Search NASA⌕ Search

SEARCH · Search NASA

Results for “Generalization error”

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 163 records · Page 9
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Predicting critical heat flux with uncertainty quantification and domain generalization using conditional variational autoencoders and deep neural networks

Deep generative models (DGMs) can generate synthetic data samples that closely resemble the original dataset, addressing data scarcity. In this work, we developed a conditional variational autoencoder (CVAE) to augment critical heat flux (CHF) data used for the 2006 Groeneveld lookup table. To compare with traditional methods, a fine-tuned deep neural network (DNN) regression model was evaluated on the same dataset. Both models achieved small mean absolute relative errors, with the CVAE showing more favorable results. Uncertainty quantification (UQ) was performed using repeated CVAE sampling and DNN ensembling. The DNN ensemble improved performance over the baseline, while the CVAE maintained consistent results with less variability and higher confidence. Both models achieved small errors inside and outside the training domain, with slightly larger errors outside. Altogether, the CVAE performed better than the DNN in predicting CHF and exhibited better uncertainty behavior.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2025

Water Dielectric Function at Finite Wavelength and the Convergence of Its Large Wavelength Limit (Static Dielectric) by Fluctuation Formulas

Here we provide a general analysis of the longitudinal dielectric function ε l (k) via fluctuation formulas at finite wavelength k, including the static dielectric constant ε w = ε l (k → 0), and analyze the different sources of errors, deriving explicit formulas. Simulations with the SPC/E water model show that the convergence of fluctuation formulas to compute the static dielectric constant is slow and requires long simulations. The analysis of ε l (k) allows us to identify the long- and short-wavelength limits and provide a precise determination of the location of the poles as well as the zeros in the complex plane, which determine the short-distance form of the electrostatic (Coulomb) interaction among charged particles.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2025

Efficient Training of Deep Neural Operator Networks via Randomized Sampling

Neural operators (NOs) employ deep neural networks to learn the mappings between infinitedimensional function spaces. Deep operator network (DeepONet), a popular NO architecture, has demonstrated success in the real-time prediction of complex dynamics across various scientific and engineering applications. In this work, we introduce a random sampling technique to be adopted during the training of DeepONet, aimed at improving the generalization ability of the model, while significantly reducing the computational time. The proposed approach targets the trunk network of the DeepONet model that outputs the basis functions corresponding to the spatiotemporal locations of the bounded domain on which the physical system is defined. While constructing the loss function, DeepONet training traditionally considers a uniform grid of spatiotemporal points at which all the output functions are evaluated for each iteration. This approach leads to a larger batch size, resulting in poor generalization and increased memory demands, due to the limitations of the stochastic gradient descent (SGD) optimizer. The proposed random sampling over the inputs of the trunk net mitigates these challenges, improving generalization and reducing the memory requirements during training, resulting in significant computational gains. We validate our hypothesis through three benchmark examples, demonstrating substantial reductions in training time while achieving comparable or lower overall test errors relative to the traditional training approach. Our results indicate that incorporating randomization in the trunk network inputs during training enhances the efficiency and robustness of DeepONet, offering a promising avenue for improving the framework’s performance in modeling complex physical systems.

Karumuri, Sharmila [Department of Civil & Systems ↗
DOE OSTI2026

Synthesis of ARM User Facility Surface Rainfall Datasets to Construct a Best Estimate Value Added Product (PrecipBE)

