal of this project is to develop effective reduced/representative system models from data that make the computational complexity sufficiently manageable so as to be useful to simulate, analyze, and even control complex non-linear power systems dynamics with large penetrations of DERs. In order to achieve the objective, the project team established a four-fold technical approach 1) Formulated a combined transmission-distribution co-simulation framework for data generation and validation, 2) Derived reduced/representative models of power systems based on data-driven methods for efficient computation and appropriate representation of system behavior, 3) Developed data driven characterization of power system behavior based on transfer operator theory, machine learning and optimization for model estimation, 4) Incorporated a scalable data management and processing architecture using distributed Kafka streaming applications that coordinate input data streams to the developed data analytics. The key accomplishments of the project are: 1) Development of a scalable multi-timescale T&D co-simulation framework (both for steady state and for dynamic co-simulation) using commercial solvers (PSSE and GridLAB-D). The steady-state T&D co-simulation interface is shared with our industry partner (PJM). 2) A structured reduced order dynamic model of distribution systems that can represent partial motor stalling along with a systematic procedure to derive the model parameters. 3) A PMU based online method to monitor, localize and mitigate fault-induced delayed voltage recovery using DER reactive support and load control in distribution systems. 4) Development of linear operator based robust methodologies for dynamic state estimation, uncertainty quantification, system identification and trajectory prediction for power system dynamics. 5) An adaptive damping control for utilizing wind energy resources to provide oscillation damping and system stability. 6) Implementation of Kafka-based framework for efficient processing of streaming data using Linux-based local virtual environment.

DER integration↗

Impacts of Different Operation Conditions and Geological Formation Characteristics on CO2 Sequestration in Citronelle Dome, Alabama

Major concerns of carbon dioxide (CO2) sequestration in subsurface formations are knowledge of the well injectivity and gas storage capacity of the formation, the CO2 pressure and saturation plume extensions during and after injection, and the risks associated with CO2 leakage and fault reactivation. Saline reservoirs are considered as one of the target formations for CO2 sequestration through structural, residual, dissolution, and mineral trapping mechanisms. The boundary condition of the saline reservoir dictates the pressure and saturation plume extension of the injected supercritical CO2 that could expand over large distances. This can lead to sources of risk, e.g., leakage and/or fault reactivation due to presence of wells, thief zones, and geological discontinuities. Therefore, there is a critical need to develop a model that describes how risk-related performance metrics (i.e., the CO2 saturation plume size, the pressure differential plume area, and the pressure differential at specific locations) vary as a function of the size of injection, time following injection, injection operations, and geologic environment. In this study, a systematic reservoir modeling studies of anthropogenic CO2 sequestration in Citronelle dome, Alabama, was performed where all relevant scenarios and conditions to address the questions of the saturation and pressure plume size in the area of review (AoR) and post-injection site care (PISC) are considered. The objective for this study was firstly to systematically simulate CO2 sequestration, i.e., saturation dynamics, and pressure behavior over a range of operational and geological conditions and to derive conclusions about the factors influencing saturation and pressure plume size, post-injection behavior, and the risk associated with them, by developing third-generation reduced order models (ROMs) for reservoir behavior. Finally, to assess the uncertainty associated with our studies, Latin Hypercube Sampling (LHS) together with an experimental design technique, i.e., Plackett–Burman design, was used. Application of Pareto charts and respond surfaces enabled us to determine the most important parameters impacting saturation and pressure plume sizes and to quantify the auto- and cross-correlation among different parameters in both history-matched and upscaled models.

58 GEOSCIENCES↗

Design of Digital Twin Sensing Strategies Via Predictive Modeling and Interpretable Machine Learning

This work develops a methodology for sensor placement and dynamic sensor scheduling decisions for digital twins. The digital twin data assimilation is posed as a classification problem, and predictive models are used to train optimal classification trees that represent the map from observed data to estimated digital twin states. In addition to providing a rapid digital twin updating capability, the resulting classification trees yield an interpretable mathematical representation that can be queried to inform sensor placement and sensor scheduling decisions. The proposed approach is demonstrated for a structural digital twin of a 12 ft wingspan unmanned aerial vehicle. Offline, training data are generated by simulating scenarios using predictive reduced-order models of the vehicle in a range of structural states. Furthermore, these training data can be further augmented using experimental or other historical data. In operation, the trained classifier is applied to observational data from the physical vehicle, enabling rapid adaptation of the digital twin in response to changes in structural health. Within this context, we study the performance of the optimal tree classifiers and demonstrate how they enable explainable structural assessments from sparse sensor measurements and also inform optimal sensor placement.

