Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “deep ensemble”

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 37 records · Page 2
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Physics-based hybrid machine learning for critical heat flux prediction with uncertainty quantification

Critical heat flux (CHF) is a key quantity in nuclear system modeling due to its impact on heat transfer, safety margins, and reactor performance. This study develops and validates an uncertainty-aware hybrid modeling approach that combines machine learning with physics-based models to predict CHF in cases of dryout. The Biasi and Bowring empirical correlations were paired with three ML uncertainty quantification (UQ) techniques: deep neural network (DNN) ensembles, Bayesian neural networks (BNNs), and deep Gaussian processes (DGPs). A pure ML model without a base model was evaluated for comparison. Model performance was assessed under plentiful (7,350 points) and limited (9 points) training data scenarios using parity, uncertainty distributions, and calibration curves. Results show that the Biasi hybrid DNN ensemble achieved the best overall performance, with a mean absolute relative error of 1.846%, and well-calibrated uncertainty estimates. The BNN-based hybrids showed slightly higher error (2.14%) but superior uncertainty calibration. DGP models underperformed, with over 6% error and poor uncertainty calibration. All hybrid models outperformed pure machine learning configurations, demonstrating resistance against data scarcity. These findings indicate that hybrid modeling significantly improves predictive accuracy, interpretability, and resilience to data scarcity. The integration of uncertainty awareness provides actionable confidence in CHF predictions, which is vital for safety-critical decisions in nuclear applications. This hybrid approach offers a viable pathway for deploying ML models in reactor analysis tools while preserving domain knowledge and physical consistency.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
NASA NTRSDate not supplied

DeepONet-Assisted Optimization of Surface Topography for Transition Delay in A Mach 4.5 Boundary Layer

We use deep learning, an ensemble variationaltechnique (EnVar), and direct numerical simulations(DNS) to design an optimal topography for a two-dimensional roughness element that delays the on-set of laminar-turbulent transition in a Mach 4.5 flat-plate boundary layer. Deep operator networks (Deep-ONets), which have the known ability to learn com-plex nonlinear operators within dynamical systems,are used for machine learning. For the baseline config-uration of a smooth flat plate, the second-mode wavesat the DNS inflow cause a quick nonlinear breakdownof the high-speed boundary layer within the computa-tional domain. Results reported in the present studyvalidate the ability of DeepONets to model the tran-sition delay via a given topography of the roughnesselement. The computing cost to optimize the rough-ness element for minimal skin-friction drag is substan-tially lowered by the DeepONets-based reduced-ordermodel. In comparison to the baseline method of EnVaroptimization based on DNS alone, the DeepONets-based EnVar optimizer is able to delay transition pastthe outflow boundary of the computational domainwhile utilizing almost 5–6 times fewer DNS.

Machine Learning↗
NASA NTRSDate not supplied

DeepONet-Assisted Optimization of Surface Topography for Transition Delay in a Mach 4.5 Boundary Layer

We use deep learning, an ensemble variational technique (EnVar), and direct numerical simulations(DNS) to design an optimal topography for a two-dimensional roughness element that delays the on-set of laminar-turbulent transition in a Mach 4.5 flat-plate boundary layer. Deep operator networks (DeepONets), which have the known ability to learn complex nonlinear operators within dynamical systems, are used for machine learning. For the baseline configuration of a smooth flat plate, the second-mode waves at the DNS inflow cause a quick nonlinear breakdown of the high-speed boundary layer within the computational domain. Results reported in the present study validate the ability of DeepONets to model the transition delay via a given topography of the roughness element. The computing cost to optimize the rough-ness element for minimal skin-friction drag is substantially lowered by the DeepONets-based reduced-order model. In comparison to the baseline method of EnVar optimization based on DNS alone, the DeepONets-based EnVar optimizer is able to delay transition past the outflow boundary of the computational domain while utilizing almost 5–6 times fewer DNS.