Surface precipitation measurements are essential for Earth system model (ESM) evaluation and understanding cloud processes. An ever-growing need for robust, temporally evolving, and easy-to-use statistical datasets provides motivation for a baseline ground-based precipitation properties data product. The U.S. Department of Energy Atmospheric Radiation Measurement (ARM) user facility operates an extensive suite of precipitation instruments with various sensitivities and operating mechanisms, which render the decision of which instrument to use based on one or more fixed thresholds challenging and prone to errors and bias. Using a long-term instrument inter-comparison from a unique per-precipitation event perspective, rather than instantaneous sample comparison, we demonstrate that ARM rainfall-measuring instruments are generally consistent with each other at the statistical level. Inter-instrument deviations at the single event level can be large, especially for specific rainfall event properties such as maximum precipitation rates. A machine-learning (ML) analysis using a random forest regressor indicates that in some cases, depending on instrument, local site climatology, and/or specific deployment configuration, certain atmospheric state variables influence the measured quantities in an unpredictable manner. Thus, a-priori weighting of different instruments does not necessarily lead to more accurate and less biased synthesis of instrument data. These results motivate the design of the ARM precipitation best-estimate (PrecipBE) value-added product, which incorporates all valid precipitation data while considering data quality and other instrument limitations. PrecipBE consists of time series and tabular statistics datasets in an easy-to-use and insightful per-precipitation event format. It provides a large set of precipitation event properties supplemented with ancillary data from ARM datasets that correspond to the detected precipitation events. We describe the PrecipBE algorithm and demonstrate its use via the examination of a single-day output as well as a long-term trend analysis of precipitation events at the ARM Southern Great Plains (SGP) site, covering more than 30 years of data. The trend analysis tentatively suggests a long-term temporal tendency for mainly shorter and less intense precipitation events at the SGP site, but a long-term increase in annual rainfall by more than 36 mm (5 %) per decade. This rainfall trend is catalyzed primarily by more extreme event properties of relatively rare, intense precipitation events, with event total and 1 min maximum precipitation rate at a 1 year timeframe increasing up to 5 mm and 9 mm h −1 (several percent) per decade, respectively. While the currently available PrecipBE datasets (at https://adc.arm.gov/discovery/, last access: 8 December 2025) cover rainfall from multiple ARM deployments up to March 2025, PrecipBE is planned to be expanded to include solid-phase precipitation and will soon become an operational product with a several-day lag from real-time. We invite the ARM user community to leverage this new product and welcome user feedback to further enhance the dataset.

Silber, Israel [Pacific Northwest National Laborat↗
DOE OSTI2025

The approximate second order coupled-cluster method based on a size-consistent Brillouin–Wigner partitioning

We present a variant of the approximate second order coupled-cluster method (CC2) with a two-parameter size-consistent Brillouin–Wigner (BW-s) partitioning instead of a Møller–Plesset (MP) partitioning for the unperturbed Hamiltonian, which we refer to as BWs-CC2. The computational complexity of this model scales identically to CC2 with molecular size. Conventional CC2 and its regularized BWs-CC2 variants, as well as conventional MP2 and two of its regularized BW-s2 variants, were assessed on a 535 element database spanning thermochemistry, non-covalent interactions, barrier heights, and isomerization energies. To ensure a well-defined model chemistry, the assessment was performed using internally stable spin-polarized Hartree–Fock (HF) orbitals in the finite aug-cc-pVQZ basis without counterpoise corrections. As a result of using stable orbitals, contrary to conventional wisdom, we find that CC2 substantially outperforms MP2 on molecules with significantly spin contaminated reference orbitals without a significant increase in error on systems with a spin-pure reference, showing the value of its single substitutions. While no single choice of regularization parameters can be optimal for all datasets, we find that BWs-CC2 generally outperforms both CC2 and BW-s2 with a single judicious parameter choice. Additional tests on dipole moments and bond lengths of diatomics provide further support for the utility of this choice. Furthermore, the main outliers and poorest performing cases are associated with large amounts of spin-contamination in the HF reference, which is indicative of systems with either strong correlation or extensive artificial symmetry breaking. Overall, these findings argue that the perception of the quality of the CC2 ground state should be reevaluated and that it can be further improved upon by the soundly based BWs-CC2 variant with the recommended parameter choice.

Correlation energy↗
DOE OSTI2025

Error field identification through torque balance on a saturated island in DIII-D

Measurement of the electromagnetic torque on a magnetic island could be an attractive method for error field identification in the early phase of ITER operation. Previous DIII-D experiments (Strait 2014 Nucl. Fusion 54 073004; Shiraki et al 2015 Plasma Phys. Control. Fusion 57 025016) have demonstrated the principle of this approach using a stationary or slowly rotating island, while recent developments in magnetic data analysis (Sweeney and Strait 2019 Phys. Plasmas 26 012509) allow the field of a rapidly rotating island to be readily distinguished from that of the wall currents induced by its rotation. In a recent experiment, a rotating n = 1 magnetic perturbation forced a saturated magnetic island to rotate, thus sampling all toroidal phases periodically in a single discharge. The phase and amplitude of the error field are inferred from analysis of the time-dependent torque balance on the island, including torques from the error field, the applied magnetic perturbation, and the wall currents induced by rotation of the applied perturbation and the island. Furthermore, results agree well with those from more conventional methods.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2024

Design of a Three-Layer Impactor for Material Strength Measurements at Multi-Megabar Pressures

