SEARCH · Engineering Papers

Results for “inference accelerators”

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.

SourceResearch connectionFrom yearThrough year

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

At least 235 records · Page 13

All sources NASA NTRS DOE OSTI

DOE OSTI2023

Adaptive learning-driven high-throughput synthesis of oxygen reduction reaction Fe–N–C electrocatalysts

Reducing human reliance on inefficient energy systems and fossil fuels has become more urgent due to the consequences of global climate change. However, traditional trial-and-error approaches have hampered our ability to accelerate the discovery and implementation of functional materials for efficient energy conversion devices, such as polymer electrolyte fuel cells (PEFCs). To address this, we develop an adaptive learning framework that integrates machine learning and state-of-the-art capabilities in high-throughput synthesis to achieve expedited optimization of iron-nitrogen-carbon PEFC oxygen reduction reaction (ORR) electrocatalysts. We use statistical inference, uncertainty quantification, and global optimization to build a computational design-of-experiment tool that identifies the optimum compositions to be investigated next to reduce the demands placed on experimental materials discovery. We benchmark the ability of the proposed strategy to discover optimum catalyst synthesis conditions in a six-dimensional search space when starting with a thirty-six-sample database. By following the adaptive learning strategy, we synthesize fourteen new catalysts from approximately ten billion unique compositions and discover four catalysts that outperform all original samples. The best machine learning-optimized catalyst is 33% more active than the highest-performing one in the initial database, showing an ORR activity seven times larger than those typically reported for the same class of materials.

36 MATERIALS SCIENCE↗

DOE OSTI2025

Basic Research Needs for Inverse Methods for Complex Systems under Uncertainty

Inverse problems, which aim to infer unknown properties of a system using experimental and observational data, are central to addressing many of the U.S. Department of Energy’s (DOE) most critical scientific and engineering challenges. Accurate, computationally efficient, and data-efficient solutions to inverse problems are essential for advancing DOE mission-critical science drivers, including analyzing data from large-scale experimental facilities, optimizing fusion reactor performance, accelerating materials discovery, enhancing geophysical imaging, improving wildfire predictions, and enabling autonomous systems and digital twins. However, these problems are becoming increasingly complex, often involving nonlinear, highdimensional, and interconnected systems and models that span multiple physics and scales, while relying on data with varying quantity, quality, and information content. Compounding these challenges is the uncertainty inherent in DOE-relevant systems, where errors in inputs, noise in data, incompleteness of data, and discrepancies between models and reality constrain the accuracy and precision of solutions. At the same time, the convergence of recent scientific computing trends—scientific machine learning, artificial intelligence, and computing advances such as exascale computing—is creating unprecedented opportunities for tackling these challenges. The cross-cutting nature of inverse problems, combined with their growing complexity and rapidly evolving data and algorithmic demands, strongly motivates the formulation of a prioritized research agenda to maximize their capabilities and impact. In response to this need, DOE’s Advanced Scientific Computing Research (ASCR) program in the Office of Science convened the Workshop on Basic Research Needs for Inverse Problems for Complex Systems Under Uncertainty in June 2025. This workshop brought together experts across disciplines to identify grand challenges and major opportunities in the field. Through collaborative discussions, the workshop defined transformative research directions aimed at addressing the mathematical, statistical, and computational challenges posed by inverse problems under uncertainty. As a result of these efforts, four priority research directions (PRDs) were identified to guide future research and development in this area. These PRDs, summarized below, represent a roadmap for advancing the foundational science and mathematics of inverse problems, enabling robust, scalable, and uncertainty-aware solutions that are critical for DOE applications.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2026

Bridging Cloud and Edge Computing at NREL Using CONNECT: Cloud Optimized Networking for Next-Gen Edge Computing Technologies [Slides]

