Search NASA⌕ Search

SEARCH · Search NASA

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 1,045 records · Page 58

Electrical Load Forecasting Over Multihop Smart Metering Networks With Federated Learning

Electric load forecasting is essential for power management and stability in smart grids. This is mainly achieved via advanced metering infrastructure, where smart meters (SMs) record household energy data. Traditional machine learning (ML) methods are often employed for load forecasting, but require data sharing, which raises data privacy concerns. Federated learning (FL) can address this issue by running distributed ML models at local SMs without data exchange. However, current FL-based approaches struggle to achieve efficient load forecasting due to imbalanced data distribution across heterogeneous SMs. Here, this article presents a novel personalized FL (PFL) method for high-quality load forecasting in metering networks. A meta-learning-based strategy is developed to address data heterogeneity at local SMs in the collaborative training of local load forecasting models. Moreover, to minimize the load forecasting delays in our PFL model, we study a new latency optimization problem based on optimal resource allocation at SMs. A theoretical convergence analysis is also conducted to provide insights into FL design for federated load forecasting. Extensive simulations from real-world datasets show that our method outperforms existing approaches regarding better load forecasting and reduced operational latency costs.

Rahman, Ratun [Univ. of Alabama, Huntsville, AL (U↗

Diverse Super-Resolution (diversity_SR) [SWR-21-60]

Deep learning tools for enhancing the spatial resolution of wind data. The software is developed in Python using the TensorFlow deep learning package. Models for diversity super-resolution is provided. Included in the package are pretrained models with example code/data to perform the super-resolution as well as tools of training models for different enhancement- or data-types. The super-resolution is an inherently ill-conditioned problem, with multiple high-resolution fields plausibly mapping to the same coarse field. Considitional GANs provide a framework for generating a distribution of high-resolution realizations from a given low-resolution input. Stochastic estimation is used to inform the network of the expected degree and location of sub-grid diversity. The package includes a pretrained network to generate distributions of 10x-enhanced fields of wind data.

Glaws, Andrew↗

A Roadmap for NEAMS Capability Transfer

The vision of the Nuclear Energy Advanced Modeling and Simulation (NEAMS) program is to bring truly predictive modeling and simulation (M&S) capabilities to the nuclear engineering community in order to enable a new approach to the design and analysis of nuclear energy systems. From its inception, the NEAMS program has always envisioned a broad user base for its software and scientific products, including researchers within the DOE complex, nuclear industry technology developers and vendors, and operators. However activities to date have focused almost exclusively on interactions with NEAMS sponsors, who are also near-term users of NEAMS technologies. The task of the NEAMS Capability Transfer (CT) program element for FY2011 is to develop a comprehensive plan to support the program's needs for user outreach and technology transfer. In order to obtain community input to this plan, a 'NEAMS Capability Transfer Roadmapping Workshop' was held 4-5 April 2011 in Chattanooga, TN, and is summarized in this report. The 30 workshop participants represented the NEAMS program, the DOE and industrial user communities, and several outside programs. The workshop included a series of presentations providing an overview of the NEAMS program and presentations on the user outreach and technology transfer experiences of (1) The Advanced Simulation and Computing (ASC) program, (2) The Standardized Computer Analysis for Licensing Evaluation (SCALE) project, and (3) The Consortium for Advanced Simulation of Light Water Reactors (CASL), followed by discussion sessions. Based on the workshop and other discussions throughout the year, we make a number of recommendations of key areas for the NEAMS program to develop the user outreach and technology transfer activities: (1) Engage not only DOE, but also industrial users sooner and more often; (2) Engage with the Nuclear Regulatory Commission to facilitate their understanding and acceptance of NEAMS approach to predictive M&S; (3) Place requirements gathering from prospective users on a more formal footing, updating requirements on a regular basis and incorporate them into planning and execution of the project in a traceable fashion; (4) Seek out the best available data for validation purposes, and work with experimental programs to design and carry out new experiments that satisfy the need for data suitable for validation of high-fidelity M&S codes; (5) Develop and implement program-wide plans and policies for export control, licensing, and distribution of NEAMS software products; (6) Establish a program of sponsored alpha testing by experienced users in order to obtain feedback on NEAMS codes; (7) Provide technical support for NEAMS software products; (8) Develop and deliver documentation, tutorial materials, and live training classes; and (9) Be prepared to support outside users who wish to contribute to the codes.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