Off-Hugoniot loading methods for dynamic compression have been a topic of interest for many years as a means of accessing high pressures without melting a material. Simulations and an initial test experiment of a three-layer gas-gun impactor suitable for use in measuring dynamic material strength at multi-megabar pressures are described. As shown through ARES hydrocode simulations, an impactor consisting of a low-, medium-, and high-impedance material, such as TPX, Al, and Ta or Pt, can produce a quasi-isentropic loading path up to 4.6 Mbar pressure with a low homologous temperature (T/T melt = 0.1–0.25). These impactors can also be tailored to create a pressure drive suitable for a Lagrangian sound speed experiment. Simulated in-situ velocities were analyzed to determine the change in calculated strength due to non-uniformity in the impactor, which provides a measure of error sensitivity. An initial test of a three-layer projectile onto a flat target at 4.4 km/s impact velocity is reported. Finally, while the impactor incurred some delamination during firing, the measured sample/window interface velocity generally agrees with the simulated peak velocity and subsequent release, indicating the feasibility of this approach for measuring material strength.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗
DOE OSTI2025

Assessing the numerical stability of physics models to equilibrium variation through database comparisons on DIII-D

High fidelity kinetic equilibria are crucial for tokamak modeling and analysis. Manual workflows for constructing kinetic equilibria are time consuming and subject to user error, motivating development of automated equilibrium reconstruction tools to provide accurate and consistent reconstructions for downstream physics analysis. These automated tools also provide access to kinetic equilibria at large database scales, which enables the quantification of general uncertainties arising from equilibrium reconstruction techniques. In this paper, we compare a large database of DIII-D kinetic equilibria generated manually by physics experts to equilibria from automated kinetic reconstruction tools, assessing the impact of reconstruction method on equilibrium parameters and resulting magnetohydrodynamic stability calculations. We find agreement among scalar parameters, whereas profile quantities, such as the bootstrap current, show larger disagreements. We analyze ideal kink and classical tearing stability with DCON and STRIDE respectively, finding that the kink stability calculation is generally more robust than the tearing index Δ' calculation. We find that in 90% of cases, both kink stability classifications are unchanged between the manual expert and automated kinetic equilibria.

CAKE↗
DOE OSTI2025

Code Coverage Status of the ARC code GAMSRC

The Argonne Reactor Code (ARC) software system supports users in their fast reactor design goals by providing neutronic, thermal-hydraulic, and structural analysis capabilities. GAMSOR serves as procedure to obtain the neutron and gamma power distribution information in the ARC code system. GAMSOR is a specially modified version of DIF3D (dif3d.x becomes dif3d_gamsor.x). After some work, it was determined that carrying out software on GAMSOR was impractical and would not fit well with commercial grade dedication. GAMSRC was written in the last decade to replace GAMSOR such that the user can rely soley upon the verified DIF3D (dif3d.x) code and GAMSRC to obtain the neutron and gamma power distribution information. GAMSRC is also fully verified and ready for commercial grade dedication. In the coming years, GAMSOR will be deprecated and GAMSRC will fully take over in the ARC code system. This document identifies the set of test problems used to assess the code coverage for GAMSRC. The goal is to document what parts of the existing GAMSRC code are touched by the set of test problems and which are not. The code coverage analysis of GAMSRC was performed with the Code Coverage Tool of the Intel Fortran compiler which requires modifications to the compilation of GAMSRC. The code coverage tables are given for each submodule of GAMSRC. Because GAMSRC links to modules in DIF3D, some details on coverage changes to the DIF3D lined files is provided. As will be seen, most of the uncovered parts/files can be ignored because they are either for error message and debugging output or obviously not needed by GAMSRC today.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2025

Using Multiple Isotope-Labeled Infrared Spectra for the Structural Characterization of an Intrinsically Disordered Peptide

Intrinsically disordered proteins (IDPs) rapidly interconvert between conformers, requiring an ensemble description. This complicates their experimental characterization, and force field limitations pose challenges for their simulation. Here, in this work, we use isotope-labeled and unlabeled infrared (IR) spectra to reweight simulated ensembles of the elastin-like peptide GVGVPGVG, a paradigmatic disordered peptide. By comparing the results obtained with different spectra, we explicitly show that the weights are underdetermined by the ensemble averaged data. We identify which labels and frequency regions maximize structural information while minimizing sensitivity to simulation error and show that these regions report on whether the peptide makes specific interactions. Our work shows the importance of incorporating simulations and simulated spectra at the planning stages of isotope-labeled IR experiments and more generally provides a framework for interpreting IR data for IDPs.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2025

Quantifying uncertainty in uranium concentration measurements via K-edge densitometry