CONNECT is an innovative on-premise hardware and software solution that integrates edge and cloud computing infrastructure at NREL. Built on the AWS Greengrass middleware and leveraging the MQTT protocol, CONNECT enables real-time data streaming from IoT devices and gateways to both cloud and local services, empowering researchers to rapidly capture, analyze, and act upon edge-generated data while leveraging cloud capabilities. The platform addresses research infrastructure challenges by providing a pre-approved platform which is already configured with the correct networking and cybersecurity baselines thus eliminating procurement delays and enabling on-demand availability. CONNECT's hybrid architecture efficiently manages burstable workloads, allowing research teams to dynamically scale computational capacity, handle peak data loads, and reduce operational bottlenecks. Advanced capabilities include built-in GPU support for executing machine learning models which enables low-latency inference at the edge from models trained in the cloud. This architecture supports real-time analytics and filtering, providing a mechanism to allow only transmitting and processing high-value data. Cloud-based configuration management permits engineers to manage on-premise systems remotely, optimizing operational efficiency. By bridging edge and cloud computing, CONNECT provides NREL researchers with a flexible, scalable platform that accelerates scientific discovery while maintaining robust security and performance standards.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2025

Demonstrate new plasticity models for doped UO 2 that capture dislocation mechanisms

In light water reactors, fuel vendors are investigating the use of dopants to modify the properties of UO 2 pellets, with the goal of improving pellet-cladding mechanical interactions during operation. Dopants are expected to ‘soften’ the pellets; that is, the doped pellets have higher plastic deformation than conventional UO 2 . This leads to a reduction in the severity of mechanical pellet-cladding interactions, helping to reduce the hoop strain on the cladding. By minimizing the strain exerted by the pellet on the cladding, it is anticipated that cladding performance under accident conditions can be enhanced (i.e., lowering the risk of burst during a LOCA). Dopants such as chromium (Cr) promote grain growth during pellet fabrication, leading to larger grains; therefore, understanding the link between chemistry, microstructure and mechanical deformation (enhanced creep rates) behavior of UO 2 is critical to helping operators further substantiate the benefits of doping UO 2 . Historically, the nuclear energy industry has relied on empirical models to make assessments of performance. Compared to empirical models, mechanistic physics-based models provide benefits, such as, fewer data points for validation and better extrapolation where experimental data is scarce or non-existent. In this report, Bayesian inference techniques have been applied to a previously developed lower length-scale-informed diffusional creep model. The objective is to i) infer lower-length-scale parameter distributions from available experiment and then ii) determine the uncertainties in the measurable quantity (in this case creep rates) after propagating the inferred lower length scale parameter uncertainties. The approach requires many evaluations of the model, which becomes computationally insurmountable; therefore, a neural-network model is trained to data obtained by sampling the full model over the most important parameters. This neural-network is then used in the Bayesian inference approach to determine probability distributions in the parameter values that represent the uncertainty in the model given what is known from the experiments (posterior). A significant reduction compared to conservative initial (prior) uncertainties is achieved through inference against the experimental data, demonstrating the efficacy of this approach. Furthermore, by accounting for uncertainties in the experimental conditions and sample non-stoichiometry, it is possible to resolve apparent discrepancies in experimental measurements within a self-consistent grain boundary (Coble) creep model that is sensitive to chemistry. This work has been written up and submitted to Nuclear Technology for a special issue on accelerated fuel qualification (AFQ). This uncertainty quantification (UQ) work not only improves the diffusional model, while accounting for uncertainty, but also establishes a framework which can readily be applied to the mechanistic models of dislocation deformation developed in this study. The most likely values from the Bayesian analysis are incorporated into our UO 2 diffusional creep model and a lower length scale-informed irradiation UO 2 creep mechanistic model to generate a dataset. This dataset has been provided to our INL collaborators for training an artificial neural network surrogate model, which will be implemented in the BISON fuel performance code to assess how the results differ from those currently obtained using a fully empirical model and that of using the nominal (uncalibrated) atomic scale parameters in our mechanistic model. Plastic deformation (creep and glide) in UO 2 is a complex phenomenon, governed by multiple underlying processes such as local defect concentrations, applied stresses, and microstructural characteristics. Consequently, there is a need for a meso-scale model with polycrystalline resolution capable of extrapolating to large grain sizes applicable to doped UO 2 , where data is limited and the model can help bridge the knowledge gap. By integrating atomistic data into the polycrystal LApx code, it becomes possible to predict dislocation climb and glide plasticity that simple analytical models cannot accurately represent. The application of atomic-scale data within LApx demonstrated the importance of climb and glide mechanisms in reproducing high-stress UO 2 behavior. Behaviors such as this are crucial to capture and implement in BISON, as parts of the fuel pellet can reach temperatures where glide can occur before pellet cracking. This model which captures dislocation based mechanisms for UO 2 is then used to stand up the doped model accounting for larger grain sizes. It was found that larger grain sizes can lead to enhanced deformation rates in the glide regime, and therefore can help with the pellet cladding mechanical interaction. Therefore if the fuel pellet reaches conditions (stress/temperature) where glide is active, the enhanced creep rates for larger grains in the glide regime (doped UO 2 ) can help with pellet cladding mechanical interactions. Plastic deformation in UO 2 involves multiple mechanisms, including diffusional creep, dislocation climb, and glide. This milestone contains two parts: (1) UQ of a pre-existing lower length scale informed mechanistic diffusional creep model, and (2) development of a new LApx based model for dislocation-mediated creep mechanisms in UO 2 , with application to large-grain doped UO 2 .

