Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Distributed training”

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 523 records · Page 29
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Information-entropy-driven generation of material-agnostic datasets for machine-learning interatomic potentials

In contrast to their empirical counterparts, machine-learning interatomic potentials (MLIAPs) promise to deliver near-quantum accuracy over broad regions of configuration space. However, due to their generic functional forms and extreme flexibility, they can catastrophically fail to capture the properties of novel, out-of-sample configurations, making the quality of the training set a determining factor, especially when investigating materials under extreme conditions. We propose a novel automated dataset generation method based on the maximization of the information entropy of the feature distribution, aiming at an extremely broad coverage of the configuration space in a way that is agnostic to the properties of specific target materials. The ability of the dataset to capture unique material properties is demonstrated on a range of unary materials, including elements with the FCC (Al), BCC (W), HCP (Be, Re and Os), graphite (C), and trigonal (Sb, Te) ground states. MLIAPs trained to this dataset are shown to be accurate over a range of application-relevant metrics, as well as extremely robust over very broad swaths of configurations space, even without dataset fine-tuning or hyper-parameter optimization, making the approach extremely attractive to rapidly and autonomously develop general-purpose MLIAPs suitable for simulations in extreme conditions.

36 MATERIALS SCIENCE↗
DOE OSTI2022

Post-Disaster Microgrid Formation for Enhanced Distribution System Resilience

This paper proposes a deep reinforcement learning (DRL) based approach for post-disaster critical load restoration in active distribution systems to form microgrids through network reconfiguration to minimize critical load curtailments. Distribution networks are represented as graph networks, and optimal network configurations with microgrids are obtained by searching for the optimal spanning forest. The constraints to the research question being explored are the radial topology and power balance. Unlike existing analytical and population-based approaches, which necessitate the repetition of entire analyses and computation for each outage scenario to find the optimal spanning forest, the proposed approach, once properly trained, can quickly determine the optimal, or near-optimal, spanning forest even when outage scenarios change. When multiple lines fail in the system, the proposed approach forms microgrids with distributed energy resources in active distribution systems to reduce critical load curtailment. The proposed DRL-based model learns the action-value function using the REINFORCE algorithm, which is a model-free reinforcement learning technique based on stochastic policy gradients. A case study was conducted on a 33-node distribution test system, demonstrating the effectiveness of the proposed approach for post-disaster critical load restoration.

active distribution systems↗
DOE OSTI2025

Modeling the Behavior of Complex Aqueous Electrolytes Using Machine Learning Interatomic Potentials: The Case of Sodium Sulfate

Understanding the structure and thermodynamics of solvated ions is essential for advancing applications in electrochemistry, water treatment, and energy storage. While ab initio molecular dynamics methods are highly accurate, they are limited by short accessible time and length scales whereas classical force fields struggle with accuracy. Herein, we explore the structure and thermodynamics of complex monovalent-divalent ion pairs using Na 2 SO 4 (aq) as a case study by applying a machine learning interatomic potential (MLIP) trained on density functional theory (DFT) data. Our MLIP-based approach reproduces key bulk properties such as density and radial distribution functions of water. We provide the hydration structure of the sodium and sulfate ions in the 0.1–2 M concentration range and the one-dimensional and two-dimensional potentials of mean force for the sodium–sulfate ion pairing at the low concentration limit (0.1 M), which are inaccessible to DFT. At low concentrations, the sulfate ion is strongly solvated, leading to the stabilization of solvent-separated ion pairs over contact ion pairs. Minimum energy pathway analysis revealed that coordinating two sodium ions with a sulfate ion is a multistep process whereby the sodium ions coordinate to the sulfate ion sequentially. Finally, we demonstrate that MLIPs allow the study of solvated ions beyond simple monovalent pairs with DFT-level accuracy in their low concentration limit (0.1 M) via statistically converged properties from ns-long simulations.

anions↗
DOE OSTI2025

What Makes Au Nanospheres Superior to Octahedral and Cubic Counterparts for the Deposition of a Pt Monolayer Shell?