Hybrid Storage Solution

With the rise of artificial intelligence and machine learning, data sets used to train models have become increasingly large. The availability, accessibility and integrity of large data sets has become important to the research conducted at Los Alamos National Laboratory. Ceph is a storage solution suitable for use with critical data because of its distributed nature and ability to keep multiple copies of a file in different locations. The amount of data means that bandwidth, latency, and cost are important factors and the reason most storage solutions are on-premises. However, there are distinct advantages to hosting services in the cloud, namely scalability and ease-of-use. In this paper, we explore the possibility of provisioning a hybrid Ceph cluster that leverages the benefits of both cloud architectures and on-premise performance.

97 MATHEMATICS AND COMPUTING↗

Chapter 7: Learning Stable Local Volt/Var Controllers in Distribution Grids

This chapter describes a framework to synthesize provably stable local Volt/Var controllers for distributed energy resources (DERs) in power distribution grids (DGs). The goal is to control the reactive power injections of DERs to improve the system performance as quantified by a generic optimal reactive power flow (ORPF) problem. To achieve this, we jointly design for each DER the control function, which prescribes the reactive power update rule, and the equilibrium function, which approximates the ORPF solutions from local measurements of voltages and powers. We provide conditions on the equilibrium functions and the control parameters ensuring the stability of the closed-loop system. In particular, we discuss the trade-offs between each set of conditions accounting for practical considerations, like fully exploiting the DERs' generation capabilities and reducing the optimality gap. These conditions are then translated into learning constraints on the neural networks' parameters that are enforced in the training phase. We validate our framework with numerical simulations on the IEEE 37-bus network and through a comparison with an optimized version of standard piece wise linear control rules.

closed-loop asymptotic stability↗

Scalable statistical inference of photometric redshift via data subsampling

Handling big data has largely been a major bottleneck in traditional statistical models. Consequently, when accurate point prediction is the primary target, machine learning models are often preferred over their statistical counterparts for bigger problems. But full probabilistic statistical models often outperform other models in quantifying uncertainties associated with model predictions. We develop a data-driven statistical modeling framework that combines the uncertainties from an ensemble of statistical models learned on smaller subsets of data carefully chosen to account for imbalances in the input space. We demonstrate this method on a photometric redshift estimation problem in cosmology, which seeks to infer a distribution of the redshift—the stretching effect in observing the light of far-away galaxies—given multivariate color information observed for an object in the sky. Our proposed method performs balanced partitioning, graph-based data subsampling across the partitions, and training of an ensemble of Gaussian process models.

data subsampling↗

Reducing systematic bias in machine learning applications to J/ψ signal extraction in high-energy nuclear physics

Machine learning techniques are increasingly used in high-energy nuclear physics because they can exploit multivariate correlations more efficiently than conventional cut-based analyses. A central challenge is the construction of training samples that faithfully reproduce the detector response observed in data. Signal samples are usually derived from detector simulations; therefore, mismatches between simulation and data can degrade classifier performance and introduce systematic biases. This work presents two practical correction procedures, namely cumulative distribution function (CDF) mapping and a shift-and-scale transformation, to align simulated signal features with those measured in data. Their performance is demonstrated with $J$/$\psi$ yield measurements in $\sqrt{s_{nn}}$ = 200 GeV Ru+Ru and Zr+Zr collisions recorded by STAR. A set of self-consistency tests shows that these procedures substantially suppress the systematic bias associated with data-simulation discrepancies in machine-learning-based signal extraction.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

PUFFIn – A user friendly fast interface for calculating and visualizing the dose distribution in materials

This article describes a new graphical user interface that uses the PENELOPE Monte Carlo code to calculate dose distributions in materials. It is named PUFFIn, for the Penelope User-Friendly Fast Interface and was developed as an educational and scoping analysis tool for non-experts in radiation modeling. PUFFIn enables the user to visualize and compare the dose distributions in objects (e.g., sterilized healthcare products) irradiated with cobalt-60 gamma-rays, electron beam (E-beam) or X-rays. From such comparisons, the user can determine the most efficient product and/or packaging designs for any given radiation field – whether for conceptual or existing products and packaging. PUFFIn is distributed in a complete, self-contained package of software, including the PENELOPE radiation transport code, a standard graphics package, and a set of simple exercises. The package is available to any user at no cost and requires a minimal amount of training compared to other similar software. PUFFIn's capabilities are described, as well as validation measurements performed at Texas A&M University E-beam facility and the Aerial E-beam Facility in France.