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗

DOE OSTI2026

Machine Learning on Heterogeneous, Edge, and Quantum Hardware for Particle Physics (ML-HEQUPP)

The next generation of particle physics experiments will face a new era of challenges in data acquisition, due to unprecedented data rates and volumes along with extreme environments and operational constraints. Harnessing this data for scientific discovery demands real-time inference and decision-making, intelligent data reduction, and efficient processing architectures beyond current capabilities. Crucial to the success of this experimental paradigm are several emerging technologies, such as artificial intelligence and machine learning (AI/ML) and silicon microelectronics, and the advent of quantum algorithms and processing. Their intersection includes areas of research such as low-power and low-latency devices for edge computing, heterogeneous accelerator systems, reconfigurable hardware, novel codesign and synthesis strategies, readout for cryogenic or high-radiation environments, and analog computing. This white paper presents a community-driven vision to identify and prioritize research and development opportunities in hardware-based ML systems and corresponding physics applications, contributing towards a successful transition to the new data frontier of fundamental science.

Gonski, Julia [SLAC]↗

DOE OSTI2024

Bayes_Opt-SWMM: A Gaussian process-based Bayesian optimization tool for real-time flood modeling with SWMM

Real-time flood model plays a pivotal role in averting urban flood damage, particularly when there is minimal lead time for preparatory measures. However, urban flood modeling in real-time often contends with inherent uncertainties arising from input data uncertainty and parameter ambiguities. Here this study introduces a real-time calibration (RTC) tool called Bayes_Opt-SWMM, specifically tailored for real-time urban flood modeling and uncertainty optimization. This tool leverages the Gaussian process-based Bayesian optimization algorithm and interfaces seamlessly with the Stormwater Management Model (SWMM). It integrates real-time model forcing data and flood monitoring collected through sensors and gauges which are strategically placed within critical locations of urban drainage systems. Our approach hinges on the Surrogate Model based Uncertainty Optimization (SMUO) concept, providing an avenue for enhancing real-time flood modeling. Bayes_Opt-SWMM runs the optimization process using a surrogate model called Gaussian Process emulator with two inference methods: (1) the Gaussian Process (GP) model and (2) Markov Chain Monte Carlo (MCMC) algorithm in GP model (GP_MCMC). Furthermore, three acquisition functions, namely Expected Improvement (EI), Maximum Probability of Improvement (MPI), and Lower Confidence Bound (LCB), facilitate optimal parameter fitting within the surrogate models. The efficiency of GP-based surrogate models in learning SWMM model parameters, leads to an improved uncertainty quantification and accelerated real-time flood modeling in urban areas. Overall, Bayes_Opt-SWMM emerges as a cost-effective and valuable tool for real-time flood modeling and monitoring, with significant potential for managing intelligent storm water systems in urban environments.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2025

