SEARCH · Search NASA

Results for “Small Data”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

SourceResearch connectionFrom yearThrough year

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

At least 91 records · Page 5

All sources NASA NTRS DOE OSTI

DOE OSTI2020

Graph interpolating activation improves both natural and robust accuracies in data-efficient deep learning

Improving the accuracy and robustness of deep neural nets (DNNs) and adapting them to small training data are primary tasks in deep learning (DL) research. In this paper, we replace the output activation function of DNNs, typically the data-agnostic softmax function, with a graph Laplacian-based high-dimensional interpolating function which, in the continuum limit, converges to the solution of a Laplace–Beltrami equation on a high-dimensional manifold. Furthermore, we propose end-to-end training and testing algorithms for this new architecture. The proposed DNN with graph interpolating activation integrates the advantages of both deep learning and manifold learning. Compared to the conventional DNNs with the softmax function as output activation, the new framework demonstrates the following major advantages: First, it is better applicable to data-efficient learning in which we train high capacity DNNs without using a large number of training data. Second, it remarkably improves both natural accuracy on the clean images and robust accuracy on the adversarial images crafted by both white-box and black-box adversarial attacks. Third, it is a natural choice for semi-supervised learning. This paper is a significant extension of our earlier work published in NeurIPS, 2018. For reproducibility, the code is available at https://github.com/BaoWangMath/DNN-DataDependentActivation .

Mathematics↗

DOE OSTI2020

Prototype energy models for data centers

Data centers in the United States consume about two percent of the nation’s electricity. Because heat gains from IT equipment drive cooling demand, data centers offer unique opportunities for energy savings. However, no prototype energy model for data centers is available in the suite of existing U.S. Department of Energy’s Commercial Prototype Building Models. Here we present the development of two new data center prototype models and their implementation in OpenStudio and EnergyPlus. The small-size data center model represents a computer room in a building served by computer room air conditioners (CRACs); while the large-sized model represents stand-alone data centers served by computer room air handlers (CRAHs) with a central chiller plant. For each data center model, two levels of IT equipment (ITE) load density were considered, to cover the wide range of IT power density of data centers: 40 and 100 W/ft 2 (430 and 1076 W/m 2 ) for the computer room, and 100 and 500 W/ft 2 (1076 and 5382 W/m 2 ) for the stand-alone data center. All other assumptions, such as building envelope, lighting, HVAC efficiencies and schedules, were based on the minimal requirements of ASHRAE Standard 90.1 at various vintages. We introduced a novel concept of supply and return air approach temperatures to capture the essential effects of non-uniform airflow and temperature distribution in data centers. The approach temperatures were pre-computed by computational fluid dynamics (CFD) simulations for various configurations of ITE loads and airflow containment management in data centers. A new feature was developed in EnergyPlus to implement the approach temperature method. A case study was conducted to demonstrate the use of the data center models. The two data center models cover all U.S. climate zones and can be used to evaluate energy saving measures for data centers, as well as to support development of data center energy efficiency codes and standards.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

DOE OSTI2022

An analysis of the hybrid internal mass modeling approach in EnergyPlus

Accurate simulation of building system dynamics is particularly important for understanding building energy flexibility. Among all dynamics in a building, a zone temperature’s variation is especially important, as it significantly affects a building’s electricity load profile when its heating, ventilating, and air conditioning (HVAC) system is controlled with on/off cycles or setpoint reset strategies. To accurately simulate a zone temperature’s dynamics, internal mass needs to be modeled carefully. In this paper, we compare the two internal mass modeling approaches provided by EnergyPlus, i.e., internal mass object and zone air capacitance multiplier, to better understand their impacts on zone temperature simulation. Real building zone temperature dynamic data from small- and medium-sized office buildings are analyzed and compared with simulated data. In particular, we illustrate the effectiveness of a hybrid method of the two EnergyPlus modeling approaches, which yields more realistic zone temperature dynamics, especially when the zone is conditioned with heat pump systems with on/off cycling.