This study quantifies the uncertainty in uranium concentration predictions of fluoride and chloride-based salts within a steel pipe using K-edge densitometry. Modeling and simulation was conducted with the Monte Carlo N-Particle Transport (MCNP) code. The quality of of this technique’s prediction in a pipe requires proper characterization of the pipe’s thickness, which is dependent on the source size and axial offset from the pipe centerline. The thickness was determined as either the center-line thickness seen by the X-ray source or an average value determined through random sampling. Generally, the predicted concentrations were slightly better at lower offset with the random sampling thickness and using the center-line thickness for the highest offsets. For a line-beam source and varying axial offsets, the relative error of concentration was within 1% of the true value but uncertainty increased by 2 orders of magnitude. Similarly, for no axial offset, the relative error was significantly less than 1% while no trend for uncertainty was found. However, at the largest possible offset for a given source size, the concentrations become erroneous and greater than the allowable 1% relative error. Furthermore, high offsets tended to increase the variance of the transmission spectra by 3 orders of magnitude.

Characterization and Analytical Technique↗
DOE OSTI2025

Advancing stream temperature prediction with a generalizable large-sample framework across CONUS river reaches

Accurately predicting stream temperature in ungauged basins remains a critical challenge for water resource management, thermoelectric power plant cooling, and ecosystem conservation. Large-sample machine learning models trained on hundreds of well-monitored river basins have shown remarkable performance; however, such models have yet to be developed solely using forcing data that can be readily extracted to simulate stream temperatures anywhere in the contiguous United States (CONUS). In this study, we present a scalable, large-sample deep learning framework using Long Short-Term Memory (LSTM) networks to simulate daily stream temperatures in ungauged basins across the CONUS. The framework leverages both modeled reanalysis of meteorological and streamflow inputs as well as static attributes available for all 2.7 million CONUS river reaches in the National Hydrography Dataset Plus (NHDPlusV2). By generating dynamical inputs from predefined thermally relevant upstream contributing areas, rather than the entire upstream basin, the model also offers improvements in very large basins where full-basin averaging can dilute the most important influences on stream temperature. Evaluated across 300 basins, the model achieves a median Mean Absolute Error (MAE) of 1.1 °C and a Nash-Sutcliffe Efficiency (NSE) of 0.95 on temporally and spatially distinct test folds—comparable to models trained exclusively using meteorological and streamflow observational data. The flexible, high-performing framework generalizes to any unmonitored river reach without significant regulation or unnatural thermal input immediately upstream, substantially expanding predictive capabilities in data-scarce regions.

Hydrology↗
DOE OSTI2025

Tree tensor network hierarchical equations of motion based on time-dependent variational principle for efficient open quantum dynamics in structured thermal environments

In this work, we introduce an efficient method, TTN-HEOM, for exactly calculating the open quantum dynamics for driven quantum systems interacting with highly structured bosonic baths by combining the tree tensor network (TTN) decomposition scheme with the bexcitonic generalization of the numerically exact hierarchical equations of motion (HEOM). The method yields a series of quantum master equations for all core tensors in the TTN that efficiently and accurately capture the open quantum dynamics for non-Markovian environments to all orders in the system–bath interaction. These master equations are constructed based on the time-dependent Dirac–Frenkel variational principle, which isolates the optimal dynamics for the core tensors given the TTN ansatz. The dynamics converges to the HEOM when increasing the rank of the core tensors, a limit in which the TTN ansatz becomes exact. We introduce TENSO, tensor equations for non-Markovian structured open systems, as a general-purpose Python code to propagate the TTN-HEOM dynamics. We implement three general propagators for the coupled master equations: two fixed-rank methods that require a constant memory footprint during the dynamics and one adaptive-rank method with a variable memory footprint controlled by the target level of computational error. We exemplify the utility of these methods by simulating a two-level system coupled to a structured bath containing one Drude–Lorentz component and eight Brownian oscillators, which is beyond what can presently be computed using the standard HEOM. Our results show that the TTN-HEOM is capable of simulating both dephasing and relaxation dynamics of driven quantum systems interacting with structured baths, even those of chemical complexity, with an affordable computational cost.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2025

Near-Efficient and Non-Asymptotic Multiway Inference

We establish non-asymptotic efficiency guarantees for tensor decomposition–based inference in count data models. Under a Poisson framework, we consider two related goals: (i) parametric inference , the estimation of the full distributional parameter tensor, and (ii) multiway analysis , the recovery of its canonical polyadic (CP) decomposition factors. Our main result shows that in the rank-one setting, a rank-constrained maximum-likelihood estimator achieves multiway analysis with variance matching the Cramér–Rao Lower Bound (CRLB) up to absolute constants and logarithmic factors. This provides a general framework for studying “near-efficient” multiway estimators in finite-sample settings. For higher ranks, we illustrate that our multiway estimator may not attain the CRLB; nevertheless, CP-based parametric inference remains nearly minimax optimal, with error bounds that improve on prior work by offering more favorable dependence on the CP rank. Numerical experiments corroborate near-efficiency in the rank-one case and highlight the efficiency gap in higher-rank scenarios.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Thermodynamics-informed latent space dynamics identification