Geant4 Event Biasing and Fast Simulation

Geant4 offers advanced event biasing techniques to significantly accelerate simulations involving rare events. Various biasing methods, such as leading particle selection, cross-section biasing, radioactive decay enhancement, and bremsstrahlung splitting, enable efficient event sampling, though they require careful handling. Additionally, Geant4 provides a Fast Simulation Interface, allowing the replacement of standard processes in specific region and for selected particles, enabling faster execution or external code integration. Applications of fast simulation include electromagnetic shower modeling in calorimeters, machine learning inference, and offloading tasks to specialized hardware like GPUs, making Geant4 a powerful tool for computationally demanding simulations.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

DOE OSTI2020

Discovery of a Gamma-Ray Black Widow Pulsar by GPU-accelerated Einstein@Home

We report the discovery of 1.97 ms period gamma-ray pulsations from the 75 minute orbital-period binary pulsar now named PSR J1653-0158. The associated Fermi Large Area Telescope gamma-ray source 4FGL J1653.6-0158 has long been expected to harbor a binary millisecond pulsar. Despite the pulsar-like gamma-ray spectrum and candidate optical/X-ray associations—whose periodic brightness modulations suggested an orbit—no radio pulsations had been found in many searches. The pulsar was discovered by directly searching the gamma-ray data using the GPU-accelerated Einstein@Home distributed volunteer computing system. The multidimensional parameter space was bounded by positional and orbital constraints obtained from the optical counterpart. More sensitive analyses of archival and new radio data using knowledge of the pulsar timing solution yield very stringent upper limits on radio emission. Any radio emission is thus either exceptionally weak, or eclipsed for a large fraction of the time. The pulsar has one of the three lowest inferred surface magnetic-field strengths of any known pulsar with B surf ≈ 4 × 10 7 G. The resulting mass function, combined with models of the companion star's optical light curve and spectra, suggests a pulsar mass gsim 2 M ⊙ . The companion is lightweight with mass ~0.01 M ⊙ , and the orbital period is the shortest known for any rotation-powered binary pulsar. This discovery demonstrates the Fermi Large Area Telescope's potential to discover extreme pulsars that would otherwise remain undetected.

79 ASTRONOMY AND ASTROPHYSICS↗

DOE OSTI2025

Benchmarking the Use of BPM Quadrupole Moments to Measure Emittance

For the PIP-II program, transverse emittance in the Fermilab Booster must remain well controlled at higher bunch intensities. 4-plate beam position monitors (BPMs) have a small but measurable quadrupole moment, making it possible to infer transverse emittance. By compositing many BPMs together, it becomes possible to improve the quality of the quadrupole signal. The Fermilab Booster BPM system has been used to measure these quadrupole moments in the past year and derive emittances from them. Recent benchmarks show that the derived BPM emittances show similar emittance evolution and value to IPM and Multiwire data. This approach can both supplement and complement existing non-intercepting emittance monitors in accelerators.

Balcewicz, M. A. [Fermilab]↗

DOE OSTI2025

Benchmarking the Use of BPM Quadrupole Moments to Measure Emittance

Balcewicz, Michael A. [Fermilab] (ORCID:0009000557↗

DOE OSTI2020

Cross-correlation of the extragalactic gamma-ray background with the thermal Sunyaev-Zel’dovich effect in the cosmic microwave background