Chen, Zhelun↗

DOE OSTI2026

Techno-Economic Assessment of Data Center Load Demand Powered by Small Modular Reactors and Distributed Energy Resources

The rapid increase in data center energy demand, driven by AI and large-scale data processing, poses significant challenges to global energy infrastructure. Data centers require substantial and reliable energy for continuous operations and high-performance computing. Current electrical grids face issues such as transmission bottlenecks and aging infrastructure, making it difficult to meet these demands. Integrating inverter-based-resources (IBRs) like solar and wind presents both opportunities and challenges due to their intermittent nature. Small Modular Reactors (SMRs) offer a promising solution with their enhanced safety, modularity, reliability, and scalability, providing consistent base load power ideal for data center operations. This study presents a comprehensive techno-economic assessment of powering data center load demand using a combination of SMRs and IBRs with grid-connected and islanded mode. This study utilized Idaho National Laboratory’s (INL) HPC data center hourly load profiles and Xendee microgrid optimization platform to conduct the analysis. In this configuration, SMRs serves as the primary base load power source, consistently providing a steady supply of electricity necessary to meet the minimum load demand of the data center with support from the IBRs. Key performance indicators such as Levelized Cost of Electricity (LCOE), Net Present Value (NPV) has been calculated to assess the economic feasibility. The findings from this research will underscore the strategic benefits of integrating SMR plant with DERs – particularly for critical infrastructure load such as data centers.

14 - SOLAR ENERGY↗

DOE OSTI2022

Advanced Airfoil Cooling Schemes to Increase Efficiency in Gas Turbines for Combined Heat and Power Applications

This report describes a three-year interdisciplinary effort funded by the U.S. Department of Energy’s (DOE) Energy Efficiency and Renewable Energy/Advanced Manufacturing Office (EERE/AMO) to promote market penetration of combined heat and power (CHP) technologies. Prior studies have shown the technical potential for CHP in the United States is much larger than the current deployment of CHP systems. A large portion of the technical potential CHP market aligns with small (<20 MWe) gas turbines. CHP systems are an attractive alternative to reduce greenhouse gas (GHG) emissions. For example, CHP systems can reduce GHG emissions by 30–40% relative to a conventional boiler and power configuration. These GHG emission reductions are “avoided emissions” which means no CO 2 separation or sequestration is required. This report describes an effort to use additive manufacturing (AM) technologies and advanced airfoil cooling designs to increase the turbine inlet temperature by 100 °C for small gas turbines typically used in CHP systems. At the beginning of this effort, baseline performance data for small gas turbines was not available, and the potential benefits of cooling system improvements were not quantified in the available literature.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

DOE OSTI2020

Accuracy of High Explosive Data used for Reactive Burn Model Calibration

Reactive burn models for a high explosive (HE) have three components: an equation of state (EOS) for the products, an EOS for the reactants and a reaction rate. For the products, we discuss the uncertainty in data for the planar detonation state and its release isentrope. For the reactants, the uncertainty in the principal shock locus data is discussed. For the reaction rate, we discuss uncertainties in shock initiation data (distance-of-run to detonation as a function of shock pressure), and curvature effect data (detonation speed as a function of front curvature). An important source of uncertainty for calibrating the reaction rate for a plastic-bonded explosive (PBX) results from variations in heterogeneities; that is the mesoscale structure of HE grains, binder and porosity. This shows up in the scatter of both shock initiation data and curvature effect data with small changes in initial density and initial temperature, and systematic changes with PBX lot. As illustrative examples, we use data for the conventional HMX based PBX 9501 and the insensitive TATB based PBX 9502 since these explosives have been extensively studied and high quality data are readily available in the literature.