47 OTHER INSTRUMENTATION↗

Statistical Correlation of Heliostat Pointing Deviation With Wind

This work was carried out as part of the Heliostat Consortium (HelioCon) Field Deployment subtask with the aim to develop a reduced order model framework for correlating wind speed and pointing deviation of a heliostat facet. There are only sparse field measurements of heliostat pointing deviations and accompanying wind conditions published in the literature. Heliostat test standards, such as IEC 62862-4-3, propose a suite of tests including laser pointing repeatability at wind speeds below 4 m/s, and provide technical requirements for heliostat slope and tracking deviations in coarse average wind speed bins of 4 m/s, 6 m/s, and 8 m/s. In addressing the gap of the variation of heliostat pointing deviation with wind speed, field measurements of laser pointing on a grid target and wind conditions were analyzed in this study at the Third-Party Metrology Platform at the National Laboratory of the Rockies (NLR) Flatirons Campus. Horizontal pointing deviations were found to follow a logarithmic relationship with peak wind speed, whereas vertical pointing deviations follow an exponential relationship with peak wind speed. Both horizontal and vertical pointing deviations also follow a second order polynomial relationship, as expected from the proportionality of elastic loads and deformations with the square of wind speed. The results indicate that heliostat facet pointing deviations in the vertical direction increase at a faster rate than in the horizontal direction with increasing wind speed over the tested range, however these are dependent on the heliostat structural design. Next steps are recommended for additional field measurements to confirm a linear relationship of pointing deviation with applied moment on a heliostat facet, and to distinguish between gravity-induced and wind-induced pointing deviations at different elevation angles. The derived correlations in the preliminary analysis in this report serve as a case study for heliostat developers and plant operators to estimate the wind-induced pointing deviations and their variation with peak gust wind speed. Next steps in future work would recommend higher resolution and longer duration datasets for different elevation angles and wind directions to reduce uncertainties and variance of collected laser beam spot data and their correlations with bin-averaged wind speed.

17 WIND ENERGY↗

Automated Parameterized CFD Simulations of Phase-Change Material Embedded Heat Exchangers

Thermal storage can be implemented using Phase-Change Materials (PCM), which absorb significant latent heat with a relatively small temperature change. PCM phase-change processes are transient and are driven by thermal diffusion and natural convection – the latter, especially for melting process. Modeling and simulation of PCM heat exchangers is typically computationally intensive due to the relative complex time-dependent underlying physics. This paper presents a study investigating a single straight tube with circular transverse fins in the vertical orientation, using PCM’s with 37oC nominal melting temperature, leveraging automated parametric CFD simulations. The computational domain is reduced to 2D axisymmetric for a segment of the HX comprising a region in between two fins with constant wall temperature as boundary condition. This approach allows for faster evaluations of the transient thermal characteristics for a given design space of interest. Correlations and reduced order models (ROM’s) are developed. Results indicate that the ROM’s reproduce the CFD simulations with high accuracy for designs from the training data set, however, designs from cross-validation and test sets do not always have good agreement. The limited number of designs in the training set is a possible cause for the lack of robustness of the ROM’s and thus additional training designs will be added in future work. The ROM’s solve the simulations on average 500,000 times faster than CFD.

25 ENERGY STORAGE↗

Orthogonal decomposition as a design tool: With application to a mixing impeller

Digital manufacturing eliminates the expense and time required to develop custom products. By utilizing this technology, designers can quickly create a customized product specifically for their performance needs. But the timescale and expense from the engineering design workflows used to develop these customized products have not been adapted from the workflows used in mass production. In many cases these customized designs build upon already successful mass-produced products that were developed using conventional engineering design workflows. Many times as part of this conventional design process significant time is spent creating and validating high fidelity models that accurately predict the performance of the final design. These existing validated high fidelity models used for the mass-produced design can be reused for analysis and design of unknown products. This thesis explores the integration of reduced order modeling and detailed analysis into the engineering design workflow developing a customized design using digital manufacturing. Specifically, detailed analysis is coupled with proper orthogonal decomposition to enable the exploration of the design space while simultaneously shaping the model representing the design. This revised workflow is examined using the design of a laboratory scale overhead mixer impeller. The case study presented here is compared with the design of the Kar Dynamic Mixer impeller developed by The Dow Chemical Company. The result of which is a customized design for a refined set of operating conditions with improved performance.