Cosmic rays in galaxy clusters are unique probes of energetic processes operating with large-scale structures in the Universe. Precise measurements of cosmic rays in galaxy clusters are essential for improving our understanding of nonthermal components in the intracluster medium (ICM) as well as the accuracy of cluster mass estimates in cosmological analyses. In this paper, we perform a cross-correlation analysis with the extragalactic gamma-ray background and the thermal Sunyaev-Zeldovich (tSZ) effect in the cosmic microwave background. The expected cross-correlation signal would contain rich information about the cosmic-ray-induced gamma-ray emission in the most massive galaxy clusters at $\textit{z}$ ~ 0.1 – 0.2 . We analyze the gamma-ray background map with 8 years of data taken by the Large Area Telescope onboard Fermi satellite and the publicly available tSZ map by Planck. We confirm that the measured cross-correlation is consistent with a null detection, and thus it enables us to put the tightest constraint on the acceleration efficiency of cosmic-ray protons at shocks in and around galaxy clusters. In this work, we find the acceleration efficiency must be below 5% with a 2σ confidence level when the hydrostatic mass bias of clusters is assumed to be 30%, and our result is not significantly affected by the assumed value of the hydrostatic mass bias. Our constraint implies that the nonthermal cosmic-ray pressure in the ICM can introduce only a≲3% level of the hydrostatic mass bias, highlighting that cosmic rays alone do not account for the mass bias inferred by the Planck analyses. Finally, we discuss future detectability prospects of cosmic-ray-induced gamma rays from the Perseus cluster for the Cherenkov Telescope Array.

79 ASTRONOMY AND ASTROPHYSICS↗

DOE OSTI2020

CQNN: a CGRA-based QNN Framework

We propose a novel Coarse-Grained Reconfigurable Architecture-based (CGRA) QNN acceleration framework, CQNN. CQNN has a large number of basic components for binary functions. By programming CQNN at runtime according to the target QNN models, these basic components are integrated efficiently to support QNN functions with any data-width and hyper-parameter requirements and CQNN is reconfigured to have the optimal architecture for the target models. The framework includes compiler, architecture design, simulator and RTL generator. Experimental results show CQNNs can complete the inference of AlexNet and VGG-16 within 0.13ms and 2.63ms.

Geng, Tong↗

DOE OSTI2025

Helium bubble formation in aged plutonium metal at ambient conditions

A model of helium bubble formation is developed that assumes the initial nascent bubbles are generated when two diffusing helium atoms come within a distance of about the interatomic spacing of the plutonium atoms. These nascent bubbles are assumed to be locked in place and grow as additional helium atoms diffuse across their surfaces. Calculations of the helium-bubble number density and sizes as a function of age are compared to experiment. This leads to an inferred helium diffusion coefficient of-the-order of 10 -20 m 2 /s, supports the idea that most of the helium from alpha-decay end up in bubbles, and that previous transmission electron microscopy size estimates are biased low. The energy that helium can transfer to 40-year-old plutonium, upon expansion, is determined to be <0.1 Joules per gram of metal. The model predicts differences between the bubble properties in naturally and accelerated aged plutonium.

36 MATERIALS SCIENCE↗

DOE OSTI2026

Reduced‐Order Modeling of Energetic Materials Using Physics‐Aware Recurrent Convolutional Neural Networks in a Latent Space (LatentPARC)

Physics-aware deep learning (PADL) has gained popularity for use in spatiotemporal dynamics simulations, such as those in computational modeling of energetic materials (EM). We show that the challenge PADL methods face while learning complex field evolution problems can be simplified and accelerated by decoupling it into two tasks: learning complex geometric features in evolving fields and modeling dynamics over these features in a lower-dimensional feature space. We build upon our previous work on physics-aware recurrent convolutional neural networks (PARC). PARC embeds knowledge of underlying physics into its neural network architecture for more robust and accurate prediction of evolving physical fields. PARC was shown to effectively learn complex nonlinear features such as the formation of hotspots and coupled shock fronts in various initiation scenarios of EMs, as a function of microstructures, serving effectively as a microstructure-aware burn model. Here, we further accelerate PARC and reduce its computational cost by projecting the original dynamics onto a lower-dimensional invariant manifold, or “latent space.” The projected latent representation encodes the complex geometry of evolving fields (e.g., temperature and pressure) in a set of data-driven features. The reduced dimension of this latent space allows us to learn the dynamics during the initiation of EM with a lighter and more efficient model. We observe a significant decrease in training and inference time while maintaining results comparable to PARC at inference. This work takes steps towards enabling rapid prediction of EM thermomechanics at larger scales and characterization of EM structure–property–performance linkages at a full application scale.