Machine Learning↗
NASA NTRSDate not supplied

Consistent Pixel Resolution Characterization of Deep Convective Clouds for Calibration

The NASA CERES project provides global TOA shortwave and longwave fluxes for climate monitoring and validation that spans over 20 years. CERES utilizes broadband fluxes derived from geostationary (GEO) imagers to estimate broadband fluxes between the CERES observations. In order for these fluxes to be viable, the GEO imager calibration must be stable over time. One such calibration method used by CERES is to evaluate ensemble sets of deep convective clouds (DCC) as invariant targets (IT) over time. DCC targets can also provide radiometric scaling between sensors. An international collaboration through GSICS is also evaluating the DCC-IT calibration methodology to provide consistent calibration coefficients across geostationary sensors. Tropical DCC are the coldest, brightest, and most Lambertian TOA Earth targets identified using a window channel brightness temperature threshold. The DCC-IT technique involves a large ensemble of TOA pixel-level reflectances, which are binned into probability density functions (PDF). The PDF structure dependency on sensor pixel resolution, which can vary greatly among sensors, is not well known. This study will identify the impact of pixel resolution on the DCC PDFs by aggregating VIIRS and Landsat OLI/TIRS pixel resolutions into various coarser pixel resolutions and comparing the shape and statistics of the resulting PDFs. This study should assist in mitigating the pixel resolution dependency in the DCC-IT approach for providing scaling factors between sensors.

Conor Haney↗
NASA NTRS1992

Infrared, microwave, and spaceborne radar simulations of a deep convective system using a 3-D cloud ensemble method

A 3D cloud model is used to simulate the storm structure, and the results are linked to microwave and infrared radiative transfer models for simulation of aircraft observations. Spaceborne radar data are also simulated along the aircraft flight track. The cloud and radiative model simulations are studied and compared with aircraft observations. The initial results indicate that the 3D cloud model is capable of simulating the major features of observed storm systems when given a representative atmospheric sounding to initialize the convective systems. The simulations of infrared and microwave radiances provide reasonably good comparisons with the observations.

Yeh, H.-Y. M.↗
DOE OSTI2026

Coherence-Induced Deep Thermalization Transition in Random Permutation Quantum Dynamics

We report a phase transition in the projected ensemble—the collection of postmeasurement wave functions of a local subsystem obtained by measuring its complement. The transition emerges in systems undergoing random permutation dynamics, a type of quantum time evolution wherein computational basis states are shuffled without creating superpositions. It separates a phase exhibiting deep thermalization, where the projected ensemble is distributed over Hilbert space in a maximally entropic fashion (Haar random), from a phase where it is minimally entropic (“classical bit-string ensemble”). Crucially, this deep thermalization transition is invisible to the subsystem’s density matrix, which always exhibits thermalization to infinite temperature across the phase diagram. Through a combination of analytical arguments and numerical simulations, we show that the transition is tuned by the total amount of injected by the input state and the measurement basis, and is exhibited robustly across different microscopic models. Our findings represent a novel form of ergodicity-breaking universality in quantum many-body dynamics, characterized not by a failure of regular thermalization, but rather by a failure of deep thermalization.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2025

Transfer learning of neural surrogates on multifidelity groundwater simulations

Multifidelity data used in the paper published in Advances in Water Resources 206 (2025) 105140, https://doi.org/10.1016/j.advwatres.2025.105140 The code used to process the data is openly available on GitHub at https://github.com/Model-Reduction-and-UQ-Group/Transfer_Learning_K_reconstruction Computationally inexpensive surrogates of process-based models, such as deep neural networks, enable ensemble-based computations used in risk assessment, data assimilation, etc. However, generation of large datasets required to train a neural network can be as expensive as the ensemble simulations themselves. We ameliorate this challenge by using data from multifidelity (MF) groundwater simulations and transfer learning (TL) to reduce data generation costs while maintaining model accuracy. As a computational example, we train a deep convolutional neural network (CNN) to reconstruct permeability fields from saturation maps derived from a multiphase flow model. Starting with very low- and low-fidelity data generated on increasingly coarse meshes, we pretrain the CNN, followed by output-layer training and fine-tuning using only a limited number of high-fidelity samples. We demonstrate the surrogate’s robustness when interpreting low-quality inputs—such as interpolated maps or data affected by noise—which has strong implications for the applicability in practical hydrogeological scenarios. This multilevel MF-TL strategy achieves a favorable trade-off between computational efficiency and predictive accuracy, significantly outperforming high-fidelity-only approaches under the same computational budget.