This study demonstrates that Au nanospheres are advantageous over their octahedral and cubic counterparts as seeds in the synthesis of Au@Pt core−shell nanocrystals with a monolayer shell. In combination with experimental characterization, we show through training a machine-learned interatomic potential that the Au nanospheres exhibit a large fraction of lowcoordination atoms which are uniformly distributed over the surface. The corresponding high-index facets, including {211}, {311}, {331}, {210}, and {310}, on a spherical seed promote nucleation while greatly shortening the diffusion distance for adatoms. In addition, the high-index facets are instrumental in retaining the deposited Pt atoms on the outermost surface by retarding their inter-diffusional exchange with the underlying Au atoms. By switching from a monolayer made of pure Pt to those made of Pt−Au alloys, we can optimize both the activity and selectivity of the nanocrystals toward the two-electron oxygen reduction reaction for the electrochemical synthesis of H 2 O 2 . This method should be extendible to the fabrication of other core−shell nanocatalysts with desired monolayer shells for various catalytic reactions.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2022

Uncertainty propagation in pore water chemical composition calculation using surrogate models

Performance assessment in deep geological nuclear waste repository systems necessitates an extended knowledge of the pore water chemical conditions prevailing in host-rock formations. In the last two decades, important progress has been made in the experimental characterization and thermodynamic modeling of pore water speciation, but the influence of experimental artifacts and uncertainties of thermodynamic input parameters are seldom evaluated. In this respect, we conducted an uncertainty propagation study in a reference geochemical model describing the pore water chemistry of the Callovian-Oxfordian clay formation. Nineteen model input parameters were perturbed, including those associated to experimental characterization (leached anions, exchanged cations, cation exchange selectivity coefficients) and those associated to generic thermodynamic databases (solubilities). A set of 13 quantities of interest were studied by the use of polynomial chaos expansions built non-intrusively with a least-squares forward stepwise regression approach. Training and validation sets of simulations were carried out using the geochemical speciation code PHREEQC. The statistical results explored the marginal distribution of each quantity of interest, their bivariate correlations as well as their global sensitivity indices. The influence of the assumed distributions for input parameters uncertainties was evaluated by considering two parametric domain sizes.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2022

A Conditional Autoencoder for Galaxy Photometric Parameter Estimation

Astronomical photometric surveys routinely image billions of galaxies, and traditionally infer the parameters of a parametric model for each galaxy. This approach has served us well, but the computational expense of deriving a full posterior probability distribution function is a challenge for increasingly ambitious surveys. In this paper, we use deep learning methods to characterize galaxy images, training a conditional autoencoder on mock data. The autoencoder can reconstruct and denoise galaxy images via a latent space engineered to include semantically meaningful parameters, such as brightness, location, size, and shape. Our model recovers galaxy fluxes and shapes on mock data with a lower variance than the Hyper Suprime-Cam photometry pipeline, and returns reasonable answers even for inputs outside the range of its training data. When applied to data in the training range, the regression errors on all extracted parameters are nearly unbiased with a variance near the Cramr-Rao bound.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2020

A deep neural network to search for new long-lived particles decaying to jets

A tagging algorithm to identify jets that are significantly displaced from the proton-proton (pp) collision region in the CMS detector at the LHC is presented. Displaced jets can arise from the decays of long-lived particles (LLPs), which are predicted by several theoretical extensions of the standard model. The tagger is a multiclass classifier based on a deep neural network, which is parameterised according to the proper decay length $\mathrm{c}\tau_0$ of the LLP. A novel scheme is defined to reliably label jets from LLP decays for supervised learning. Samples of pp collision data, recorded by the CMS detector at a centre-of-mass energy of 13 TeV, and simulated events are used to train the neural network. Domain adaptation by backward propagation is performed to improve the simulation modelling of the jet class probability distributions observed in pp collision data. The potential performance of the tagger is demonstrated with a search for long-lived gluinos, a manifestation of split supersymmetric models. The tagger provides a rejection factor of 10 000 for jets from standard model processes, while maintaining an LLP jet tagging efficiency of 30-80% for gluinos with 1 mm $\leq$ $c\tau_0$ $\leq$ 10 m. The expected coverage of the parameter space for split supersymmetry is presented.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2024