This software showcases a latent space dynamics identification method, namely tLaSDI, that embeds the first and second principles of thermodynamics. The latent variables are learned through an autoencoder as a nonlinear dimension reduction model. The latent dynamics are constructed by a neural network-based model that precisely preserves certain structures for the thermodynamic laws through the GENERIC formalism. An abstract error estimate is established, which provides a new loss formulation involving the Jacobian computation of autoencoder. The autoencoder and the latent dynamics are simultaneously trained to minimize the new loss. Computational examples demonstrate the effectiveness of tLaSDI, which exhibits robust generalization ability, even in extrapolation. In addition, an intriguing correlation is empirically observed between a quantity from tLaSDI in the latent space and the behaviors of the full-state solution.

Cheung, Siu Wun↗
DOE OSTI2025

Hiperclust

This software leverages transfer learning to analyze atom probe tomography (APT) data. It is trained on synthetic data and then applies this knowledge to predict the optimal number of clusters for a given APT dataset. Initially, the software used preliminary clustering to estimate the general structure of the data. Based on this, it provides suggestions for key parameters like minimum cluster size and minimum number of points. These parameters are critical for algorithms like HDBSCAN, ensuring accurate cluster formation without the need for trial-and-error testing. The software runs on High-Performance computing (HPC) systems, enabling fast, scalable analysis of large APT datasets, ultimately saving time and improving the reliability of clustering outcomes.

Tang, Yalei [Idaho National Laboratory (INL), Idah↗
DOE OSTI2024

Physics-Based Machine Learning Methods for U-235 Forensics Signatures

Signatures of low-intensity U-235 sources have been recently studied by utilizing a variety of machine learning (ML) classifiers using features derived from gamma spectral measurements collectedunder structured campaigns. Several ML classifiers, such as ensemble of tress and classification trees, revealed misleadingly-optimistic training error due to over-fitting, and furthermore,their performance is not directly relatable to the physical properties due to their data-driven, opaque designs. We present a regression-based ML method that first estimates the inverse distanceto the source and then utilizes a threshold to infer its presence, by representing the background as a source located at an infinite distance. For the inverse distance estimation, we study the ensembleof trees and Gaussian process regression methods, and a hyper parameter auto-tuning and selection method that employs five regression estimators. These methods avoid the over-fittingobserved in several ML classifiers, while providing the classification error nearly comparable to them based on independent test data. Their error is directly related to estimates of the inversephysical distance to source, and the precision of error determines the seperability property that determines the false alarm and missed detection rates. The property of monotonic decrease of thesource strength with increasing detector distance combined with Poisson distribution of measurements is utilized to analytically validate these methods by deriving the generalization equations ofunderlying regression methods.

Rao, Nageswara↗
DOE OSTI2026

Estimators and Fusers for Fiber Delay Estimation Using Environmental Measurements

The properties of deployed network fiber are affected by environmental factors due to their exposure to the elements. Particularly for quantum networks, the resultant delay variations may have significant impacts due to the extreme sensitivity of synchronization, coincidence counting, and other critical operations. In this paper, the delays of 15 km aerial-inground fiber connections are measured, and effects due to temperature, humidity and wind speed are analyzed over multiple periods spanning four seasons of a year. Machine learning methods are first utilized to reveal surprisingly pronounced effects of humidity on the delay, in addition to the expected temperature and its seasonal variations. Estimator and fusion methods are developed to estimate the delay using temperature, humidity and wind speed measurements, by utilizing smooth Gaussian Process Regression (GPR) and nonsmooth Ensemble of Trees (EOT) methods. Measurements from winter and summer periods are temporally fused using twelve different methods, and eight methods provide estimates for the delay throughout the year with median test errors under 1.28%. The results reveal distinct temperature-humidity trends across the seasons, and the ability of estimator and temporal fusion methods to exploit them for estimating the delay. These results constitute a case study of machine learning analytical results, wherein generalization equations explain the performance of various estimator and fuser methods.

Rao, Nageswara [ORNL] (ORCID:0000000234085941)↗