20 FOSSIL-FUELED POWER PLANTS↗

SURROGATE MODEL DEVELOPMENT AND VALIDATION FOR RELIABILITY ANALYSIS OF REACTOR PRESSURE VESSELS

In nuclear light water reactors (LWRs), the reactor coolant, core and shroud are contained within a massive, thick walled steel vessel known as a reactor pressure vessel (RPV). Given the tremendous size of these structures, RPVs typically contain a large population of pre-existing flaws introduced in the manufacturing process. After many years of operation, irradiation-induced embrittlement makes these vessels increasingly susceptible to fracture initiation at the locations of the pre-existing flaws. Because of the uncertainty in the loading conditions, flaw characteristics and material properties, probabilistic methods are widely accepted and used in assessing RPV integrity. The Fracture Analysis of Vessels – Oak Ridge (FAVOR) computer program developed by researchers at Oak Ridge National Laboratory is widely used for this purpose. This program can be used in order to perform deterministic and probabilistic risk-informed analyses of the structural integrity of an RPV subjected to a range of thermal-hydraulic events. FAVOR uses a one-dimensional representation of the global response of the RPV, which is appropriate for the beltline region, which experiences the most embrittlement, and employs an influence coefficient technique to rapidly compute stress intensity factors for axis-aligned surface-breaking flaws. The Grizzly code is currently under development at Idaho National Laboratory (INL) to be used as a general multiphysics simulation tool to study a variety of degradation mechanisms in nuclear power plant components. The first application of Grizzly has been to study fracture in embrittled RPVs. Grizzly can be used to model the thermo-mechanical response of an RPV under transient conditions observed in a pressurized thermal shock (PTS) scenario. The global response of the vessel provides boundary conditions for local 3D models of the material in the vicinity of a flaw. Fracture domain integrals are computed to obtain stress intensity factors, which can in turn be used to assess whether a fracture would initiate at a pre-existing flaw. To use Grizzly for probabilistic analysis, it is necessary to have a way to rapidly evaluate stress intensity factors. To accomplish this goal, a reduced order model (ROM) has been developed to efficiently represent the behavior of a detailed 3D Grizzly model used to calculate fracture parameters. This approach uses the stress intensity factor influence coefficient method that has been used with great success in FAVOR. Instead of interpolating between tabulated solutions, as FAVOR does, the ROM approach uses a response surface methodology to compute fracture solutions based on a sampled set of results used to train the ROM. The main advantages of this approach are that the process of generating the training data can be fully automated, and the procedure can be readily used to consider more general flaw configurations. This paper demonstrates the procedure used to generate a ROM to rapidly compute stress intensity factors for axis-aligned flaws. The results from this procedure are in good agreement with those produced using the traditional influence coefficient interpolation procedure, which gives confidence in this method. This paves the way for applying this procedure for more general flaw configurations.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

Three-dimensional flow model development for thermal mixing and stratification modeling in reactor system transients analyses

Mixing, thermal-stratification, and mass transport phenomena in large pools or enclosures play major roles for the safety of reactor systems. Depending on the fidelity requirement and computational resources, various modeling methods, from the 0-D perfect mixing model to 3-D Computational Fluid Dynamics (CFD) models, are available. Each is associated with its own advantages and shortcomings. It is very desirable to develop an advanced and efficient thermal mixing and stratification modeling capability embedded in a modern system analysis code to improve the accuracy of reactor safety analyses and to reduce modeling uncertainties. An advanced system analysis tool, SAM, is being developed at Argonne National Laboratory for advanced non-LWR reactor safety analysis. While SAM is being developed as a system-level modeling and simulation tool, a reduced-order three-dimensional module is under development to model the mull-dimensional flow and thermal mixing and stratification in large enclosures of reactor systems. This paper provides an overview of the three-dimensional finite element flow model in SAM, including the governing equations, stabilization scheme, and solution methods. Additionally, several verification and validation tests are presented, including lid-driven cavity flow, natural convection inside a cavity, laminar flow in a channel of parallel plates. Here, based on the comparisons with the analytical solutions and experimental results, it is demonstrated that the developed 3-D fluid model can perform very well for a wide range of flow problems.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

A Data-Driven Nonparametric Approach for Probabilistic Load-Margin Assessment Considering Wind Power Penetration

A modern power system is characterized by an increasing penetration of wind power, which results in large uncertainties in its states. These uncertainties must be quantified properly; otherwise, the system security may be threatened. Facing this challenge, here we propose a cost-effective, data-driven approach to assessing a power system's load margin probabilistically. Using actual wind data, a kernel density estimator is applied to infer the nonparametric wind speed distributions, which are further merged into the framework of a vine copula. The latter enables us to simulate complex multivariate and highly dependent model inputs with a variety of bivariate copulae that precisely represent the tail dependence in the correlated samples. Furthermore, to reduce the prohibitive computational time of traditional Monte-Carlo simulations that process a large amount of samples, we propose to use a nonparametric, Gaussian-process-emulator-based reduced-order model to replace the original complicated continuation power-flow model through a Bayesian-learning framework. To accelerate the convergence rate of this Bayesian algorithm, a truncated polynomial chaos surrogate, which serves as a highly efficient, parametric Bayesian prior, is developed. This emulator allows us to execute the time-consuming continuation power-flow solver at the sampled values with a negligible computational cost. Results of simulations that are performed on several test systems reveal the impressive performance of the proposed method in the probabilistic load-margin assessment.