MLUQ (Uncertainty quantification for ML closure models) [SWR-24-36]

Data-based closure models are increasingly being used to replace physic-based closure models because of their flexibility and the growing availability of data. However, closure models are subject to uncertainty because of lack of data in parts of the input space (epistemic uncertainty) or because of noise in the data (aleatoric uncertainty). This software contains a toolbox for training bayesian neural nets that can estimate both uncertainties. A specific treatment is provided to ensure accuracy outside of the data distribution. A set of tools are provided to reduce the dimensionality of the uncertain parameter space, thereby enabling fast uncertainty propagation.

Hassanaly, Malik↗
DOE OSTI2024

Fostering Geothermal Machine Learning Success: Elevating Big Data Accessibility and Automated Data Standardization in the Geothermal Data Repository: Preprint

The Department of Energy's (DOE) Geothermal Data Repository (GDR) has implemented improvements to both its data lakes and its data standards and automated data pipelines. The GDR data lakes have reduced storage and compute-related barriers to using large geothermal datasets, enabling these large datasets to be accessed by anyone with a modern computer and internet access. More recently, the GDR has been working to further reduce barriers through streamlining the data intake process, educating users on the process and requirements, and aiding users in accessing data from the data lakes. These improvements have augmented the quantity of datasets the GDR is able to accept into its data lakes and have enabled users who are new to cloud tools to access these datasets more easily, overall increasing the accessibility of big geothermal data for use in machine learning and other projects. In addition, the GDR now has built-in data standards and pipelines for drilling data, geospatial data, and distributed acoustic sensing (DAS) data. These standardization efforts aim to enhance the real-world applicability of geothermal machine learning outcomes by improving the quality of training data. Specifically, through standardizing high-value datasets, the GDR is reducing project-specific data curation requirements, thus allowing more time for actual research. By automating this process, the burden of standardization is lifted from the user, ultimately increasing the availability of standardized data.

accessibility↗
DOE OSTI2024

Evidential Deep Learning: Enhancing Predictive Uncertainty Estimation for Earth System Science Applications

Abstract Robust quantification of predictive uncertainty is a critical addition needed for machine learning applied to weather and climate problems to improve the understanding of what is driving prediction sensitivity. Ensembles of machine learning models provide predictive uncertainty estimates in a conceptually simple way but require multiple models for training and prediction, increasing computational cost and latency. Parametric deep learning can estimate uncertainty with one model by predicting the parameters of a probability distribution but does not account for epistemic uncertainty. Evidential deep learning, a technique that extends parametric deep learning to higher-order distributions, can account for both aleatoric and epistemic uncertainties with one model. This study compares the uncertainty derived from evidential neural networks to that obtained from ensembles. Through applications of the classification of winter precipitation type and regression of surface-layer fluxes, we show evidential deep learning models attaining predictive accuracy rivaling standard methods while robustly quantifying both sources of uncertainty. We evaluate the uncertainty in terms of how well the predictions are calibrated and how well the uncertainty correlates with prediction error. Analyses of uncertainty in the context of the inputs reveal sensitivities to underlying meteorological processes, facilitating interpretation of the models. The conceptual simplicity, interpretability, and computational efficiency of evidential neural networks make them highly extensible, offering a promising approach for reliable and practical uncertainty quantification in Earth system science modeling. To encourage broader adoption of evidential deep learning, we have developed a new Python package, Machine Integration and Learning for Earth Systems (MILES) group Generalized Uncertainty for Earth System Science (GUESS) (MILES-GUESS) ( https://github.com/ai2es/miles-guess ), that enables users to train and evaluate both evidential and ensemble deep learning. Significance Statement This study demonstrates a new technique, evidential deep learning, for robust and computationally efficient uncertainty quantification in modeling the Earth system. The method integrates probabilistic principles into deep neural networks, enabling the estimation of both aleatoric uncertainty from noisy data and epistemic uncertainty from model limitations using a single model. Our analyses reveal how decomposing these uncertainties provides valuable insights into reliability, accuracy, and model shortcomings. We show that the approach can rival standard methods in classification and regression tasks within atmospheric science while offering practical advantages such as computational efficiency. With further advances, evidential networks have the potential to enhance risk assessment and decision-making across meteorology by improving uncertainty quantification, a longstanding challenge. This work establishes a strong foundation and motivation for the broader adoption of evidential learning, where properly quantifying uncertainties is critical yet lacking.