97 MATHEMATICS AND COMPUTING↗

Transferable Atomic Multipole Machine Learning Models for Small Organic Molecules

Accurate representation of the molecular electrostatic potential, which is often expanded in distributed multipole moments, is crucial for an efficient evaluation of intermolecular interactions. In this paper we introduce a machine learning model for multipole coefficients of atom types H, C, O, N, S, F, and Cl in any molecular conformation. The model is trained on quantum-chemical results for atoms in varying chemical environments drawn from thousands of organic molecules. Multipoles in systems with neutral, cationic, and anionic molecular charge states are treated with individual models. The models’ predictive accuracy and applicability are illustrated by evaluating intermolecular interaction energies of nearly 1,000 dimers and the cohesive energy of the benzene crystal.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Type Ia supernova Hubble residuals and host-galaxy properties

Kim et al. introduced a new methodology for determining peak-brightness absolute magnitudes of type Ia supernovae from multi-band light curves. We examine the relation between their parameterization of light curves and Hubble residuals, based on photometry synthesized from the Nearby Supernova Factory spectrophotometric time series, with global host-galaxy properties. The K13 Hubble residual step with host mass is 0.013 ± 0.031 mag for a supernova subsample with data coverage corresponding to the K13 training; at <<1σ, the step is not significant and lower than previous measurements. Relaxing the data coverage requirement of the Hubble residual step with the host mass is 0.045 ± 0.026 mag for the larger sample; a calculation using the modes of the distributions, less sensitive to outliers, yields a step of 0.019 mag. The analysis of this article uses K13 inferred luminosities, as distinguished from previous works that use magnitude corrections as a function of SALT2 color and stretch parameters: steps at >2σ significance are found in SALT2 Hubble residuals in samples split by the values of their K13 x(1) and x(2) light-curve parameters. x(1) affects the light-curve width and color around peak (similar to the Δm {sub 15} and stretch parameters), and x(2) affects colors, the near-UV light-curve width, and the light-curve decline 20-30 days after peak brightness. The novel light-curve analysis, increased parameter set, and magnitude corrections of K13 may be capturing features of SN Ia diversity arising from progenitor stellar evolution.

79 ASTRONOMY AND ASTROPHYSICS↗

Data-Driven Method for Groundwater-Level Mapping and Monitoring-Well Network Optimization at Hanford

This report summarizes the initial results and outcomes of a physics-informed, data-driven groundwater level (GWL) mapping capability for the Hanford Site. GWL mapping at Hanford is typically conducted annually and requires a significant amount of computational and expert resources, and it does not allow assessment of the informational value of specific monitoring wells. The proposed method produces spatially and temporally resolved fields consistent with sparse, irregularly sampled, and nonuniformly distributed well measurements. Implemented successfully, this capability will allow rapid mapping of groundwater levels and provide an opportunity to optimize monitoring activities (both location and sampling frequency) based on data information value evaluation. The approach integrates a diffusion-based generative model – trained on MODFLOW simulation data from the Plateau-to-River (P2R) model – with score-based data assimilation (SDA), allowing observation-conditioned mapping without retraining for each monitoring-network layout.