Chiofalo, Alessia [University of Bologna] (ORCID:0↗
DOE OSTI2026

Uncertainty guided online ensemble for non-stationary data streams in fusion science

Machine Learning (ML) is poised to play a pivotal role in the development and operation of next-generation fusion devices. Fusion data shows non-stationary behavior with distribution drifts, resulted by both experimental evolution and machine wear-and-tear. ML models assume stationary distribution and fail to maintain performance when encountered with such non-stationary data streams. Online learning techniques have been leveraged in other domains, however it has been largely unexplored for fusion applications. In this paper, we investigate online learning for continuous adaptation to drifting data streams in the prediction of Toroidal Field (TF) coils deflection at the DIII-D fusion facility. We further address the short-term performance degradation inherent to standard online learning, which arises because ground truth is unavailable at prediction time. To mitigate this issue, we propose an uncertainty-guided online ensemble framework. The method leverages the Deep Gaussian Process Approximation (DGPA) for calibrated uncertainty estimation and uses these uncertainty measures to guide a meta-algorithm that aggregates predictions from learners trained over different historical horizons. Our results show that online learning reduces prediction error by 80% compared to a static model. The online ensemble and the proposed uncertainty-guided ensemble further reduce error by approximately 6%, and 10% respectively, relative to standard single-model online learning, while also providing calibrated uncertainty estimates to support operational decision-making.

AI↗
DOE OSTI2025

Uncertainty based Online Ensemble on Non-Stationary Data for Fusion Science

Machine Learning (ML) is poised to play a pivotal role in the development and operation of next-generation fusion devices. Fusion data shows non-stationary behavior due to drifts in the data. The drifts can arise from both experimental evolution and machine wear-and-tear. ML models assume stationary distribution and fail to maintain performance when encountered with non-stationary data streams.Online learning can be used to continuously adapt the models with new data as it is acquired. However, traditional online learning can suffer from short-term performance degradation, as ground truth are not available before making the prediction. To address this challenge, we propose uncertainty aware ensemble approach for online learning. We use Deep Gaussian Process Approximation (DGPA) technique for calibrated uncertainty estimation and use the uncertainty values to guide a meta-algorithm that produces predictions based on ensemble of learners. Moreover, DGPA also provides uncertainty estimation along with the predictions for decision makers. This paper demonstrates that the proposed method outperforms traditional online learning approach, and a naive ensemble without uncertainty guidance by about 7% and 6%, respectively, on B-coil deflection prediction at DIII-D Fusion Facility.

Rajput, Kishansingh [Thomas Jefferson National Acc↗
DOE OSTI2025

Uncertainty based Online Ensemble on Non-Stationary Data for Fusion Science

Machine Learning (ML) is poised to play a pivotal role in the development and operation of next-generation fusion devices. Fusion data shows non-stationary behavior due to drifts in the data. The drifts can arise from both experimental evolution and machine wear-and-tear. ML models assume stationary distribution and fail to maintain performance when encountered with non-stationary data streams.Online learning can be used to continuously adapt the models with new data as it is acquired. However, traditional online learning can suffer from short-term performance degradation, as ground truth are not available before making the prediction. To address this challenge, we propose uncertainty aware ensemble approach for online learning. We use Deep Gaussian Process Approximation (DGPA) technique for calibrated uncertainty estimation and use the uncertainty values to guide a meta-algorithm that produces predictions based on ensemble of learners. Moreover, DGPA also provides uncertainty estimation along with the predictions for decision makers. This paper demonstrates that the proposed method outperforms traditional online learning approach, and a naive ensemble without uncertainty guidance by about 7% and 6%, respectively, on B-coil deflection prediction at DIII-D Fusion Facility.

Rajput, Kishansingh [Thomas Jefferson National Acc↗
DOE OSTI2025

Resolving Mesoscale Convective Systems: Grid Spacing Sensitivity in the Tropics and Midlatitudes

Abstract Mesoscale convective systems (MCSs) are a critical global water cycle component and drive extreme precipitation events in tropical and midlatitude regions. However, simulating deep convection remains challenging for modern numerical weather and climate models due to the complex interactions of processes from microscales to synoptic scales. Recent models with kilometer‐scale horizontal grid spacings offer notable improvements in simulating deep convection compared to coarser‐resolution models. Still, deficiencies in representing key physical processes, such as entrainment, lead to systematic biases. Additionally, evaluating model outputs using process‐oriented observational data remain difficult. This study presents an ensemble of MCS simulations with spanning the deep convective gray zone ( from 12 km to 125 m) in the Southern Great Plains of the U.S. and the Amazon Basin. Comparing these simulations with Atmospheric Radiation Measurement (ARM) wind profiler observations, we find greater sensitivity in the Amazon Basin compared to the Great Plains. Convective drafts converge structurally at sub‐kilometer scales, but some deficiencies remain. In both regions, simulated up and downdrafts are too deep and extreme downdrafts are not strong enough. Furthermore, Amazonian updrafts are too strong. Overall, we observe higher sensitivity in the tropics, including an artificial buildup in vertical kinetic energy at scales of , suggesting a need for 250 m in this region. Nevertheless, bulk convergence—agreement of storm‐average statistics—is achievable with kilometer‐scale simulations within a 10% error margin with 1 km providing a good balance between accuracy and computational cost.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