Schreck, John S.↗
DOE OSTI2024

Machine learning snow depth predictions at sites in Alaska, Norway, Siberia, Colorado and New Mexico

Temporally continuous snow depth estimates are vital for understanding changing snow patterns in the Arctic and impacts on permafrost. We trained random forest machine learning models to predict snow depth from temperature data recorded at or just below the ground surface. Training data was collected at the Teller 27 Watershed and Kougarok 64 Hillslope during the 2021 - 2022 water year on the Seward Peninsula, Alaska using distributed temperature profiling (DTP) systems. We then applied this model to other sites where ground surface or shallow soil temperature data was available for at least one water year (see Related Datasets). Many of these temperature measurements were collocated with snow depth observations. Ground surface temperature (i.e. snow-ground interface temperature) is easy to measure using small, cheap and easy-to-deploy temperature sensors such as iButtons and TinyTags, and such measurements have previously been used to calculate a variety of snow metrics (e.g. snow onset date). However, this is the first study to estimate snow depth directly from ground surface temperature data. The present dataset contains one *.csv file which includes machine learning snow depth predictions at sites in Alaska, Norway, Siberia, Colorado, and New Mexico and one *.kml file including the locations of sites with snow depth predictions. No training data predictions are included in the *.csv file. The Next-Generation Ecosystem Experiments: Arctic (NGEE Arctic), was a research effort to reduce uncertainty in Earth System Models by developing a predictive understanding of carbon-rich Arctic ecosystems and feedbacks to climate. NGEE Arctic was supported by the Department of Energy’s Office of Biological and Environmental Research. The NGEE Arctic project had two field research sites: 1) located within the Arctic polygonal tundra coastal region on the Barrow Environmental Observatory (BEO) and the North Slope near Utqiagvik (Barrow), Alaska and 2) multiple areas on the discontinuous permafrost region of the Seward Peninsula north of Nome, Alaska. Through observations, experiments, and synthesis with existing datasets, NGEE Arctic provided an enhanced knowledge base for multi-scale modeling and contributed to improved process representation at global pan-Arctic scales within the Department of Energy’s Earth system Model (the Energy Exascale Earth System Model, or E3SM), and specifically within the E3SM Land Model component (ELM).

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2023

Machine-Learning Architecture for Ultrasonic Thermometry

Temperature distribution in solids can be inverted from the speed of sound (SOS) measurements, as has been shown feasible by timing the propagation of the excitation pulse and the train of echoes in ultrasonically segmented waveguides (WGs) and metal components. However, complicated geometries and closely-space echogenic features (EFs) create complex waveforms, from which the segmental time of flights (TOFs) are impossible to estimate using traditional methods. This work describes a machine learning architecture shown to extract temperature information from complex ultrasonic waveforms without explicit measurements of segmental TOFs. We accomplish this by using an autoencoder neural network (NN) to map ultrasonic waveforms into a low-dimensional latent space. A second NN then maps the latent space into unknown temperature distribution along the WG. The proposed architecture was tested in simulations and experimentally. The autoencoder accurately reconstructs the waveforms from their latent representation, several orders of magnitude lower in dimensionality. The obtained latent space was successfully mapped into the temperature of the propagation path.