54 ENVIRONMENTAL SCIENCES↗

Embedding Neural Thermal Scattering (NeTS) Modules in SERPENT for Higher Fidelity Advanced Reactor Analysis

When a neutron born in fission thermalizes to the order of $k$ $B$ $T$, it’s de-Broglie wavelength and energy approach the order of inter-atomic spacing and elementary lattice oscillations, respectively. $S$($a,β,t$) or the scattering law, uuantify these temperature-dependent crystallographic contributions to total cross section (or reaction rate). In a Monte Carlo analysis, cumulative distribution functions (CDFs) of $S$($a,β,t$) are loaded to memory from “A Compact ENDF” (ACE) files for stochastically selecting thermal scattered neutron trajectories. In this work, novel neural thermal scattering (NeTS) modules for $S$($a,β,t$) CDFs are designed, trained, serialized and embedded within SERPENT using Python’s limited C-API for on-the-fly deployment of crystalline graphite $S$($a,β,t$) sampling. Torchscript tracing and Numba just-in-time (JIT) compilation streamline neural inference on NVIDIA GPUs with CUDA libraries. Demonstrations of bare sphere thermalization of fast and thermal sources show excellent agreement between embedded NeTS in SERPENT and MCNP. With an explicit model of the reactor, NeTS can predict on-the-fly changes in TREAT neutron spectra as a function of local temperature, which can serve to improve transient and accident predictions in a multiphysics analysis framework. This framework can be further extended to account on-the-fly for changes in local graphitic microstructure to scattering cross sections, and outlines a novel coupling of modern machine learning with state-of-the-art reactor physics methods.

97 MATHEMATICS AND COMPUTING↗

High-speed impact of micron-sized diesel drop trains—Splashing dynamics, secondary droplet formation, and effects of pre-existing film thickness

This work investigates surface impingement of monodispersed diesel drop trains using computational simulations. The three-dimensional simulations include high-speed impact of micrometer-sized fuel drops onto initially dry and wetted stainless steel substrates. The drop size and impact velocity are representative of fuel injection conditions in internal combustion engines (ICEs). The drop trains serve as a simplified representation of fuel spray. To accurately capture the film that naturally develops on initially dry substrates, a dynamic diesel-stainless steel contact angle model was developed using experiments of single drop impact under ICE representative temperature. Simulations are presented for a highly splashing case and the effects of a pre-existing film on splashing dynamics were investigated, including the temporal evolution of splashed mass and film thickness. It was concluded that for thin films, the effect of pre-existing film thickness is less significant than in single drop impingement. Secondary droplet characterization was performed on simulation results, leading to instantaneous and time-averaged distributions of secondary droplet size, velocity magnitude, and trajectory angle. It was found that for each drop impingement, approximately 58% of the splashed mass is from the impinging drop itself, while the remainder of the splashed mass is composed of film liquid. From a high resolution case, details of secondary droplet formation are observed and three distinct phases of secondary droplet formation are identified. The detailed analysis of drop train impingement under engine-relevant conditions serves as a first step toward a robust understanding of fuel impingement and the development of cleaner and more efficient ICEs.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Out of distribution evaluation for neural image compression

Official code for the NeurIPS 2023 paper "Neural Image Compression: Generalization, Robustness, and Spectral Biases". This code can be used to: - Computing spectral distortion errors of images compressed with traditional codes or neural image compression models (as proposed in the aformentioned paper) - Visualize power spectral densities and fourier heatmaps (as proposed in the aformentioned paper) - Train and test a variety of neural image compression models

Lieberman, KelseyA↗

Post-irradiation Examination and Fission Product Inventory Analysis of AGR-1 Irradiation Capsules

The AGR-1 experiment was the first in a series of Advanced Gas Reactor (AGR) experiments designed to test TRISO fuel under High Temperature Gas Reactor irradiation conditions. This experiment was irradiated in the Advanced Test Reactor (ATR) at Idaho National Laboratory (INL) and is currently undergoing post-irradiation examination (PIE) at INL’s Materials and Fuels Complex (MFC). The inventory and distribution of fission products, especially Ag-110m, was assessed and analyzed for all the components of the AGR-1 capsules. This data should help inform the study of fission product migration in coated particle fuel. Gamma spectrometry was used to measure the activity of various different fission products in the different components of the AGR-1 test train. Each capsule contained: 12 fuel compacts, a graphite holder that kept the fuel compacts in place, graphite spacers that were above and below the graphite holders and fuel compacts, gas lines through which a helium neon gas mixture flowed in and out of each capsule, and the stainless steel shell that contained the experiment. Gamma spectrometry results and the experimental techniques used to capture these results will be presented for all the capsule components. The components were assayed to determine the total activity of different fission products present in or on them. These totals are compared to the total expected activity of a particular fission product in the capsule based on predictions from physics simulation. Based on this metric, a significant fraction of the Ag-110m was detected outside the fuel compacts, but the amount varied highly between the 6 capsules. Very small fractions of Cs-137 (<2E-5), Cs-134 (<1e-5), and Eu-154 (<4e-4) were detected outside of the fuel compacts. Additionally, the distribution of select fission products in some of the components including the fuel compacts and the graphite holders were measured and will be discussed.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗

Prediction by Convolutional Neural Networks of CO 2 /N 2 Selectivity in Porous Carbons from N 2 Adsorption Isotherm at 77 K

Abstract Porous carbons are an important class of porous materials with many applications, including gas separation. An N 2 adsorption isotherm at 77 K is the most widely used approach to characterize porosity. Conventionally, textual properties such as surface area and pore volumes are derived from the N 2 adsorption isotherm at 77 K by fitting it to adsorption theory and then correlating it to gas separation performance (uptake and selectivity). Here the N 2 isotherm at 77 K was used directly as input (representing feature descriptors for the porosity) to train convolutional neural networks to predict gas separation performance (using CO 2 /N 2 as a test case) for porous carbons. The porosity space for porous carbons was explored for higher CO 2 /N 2 selectivity. Porous carbons with a bimodal pore‐size distribution of well‐separated mesopores (3–7 nm) and micropores (<2 nm) were found to be most promising. This work will be useful in guiding experimental research of porous carbons with the desired porosity for gas separation and other applications.

Wang, Song↗

Prediction by Convolutional Neural Networks of CO 2 /N 2 Selectivity in Porous Carbons from N 2 Adsorption Isotherm at 77 K

Abstract Porous carbons are an important class of porous materials with many applications, including gas separation. An N 2 adsorption isotherm at 77 K is the most widely used approach to characterize porosity. Conventionally, textual properties such as surface area and pore volumes are derived from the N 2 adsorption isotherm at 77 K by fitting it to adsorption theory and then correlating it to gas separation performance (uptake and selectivity). Here the N 2 isotherm at 77 K was used directly as input (representing feature descriptors for the porosity) to train convolutional neural networks to predict gas separation performance (using CO 2 /N 2 as a test case) for porous carbons. The porosity space for porous carbons was explored for higher CO 2 /N 2 selectivity. Porous carbons with a bimodal pore‐size distribution of well‐separated mesopores (3–7 nm) and micropores (<2 nm) were found to be most promising. This work will be useful in guiding experimental research of porous carbons with the desired porosity for gas separation and other applications.

Wang, Song↗

A robust synthetic data generation framework for machine learning in high-resolution transmission electron microscopy (HRTEM)

Machine learning techniques are attractive options for developing highly-accurate analysis tools for nanomaterials characterization, including high-resolution transmission electron microscopy (HRTEM). However, successfully implementing such machine learning tools can be difficult due to the challenges in procuring sufficiently large, high-quality training datasets from experiments. In this work, we introduce Construction Zone, a Python package for rapid generation of complex nanoscale atomic structures which enables fast, systematic sampling of realistic nanomaterial structures and can be used as a random structure generator for large, diverse synthetic datasets. Using Construction Zone, we develop an end-to-end machine learning workflow for training neural network models to analyze experimental atomic resolution HRTEM images on the task of nanoparticle image segmentation purely with simulated databases. Further, we study the data curation process to understand how various aspects of the curated simulated data—including simulation fidelity, the distribution of atomic structures, and the distribution of imaging conditions—affect model performance across three benchmark experimental HRTEM image datasets. Using our workflow, we are able to achieve state-of-the-art segmentation performance on these experimental benchmarks and, further, we discuss robust strategies for consistently achieving high performance with machine learning in experimental settings using purely synthetic data. Construction Zone and its documentation are available at https://github.com/lerandc/construction_zone.

36 MATERIALS SCIENCE↗