Mathematics and Computing↗

DOE OSTI2023

Imaging electron angular distributions to assess a full-power petawatt-class laser focus

Here we present a technique to assess the focal volume of petawatt-class lasers at full power. Our approach exploits quantitative measurement of the angular distribution of electrons born in the focus via ionization of rarefied gas, which are accelerated forward and ejected ponderomotively by the field. We show that a bivariate (θ,Φ) angular distribution, which was obtained with image plates, not only enables the peak intensity to be extracted, but also reflects nonideality of the focal-spot intensity distribution. In our prototype demonstration at intensities of a few ×10 19 to a few ×10 20 W/cm 2 , an f/10 optic produced a focal spot in the paraxial regime. This allows a plane-wave parametrization of the peak intensity given by tanθ c =2/a 0 (a 0 being the normalized vector potential and θ c the minimum ejection angle) to be compared with our measurements. Qualitative agreement was found using an a 0 inferred from the pulse energy, pulse duration, and focal spot distribution with a modified parametrization, tanθ c =2η/a 0 ($η=2.02^{+0.26}_{–0.22}$). This highlights the need for (i) better understanding of intensity degradation due to focal-spot distortions and (ii) more robust modeling of the ejection dynamics. Using single-shot detection of electrons, we showed that while there is significant shot-to-shot variation in the number of electrons ejected at a given angular position, the average distribution scales with the pulse energy in a way that is consistent with that seen with the image plates. Finally, we note that the asymptotic behavior as θ→0° limits the usability of angular measurement. For 800 nm, this limit is at an intensity ~10 21 W/cm 2 .

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

DOE OSTI2026

Photoelectrode Durability in Two- versus Three-Electrode Configurations: Understanding the Impact of Circuit Configuration on Water-Splitting Stability

Device durability remains a significant challenge in photoelectrochemical (PEC) water splitting under ambient conditions. Yet, a lack of understanding of the test configuration and applied bias effects continue to hinder progress. In this study, we differentiate two-electrode (2E) and three-electrode (3E) configurations for evaluating PEC material durability, focusing particularly on their impacts on photoabsorber solid-state operating conditions. Our results underscore the fallacy of inferring 2E device stability from durability measurements performed solely in 3E configurations. Unmeasured and often misunderstood total circuit bias in 3E tests moderates material degradation, leading to the overestimation of photoelectrode stability compared to short-circuit operation. We demonstrate how the photoabsorber's operating voltage critically governs charge separation, surface stability, and degradation mechanisms during PEC operation. With these findings, we propose a standardized framework for conducting more reliable 3E durability experiments that simulate unassisted performance to help accelerate the development of robust, stable materials for solar-driven water splitting.

08 HYDROGEN↗

DOE OSTI2025

Geometric GNNs for charged particle tracking at GlueX

Nuclear physics experiments are aimed at uncovering the fundamental building blocks of matter. The experiments involve high-energy collisions that produce complex events with many particle trajectories. Tracking charged particles resulting from collisions in the presence of a strong magnetic field is critical to enable the reconstruction of particle trajectories and precise determination of interactions. It is traditionally achieved through combinatorial approaches that scale worse than linearly as the number of hits grows. Since particle hit data naturally form a point cloud and can be structured as graphs, graph neural networks (GNNs) emerge as an intuitive and effective choice for this task. In this study, we evaluate the GNN model for track finding on the data from the GlueX experiment at Jefferson Lab. We use simulation data to train the model and test on both simulation and real GlueX measurements. We demonstrate that GNN-based track finding outperforms the currently used traditional method at GlueX in terms of segment-based efficiency at a fixed purity while providing faster inferences. We show that the GNN model can achieve significant speedup by processing multiple events in batches, which exploits the parallel computation capability of graphical processing units (GPUs). Finally, we compare the GNN implementation on GPU and field-programmable gate array and describe the trade-off.

batched GNN pipeline↗

DOE OSTI2022

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↗