John, Mason↗
DOE OSTI2020

Quantifying the generalization error in deep learning in terms of data distribution and neural network smoothness

We report the accuracy of deep learning, i.e., deep neural networks, can be characterized by dividing the total error into three main types: approximation error, optimization error, and generalization error. Whereas there are some satisfactory answers to the problems of approximation and optimization, much less is known about the theory of generalization. Most existing theoretical works for generalization fail to explain the performance of neural networks in practice. To derive a meaningful bound, we study the generalization error of neural networks for classification problems in terms of data distribution and neural network smoothness. We introduce the cover complexity (CC) to measure the difficulty of learning a data set and the inverse of the modulus of continuity to quantify neural network smoothness. A quantitative bound for expected accuracy/error is derived by considering both the CC and neural network smoothness. Although most of the analysis is general and not specific to neural networks, we validate our theoretical assumptions and results numerically for neural networks by several data sets of images. The numerical results confirm that the expected error of trained networks scaled with the square root of the number of classes has a linear relationship with respect to the CC. We also observe a clear consistency between test loss and neural network smoothness during the training process. In addition, we demonstrate empirically that the neural network smoothness decreases when the network size increases whereas the smoothness is insensitive to training dataset size.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Revealing the Milky Way’s most recent major merger with a Gaia EDR3 catalogue of machine-learned line-of-sight velocities

Machine learning can play a powerful role in inferring missing line-of-sight velocities from astrometry in surveys such as Gaia. In this paper, we apply a neural network to Gaia Early Data Release 3 (EDR3) and obtain line-of-sight velocities and associated uncertainties for ~92 million stars. The network, which takes as input a star’s parallax, angular coordinates, and proper motions, is trained and validated on ~6.4 million stars in Gaia with complete phase-space information. The network’s uncertainty on its velocity prediction is a key aspect of its design; by properly convolving these uncertainties with the inferred velocities, we obtain accurate stellar kinematic distributions. As a first science application, we use the new network-completed catalogue to identify candidate stars that belong to the Milky Way’s most recent major merger, Gaia-Sausage-Enceladus (GSE). We present the kinematic, energy, angular momentum, and spatial distributions of the ~450 000 GSE candidates in this sample, and also study the chemical abundances of those with cross matches to GALAH and APOGEE. Furthermore, the network’s predictive power will only continue to improve with future Gaia data releases as the training set of stars with complete phase-space information grows. This work provides a first demonstration of how to use machine learning to exploit high-dimensional correlations on data to infer line-of-sight velocities, and offers a template for how to train, validate, and apply such a neural network when complete observational data is not available.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2023

Deep Learning Parameterization of Vertical Wind Velocity Variability via Constrained Adversarial Training

Atmospheric models with typical resolution in the tenths of kilometers cannot resolve the dynamics of air parcel ascent, which varies on scales ranging from tens to hundreds of meters. Small-scale wind fluctuations are thus characterized by a subgrid distribution of vertical wind velocity W with standard deviation σ W . The parameterization of σ W is fundamental to the representation of aerosol–cloud interactions, yet it is poorly constrained. Using a novel deep learning technique, this work develops a new parameterization for σ W merging data from global storm-resolving model simulations, high-frequency retrievals of W , and climate reanalysis products. The parameterization reproduces the observed statistics of σ W and leverages learned physical relations from the model simulations to guide extrapolation beyond the observed domain. Incorporating observational data during the training phase was found to be critical for its performance. The parameterization can be applied online within large-scale atmospheric models, or offline using output from weather forecasting and reanalysis products.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2022

Hybrid-RL-MPC4CLR (Hybird-Reinforcement-Learning-Model-Predictive-Control-for-Reserve-Policy-Assisted-Critical-Load-Restoration-in-Distribution-Grids)