45 MILITARY TECHNOLOGY, WEAPONRY, AND NATIONAL DEF↗

DOE OSTI2022

Soil Metabolomics Predict Microbial Taxa as Biomarkers of Moisture Status in Soils from a Tidal Wetland

We present observations from a laboratory-controlled study on the impacts of extreme wetting and drying on a wetland soil microbiome. Our approach was to experimentally challenge the soil microbiome to understand impacts on anaerobic carbon cycling processes as the system transitions from dryness to saturation and vice-versa. Specifically, we tested for impacts on stress responses related to shifts from wet to drought conditions. We used a combination of high-resolution data for small organic chemical compounds (metabolites) and biological (community structure based on 16S rRNA gene sequencing) features. Using a robust correlation-independent data approach, we further tested the predictive power of soil metabolites for the presence or absence of taxa. Here, we demonstrate that taking an untargeted, multidimensional data approach to the interpretation of metabolomics has the potential to indicate the causative pathways selecting for the observed bacterial community structure in soils.

16S rRNA gene↗

DOE OSTI2020

Bose-Einstein condensation phenomenology in systems with repulsive interactions

The role of repulsive interactions in statistical systems of Bose particles is investigated. Three different phenomenological frameworks are considered: A mean-field model, an excluded volume model, and a model with a medium-dependent effective mass. All three models are tuned to yield similar equations of state, with only minor deviations from the ideal Bose gas at small chemical potentials. Our analysis indicates, however, that these models lead to qualitatively different results for the Bose-Einstein condensation phenomenon. We discuss the different aspects of this phenomenon, namely, an onset of the Bose-Einstein condensation, particle number fluctuations, and a behavior of the Bose condensate. The obtained results can be helpful for interpreting the lattice QCD data at small temperature and large isospin chemical potential and the data on multiple pion production in high-energy nuclear collisions.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

DOE OSTI2023

SPLENDAQ: A Detector-Agnostic Data Acquisition System for Small-Scale Physics Experiments

Many scientific applications from rare-event searches to condensed matter system characterization to high-rate nuclear experiments require time-domain triggering on a raw stream of data, where the triggering is generally threshold-based or randomly acquired. When carrying out detector R &D, there is a need for a general data acquisition (DAQ) system to quickly and efficiently process such data. In the SPLENDOR collaboration, we are developing the Python-based SPLENDAQ package for this exact purpose—it offers two main features for offline analysis of continuous data: a threshold triggering algorithm based on the time-domain optimal filter formalism and an algorithm for randomly choosing nonoverlapping segments for noise measurements. Further, combined with the commercially available Moku platform, developed by Liquid Instruments, we have a full pipeline of event building off raw data with minimal setup. Here, we review the underlying principles of this detector-agnostic DAQ package and give concrete examples of its utility in various applications.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

DOE OSTI2021

AtomSets as a hierarchical transfer learning framework for small and large materials datasets

Abstract Predicting properties from a material’s composition or structure is of great interest for materials design. Deep learning has recently garnered considerable interest in materials predictive tasks with low model errors when dealing with large materials data. However, deep learning models suffer in the small data regime that is common in materials science. Here we develop the AtomSets framework, which utilizes universal compositional and structural descriptors extracted from pre-trained graph network deep learning models with standard multi-layer perceptrons to achieve consistently high model accuracy for both small compositional data (<400) and large structural data (>130,000). The AtomSets models show lower errors than the graph network models at small data limits and other non-deep-learning models at large data limits. They also transfer better in a simulated materials discovery process where the targeted materials have property values out of the training data limits. The models require minimal domain knowledge inputs and are free from feature engineering. The presented AtomSets model framework can potentially accelerate machine learning-assisted materials design and discovery with less data restriction.

Chen, Chi (ORCID:0000000180087043)↗

DOE OSTI2023

Machine learning-based inversion for acoustic impedance with large synthetic training data: Workflow and data characterization