17 WIND ENERGY↗

Shape optimization under uncertainty for rotor blades of horizontal axis wind turbines

We present a computational framework for the shape optimization of a Horizontal-Axis Wind Turbine (HAWT) rotor blade under uncertainty. Our framework integrates aerodynamic simulations based on the blade element method which utilizes reduced order models of the blade structure and wind load with design sensitivity analysis and nonlinear programming. The wind velocity is modeled as a stochastic process to account for variations in time and space. An additional stochastic process accounts for uncertainties in the structural material properties. The uncertainty propagation is based on a non-intrusive polynomial chaos expansion that allows accurate estimation of stochastic performance metrics such as generated power and structural compliance. Sensitivities of cost and constraint functions with respect to shape parameters namely twist angles are computed with an efficient scheme to enable gradient based optimization. To demonstrate the effect of uncertainty, designs obtained from optimization under uncertainty are compared to those obtained from deterministic optimization.

42 ENGINEERING↗

A COUPLED DETERMINISTIC TRANSPORT CALCULATION IN COMSOL USING PROPER ORTHOGONAL DECOMPOSITION

A coupled physics problem consisting of radiation transport and heat transfer was modeled using COMSOL Multiphysics to simulate a criticality accident. Reduced order models (ROM) were created to accelerate the radiation transport calculation through Proper Orthogonal Decomposition (POD). Additionally, on-the-fly neutron cross sections were generated from a non-linear function through a feed forward neural network. The Livelink for MATLAB module allowed for data transfer between an otherwise independent solver and in-house modules. A data driven approach to POD was developed to act as a surrogate model to couple with heat transfer, with the POD module written in MATLAB coupled to an isolated heat transfer solve in COMSOL. A coupled transient solution resulted in a good approximation of the flux and temperature, with the maximum error being 3E-2 and 2.5E-3 respectively.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

Forward sensitivity analysis and mode dependent control for closure modeling of Galerkin systems

Model reduction by projection-based approaches is often associated with losing some of the important features that contribute towards the dynamics of the retained scales. As a result, a mismatch occurs between the predicted trajectories of the original system and the truncated one. We put forth a framework to apply a continuous time control signal in the latent space of the reduced order model (ROM) to account for the effect of truncation. We set the control input using parameterized models by following energy transfer principles. Our methodology relies on observing the system behavior in the physical space and using the projection operator to restrict the feedback signal into the latent space. Then, we leverage the forward sensitivity method (FSM) to derive relationships between the feedback and the desired mode-dependent control. We test the performance of the proposed approach using two test cases, corresponding to viscous Burgers and vortex merger problems at high Reynolds number. Results show that the ROM trajectory with the applied FSM control closely matches its target values in both the data-dense and data-sparse regimes.

97 MATHEMATICS AND COMPUTING↗

Risk assessment of wellbore leakage during underground hydrogen storage

The expansion of renewable energy sources would require large-scale energy storage options to overcome the intermittent nature of these sources. Underground hydrogen storage (UHS) in depleted hydrocarbon reservoirs offers a scalable and practical energy storage solution. These reservoirs are chosen for their availability and large capacity, but the unique properties of hydrogen raise concerns about potential leakage pathways, particularly through wellbores. In this study, we develop and apply, for the first time, reduced-order models (ROMs) specifically designed for efficient leakage risk prediction in UHS systems operating in depleted hydrocarbon reservoirs. Using 3,000 high-fidelity simulation scenarios, we examine the influence of 11 key parameters, including reservoir and aquifer depths, wellbore permeability and porosity, initial saturations of water, oil and gas fractions (hydrogen, light, intermediate, and heavy hydrocarbons), reservoir pressure multiplier, and the aquifer-to-reservoir volume ratio, to simulate leakage behavior over a 1,000-year timescale. We train ROMs using a two-step classification-regression approach, achieving R 2 values exceeding 99 % across all targets. These ROMs effectively capture the leakage evolution and identify critical controls of leakage, guiding the design of mitigation strategies. Results indicate that gas leakage occurs in about 27 % of scenarios as early as five years post-operation, reaching volumes of up to 106 ft3. Oil leakage is less frequent (~17 %) and typically begins decades later. Our findings also show that hydrogen often migrates first, owing to its smaller molecular size and higher buoyancy, followed by heavier hydrocarbons. Over time, these heavier components contribute significantly to the total leaked volume, reinforcing the need for targeted monitoring and remediation strategies. Our analysis highlights that deeper storage reservoirs, shallower aquifers, and low-permeability wellbores significantly reduce leakage risks. In conclusion, this work offers a robust framework for risk-informed UHS deployment, supporting energy security through reliable large-scale hydrogen storage while safeguarding environmental integrity.

08 HYDROGEN↗