Hybrid-RL-MPC4CLR was developed as a hybrid controller for active distribution grid critical load restoration, combining deep reinforcement learning (RL) and model predictive control (MPC) aiming at maximizing total restored load following an extreme event. The RL determines a policy for quantifying operating reserve requirements, thereby hedging against uncertainty, while the MPC models grid operations incorporating the RL policy actions (i.e., reserve requirements), renewable (wind and solar) power predictions, and load demand forecasts. The developers formulated the reserve requirement determination problem as a sequential decision-making problem based on the Markov Decision Process (MDP) and design an RL learning environment based on the OpenAI Gym framework and MPC simulation. The RL agent reward and MPC objective function aim to maximize and monotonically increase total restored load and minimize load shedding and renewable power curtailment. The software is developed using various software packages in Python. The MPC's optimal power flow (OPF) model is implemented using the Pyomo package, the RL simulation environment is implemented using the MPC simulation with various scenarios of renewable energy and load demand profiles and power outage beginning times, based on the OpenAI Gym framework. The RL agent training is performed using the RLlib Ray package. The RL algorithm is trained offline using historical forecasts of renewable generation and load demand profiles. Simulation analysis and performance tests are conducted using a modified IEEE 13-bus distribution test feeder containing wind turbine, photovoltaic, microturbine, and battery.

Eseye, Abinet Tesfaye↗
DOE OSTI2021

Scenario adaptive disruption prediction study for next generation burning-plasma tokamaks

Next generation High Performance (HP) tokamaks risk damage from unmitigated disruptions at high current and power. Achieving reliable disruption prediction for a device's HP operation based on its Low Performance (LP) data is a key to its success. In this letter, through explorative data analysis and dedicated numerical experiments on multiple existing tokamaks, we demonstrate how the operational regimes of tokamaks can affect the power of a trained disruption predictor. First, our results suggest data-driven disruption predictors trained on abundant LP discharges work poorly on the HP regime of the same tokamak, which is a consequence of the distinct distributions of the tightly correlated signals related to disruptions in these two regimes. Second, we find that matching operational parameters among tokamaks strongly improves cross-machine accuracy which implies our model learns from the underlying scalings of dimensionless physics parameters like q 95 , β p and confirms the importance of these parameters in disruption physics and cross machine domain matching from the data-driven perspective. Finally, our results show in the absence of HP data from the target devices, the best predictivity of the HP regime for the target machine can be achieved by combining LP data from the target with HP data from other machines. Furthermore, these results provide a possible disruption predictor development strategy for next generation tokamaks, such as ITER and SPARC, and highlight the importance of developing baseline scenario discharges of future tokamaks on existing machines to collect more relevant disruptive data.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2023

Uncertainty Quantification of Capacitor Switching Transient Location using Machine Learning

Identification of capacitor switching transient location provides valuable insight into the state of the associated equipment. Machine learning (ML) models, and convolutional neural networks (CNNs) in particular, have demonstrated remarkable performance in signal location. However, ML models are data driven whose predictions are affected by noise in data and may also suffer from large extrapolation errors when applied to new conditions. Uncertainty quantification (UQ) is necessary to ensure model trustworthiness and avoid overconfident predictions in extrapolation. Here, in this work, we propose a novel UQ method, called PI3NN, to quantify prediction uncertainty of ML models and integrate the method with CNNs for transient source location. PI3NN calculates Prediction Intervals by training 3 Neural Networks and uses root-finding methods to determine the interval precisely. Additionally, PI3NN can identify out-of-distribution (OOD) data in a nonstationary condition to avoid overconfident prediction. Results indicate that with PI3NN, transient signals are not only correctly identified, but when said signals are subject to corruptions characteristic of an actual power monitoring system (e.g. non-ideal sensors), the model recognizes when it is uncertain about its predictions, effectively letting the user know when to accept or discard the results.

24 POWER TRANSMISSION AND DISTRIBUTION↗