Where wells are sparse or training data are difficult to label with high-quality wireline-derived impedance logs, machine learning (ML)-based inversion of acoustic impedance typically depends on small training data sets, leading to biased prediction. We have advanced a novel workflow that applies large synthetic seismic training data to reduce facies-related bias. Using a geologically realistic model as the truth model, we randomly select sparse seed wells to perform sequential Gaussian simulation (SGS) for impedance models of the same geometry and simulate facies variability. We implement random forest regression on 30 features extracted from the synthetic volume. We observe that more seed wells tend to reduce facies-induced bias by sampling more types of facies, resulting in a better prediction. We then focus on the responses of SGS models to facies changes, the number of seed wells necessary for a useful synthetic model, and how much a synthetic model can help ML-based inversion. Here, we observe that the SGS synthetic training model outperforms well-direct training in general. For modeled clastic shore-zone systems in Miocene Gulf of Mexico, two or more seed wells are necessary for a significant reduction of root-mean-square error and outliners, and improvement of facies imaging. In a field-data test, we apply a similar workflow to quantitatively predict acoustic impedance, which is then converted to a sand-volume map at a high-frequency sequence (10–100 m), revealing detailed facies and sandstone patterns. Such results are valuable in many geologic and engineering applications, such as hydrocarbon and CO 2 reservoir prospecting, reserve estimation, simulation, etc.

3D seismic↗

DOE OSTI2022

Analysis of Data Fusion Between Waveform Events and Radionuclide Detections Reported in 2021 by the International Data Centre

During this project, we assessed the percentage of events reported by the International Data Centre (IDC) that are candidates for evaluation using data fusion methods. We calculated the percentage of waveform (seismic, hydroacoustic, infrasound, SHI) events that may be associated with radionuclide (RN) detections and vice versa. For this task, data fusion means identifying RN detections that may be associated with SHI events. The task of producing a fused SHI and RN bulletin is included in the IDC operational manual. As of 2022, the production of a fused event bulletin remains incomplete, largely because methods for producing the bulletin are under development. Nonetheless, simple methods for data fusion have been developed and preliminary software tools are available at the IDC to associate SHI events and RN detections. This report is a first look at the percentage of SHI events that may be candidates for fusion with RN detections or bulletins. One year of IDC bulletin data (2021) is considered in this report. It is important to note that there were no known nuclear explosions during this time period. Hence, we expect that events during this time period would generate SHI and RN signals. If many SHI events are candidates for fusion with RN data, greater priority should be placed on establishing screening procedures before and/or during the fusion process. By contrast, if the number of candidate events is diminishingly small, then data fusion is not a driver for further development of event or detection screening at the IDC. LLNL reviewed the events reported in the Standard Event Bulletin (SEB) and determined which events are candidates for fusion with the Reviewed Radionuclide Reports (RRR). Much of the work involves establishing a metric or metrics for determining whether a Reviewed Event Bulletin (REB) event is a candidate for data fusion.

58 GEOSCIENCES↗

DOE OSTI2021

Predicting fault slip via transfer learning

Abstract Data-driven machine-learning for predicting instantaneous and future fault-slip in laboratory experiments has recently progressed markedly, primarily due to large training data sets. In Earth however, earthquake interevent times range from 10’s-100’s of years and geophysical data typically exist for only a portion of an earthquake cycle. Sparse data presents a serious challenge to training machine learning models for predicting fault slip in Earth. Here we describe a transfer learning approach using numerical simulations to train a convolutional encoder-decoder that predicts fault-slip behavior in laboratory experiments. The model learns a mapping between acoustic emission and fault friction histories from numerical simulations, and generalizes to produce accurate predictions of laboratory fault friction. Notably, the predictions improve by further training the model latent space using only a portion of data from a single laboratory earthquake-cycle. The transfer learning results elucidate the potential of using models trained on numerical simulations and fine-tuned with small geophysical data sets for potential applications to faults in Earth.

58 GEOSCIENCES↗

DOE OSTI2023

Advanced techniques in automated high-resolution scanning transmission electron microscopy

Scanning transmission electron microscopy is a common tool used to study the atomic structure of materials. It is an inherently multimodal tool allowing for the simultaneous acquisition of multiple information channels. Despite its versatility, however, experimental workflows currently rely heavily on experienced human operators and can only acquire data from small regions of a sample at a time. Here, we demonstrate a flexible pipeline-based system for high-throughput acquisition of atomic-resolution structural data using an all-piezo sample stage applied to large-scale imaging of nanoparticles and multimodal data acquisition. As a result, the system is available as part of the user program of the Molecular Foundry at Lawrence Berkeley National Laboratory.