Maximum Entropy Principle in Deep Thermalization and in Hilbert-Space Ergodicity

We report universal statistical properties displayed by ensembles of pure states that naturally emerge in quantum many-body systems. Specifically, two classes of state ensembles are considered: those formed by (i) the temporal trajectory of a quantum state under unitary evolution or (ii) the quantum states of small subsystems obtained by partial, local projective measurements performed on their complements. These cases, respectively, exemplify the phenomena of “Hilbert-space ergodicity” and “deep thermalization.” In both cases, the resultant ensembles are defined by a simple principle: The distributions of pure states have maximum entropy, subject to constraints such as energy conservation, and effective constraints imposed by thermalization. We present and numerically verify quantifiable signatures of this principle by deriving explicit formulas for all statistical moments of the ensembles, proving the necessary and sufficient conditions for such universality under widely accepted assumptions, and describing their measurable consequences in experiments. We further discuss information-theoretic implications of the universality: Our ensembles have maximal information content while being maximally difficult to interrogate, establishing that generic quantum state ensembles that occur in nature hide (scramble) information as strongly as possible. Our results generalize the notions of Hilbert-space ergodicity to time-independent Hamiltonian dynamics and deep thermalization from infinite to finite effective temperature. Our work presents new perspectives to characterize and understand universal behaviors of quantum dynamics using statistical and information-theoretic tools.

Eigenstate thermalization↗
DOE OSTI2025

Joint state-parameter estimation for the reduced fracture model via the united filter

Here, in this paper, we introduce an effective United Filter method for jointly estimating the solution state and physical parameters in flow and transport problems within fractured porous media. Fluid flow and transport in fractured porous media are critical in subsurface hydrology, geophysics, and reservoir geomechanics. Reduced fracture models, which represent fractures as lower-dimensional interfaces, enable efficient multi-scale simulations. However, reduced fracture models also face accuracy challenges due to modeling errors and uncertainties in physical parameters such as permeability and fracture geometry. To address these challenges, we propose a United Filter method, which integrates the Ensemble Score Filter (EnSF) for state estimation with the Direct Filter for parameter estimation. EnSF, based on a score-based diffusion model framework, produces ensemble representations of the state distribution without deep learning. Meanwhile, the Direct Filter, a recursive Bayesian inference method, estimates parameters directly from state observations. The United Filter combines these methods iteratively: EnSF estimates are used to refine parameter values, which are then fed back to improve state estimation. Numerical experiments demonstrate that the United Filter method surpasses the state-of-the-art Augmented Ensemble Kalman Filter, delivering more accurate state and parameter estimation for reduced fracture models. This framework also provides a robust and efficient solution for PDE-constrained inverse problems with uncertainties and sparse observations.

Bayesian inference↗
NASA NTRS1984

Using GPS and VLBI technology to maintain 14 digit synchronization

To facilitate the navigation of spacecraft to the outer planets, Jupiter and beyond, the JPL-NASA Deep Space Network (DSN) has implemented three ensembles of atomic clocks at widely separated locations. These clocks must be maintained, synchronized, to with a few parts in 10 to the 13th power of each other and, the entire group must be maintained, to a lesser degree, in synchronism with Coordinated Universal Time (UTC)NBS/USNO. Over the last 1 1/2 years the DSN has been using Global Positioning Satellites (GPS) and Very Long Baseline Interferometry (VLBI) technology to perform these critical Frequency and Time (F&T) synchronization tasks. A year of F&T synchronization data collected from the intercomparison of 3 sets of cesium and hydrogen maser driven clock ensembles through the use of GPS and VLBI techniques are covered. Also covered, are some of the problems met and limitations of these two techniques at their present level of technology.

Ward, S. C.↗
NASA NTRS2023

Global and Zonal-Mean Hydrological Response to Early Eocene Warmth

Earth's hydrological cycle is expected to intensify in response to global warming, with a “wet-gets-wetter, dry-gets-drier” response anticipated over the ocean. Subtropical regions (∼15°–30°N/S) are predicted to become drier, yet proxy evidence from past warm climates suggests these regions may be characterized by wetter conditions. Here we use an integrated data-modeling approach to reconstruct global and zonal-mean rainfall patterns during the early Eocene (∼56–48 million years ago). The Deep-Time Model Intercomparison Project (DeepMIP) model ensemble indicates that the mid- (30°–60°N/S) and high-latitudes (>60°N/S) are characterized by a thermodynamically dominated hydrological response to warming and overall wetter conditions. The tropical band (0°–15°N/S) is also characterized by wetter conditions, with several DeepMIP models simulating narrowing of the Inter-Tropical Convergence Zone. However, the latter is not evident from the proxy data. The subtropics are characterized by negative precipitation-evaporation anomalies (i.e., drier conditions) in the DeepMIP models, but there is surprisingly large inter-model variability in mean annual precipitation (MAP). Intriguingly, we find that models with weaker meridional temperature gradients (e.g., CESM, GFDL) are characterized by a reduction in subtropical moisture divergence, leading to an increase in MAP. These model simulations agree more closely with our new proxy-derived precipitation reconstructions and other key climate metrics and imply that the early Eocene was characterized by reduced subtropical moisture divergence. If the meridional temperature gradient was even weaker than suggested by those DeepMIP models, circulation-induced changes may have outcompeted thermodynamic changes, leading to wetter subtropics. This highlights the importance of accurately reconstructing zonal temperature gradients when reconstructing past rainfall patterns.

Margot J. Cramwinckel↗
DOE OSTI2025

LTAU-FF: Loss Trajectory Analysis for Uncertainty in atomistic Force Fields

Model ensembles are effective tools for estimating prediction uncertainty in deep learning atomistic force fields. However, their widespread adoption is hindered by high computational costs and overconfident error estimates. In this work, we address these challenges by leveraging distributions of per-sample errors obtained during training and employing a distance-based similarity search in the model latent space. Our method, which we call LTAU (Loss Trajectory Analysis for Uncertainty), efficiently estimates the full probability distribution function of errors for any test point using the logged training errors, achieving speeds that are 2–3 orders of magnitudes faster than typical ensemble methods and allowing it to be used for tasks where training or evaluating multiple models would be infeasible. We apply LTAU towards estimating parametric uncertainty in atomistic force fields (LTAU-FF), demonstrating that it produces well-calibrated confidence intervals and predicts errors that correlate strongly with the true errors for data near the training domain. Furthermore, we show that the errors predicted by LTAU-FF can be used in practical applications for detecting out-of-domain data, tuning model performance, and predicting failure during simulations. We believe that LTAU will be a valuable tool for uncertainty quantification in atomistic force fields and is a promising method that should be further explored in other domains of machine learning.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS2004

A Study of the Response of Deep Tropical Clouds to Mesoscale Processes: Sensitivities to Microphysics, Radiation, and Surface Fluxes - Part 2

The Goddard Cumulus Ensemble (GCE) model is used to examine the sensitivities of surface fluxes, explicit radiation, and ice microphysical processes on multi-day simulations of deep tropical convection over the Tropical Ocean Global Atmosphere Coupled Ocean-Atmosphere Response Experiment (TOGA COARE). The simulations incorporate large-scale advective temperature and moisture forcing, as well as large-scale momentum, that are updated every time step on a periodic lateral boundary grid. This study shows that when surface fluxes are eliminated, the mean atmosphere is much cooler and drier, convection and CAPE are much weaker, precipitation is less, and cloud coverage in stratiform regions much greater. Surface fluxes using the TOGA COARE flux algorithm are weaker than with the aerodynamic formulation, but closer to the observed fluxes. In addition, similar trends noted above for the case without surface fluxes are produced for the TOGA flux case, albeit to a much lesser extent. The elimination of explicit shortwave and longwave radiation is found to have only minimal effects on the mean thermodynamics, convection, and precipitation. However explicit radiation does have a significant impact on cloud temperatures and structure above 200 mb and on the overall mean vertical circulation. The removal of ice processes produces major changes in the structure of the cloud. Much of the liquid water is transported aloft and into anvils above the melting layer (600 mb), leaving narrow, but intense bands of rainfall in convective regions. The elimination of melting processes leads to greater hydrometeor mass below the melting layer, and produces a much warmer and moister boundary layer, leading to a greater mean CAPE. Finally, the elimination of the graupel species has only a small impact on mean total precipitation, thermodynamics, and dynamics of the simulation, but does produce much greater snow mass just above the melting layer. Some of these results differ from previous CRM studies of tropical systems, which is likely due to the type of simulated system, total time integration, and model setup.

Johnson, Daniel↗