4D-STEM↗

DOE OSTI2022

Generalization in quantum machine learning from few training data

Modern quantum machine learning (QML) methods involve variationally optimizing a parameterized quantum circuit on a training data set, and subsequently making predictions on a testing data set (i.e., generalizing). In this work, we provide a comprehensive study of generalization performance in QML after training on a limited number N of training data points. We show that the generalization error of a quantum machine learning model with T trainable gates scales at worst as $\sqrt{T/N}$. When only K$\ll$T gates have undergone substantial change in the optimization process, we prove that the generalization error improves to $\sqrt{K/N}$. Our results imply that the compiling of unitaries into a polynomial number of native gates, a crucial application for the quantum computing industry that typically uses exponential-size training data, can be sped up significantly. We also show that classification of quantum states across a phase transition with a quantum convolutional neural network requires only a very small training data set. Other potential applications include learning quantum error correcting codes or quantum dynamical simulation. Our work injects new hope into the field of QML, as good generalization is guaranteed from few training data.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2020

Transforming the study of organisms: Phenomic data models and knowledge bases

The rapidly decreasing cost of gene sequencing has resulted in a deluge of genomic data from across the tree of life; however, outside a few model organism databases, genomic data are limited in their scientific impact because they are not accompanied by computable phenomic data. The majority of phenomic data are contained in countless small, heterogeneous phenotypic data sets that are very difficult or impossible to integrate at scale because of variable formats, lack of digitization, and linguistic problems. One powerful solution is to represent phenotypic data using data models with precise, computable semantics, but adoption of semantic standards for representing phenotypic data has been slow, especially in biodiversity and ecology. Some phenotypic and trait data are available in a semantic language from knowledge bases, but these are often not interoperable. In this review, we will compare and contrast existing ontology and data models, focusing on nonhuman phenotypes and traits. We discuss barriers to integration of phenotypic data and make recommendations for developing an operationally useful, semantically interoperable phenotypic data ecosystem.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2021

Implementation of the Windowed Multipole Method in Shift

The windowed multipole (WMP) method has been implemented in the Shift Monte Carlo (MC) radiation transport code with support for both CPU and GPU execution. With this method, small WMP data libraries (~100 MB) can be used to accurately Doppler broaden cross sections to arbitrary temperatures “on the fly” during an MC simulation. This approach yields significant memory savings relative to traditional methods, making it ideal for high-fidelity analysis such as coupled multiphysics simulations. This document provides the exact forms of the WMP equations used by Shift, as well as a detailed description of the structure of WMP HDF5 data files provided by the Massachusetts Institute of Technology (MIT). The Shift implementation has been validated against the OpenMC radiation transport code, with excellent agreement demonstrated for 70 nuclides across an operative range of temperatures. CPU and GPU performance testing using a small module reactor (SMR) problem demonstrated that this method decreases the neutron tracking rate by a factor of ~2 on the Summitdev machine. A new set of WMP data being developed in-house will employ novel methods to improve tracking rates.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

DOE OSTI2020

Impact of LHC vector boson production in heavy ion collisions on strange PDFs

Abstract The extraction of the strange quark parton distribution function (PDF) poses a long-standing puzzle. Measurements from neutrino-nucleus deep inelastic scattering (DIS) experiments suggest the strange quark is suppressed compared to the light sea quarks, while recent studies of $$W^\pm /Z$$ W ± / Z boson production at the LHC imply a larger strange component at small x values. As the parton flavor determination in the proton depends on nuclear corrections, e.g. from heavy-target DIS, LHC heavy ion measurements can provide a distinct perspective to help clarify this situation. In this investigation we extend the nCTEQ15 nPDFs to study the impact of the LHC proton-lead $$W^\pm /Z$$ W ± / Z production data on both the flavor differentiation and nuclear corrections. This complementary data set provides new insights on both the LHC $$W^\pm /Z$$ W ± / Z proton analyses and the neutrino-nucleus DIS data. We identify these new nPDFs as nCTEQ15WZ . Our calculations are performed using a new implementation of the nCTEQ code ( nCTEQ++ ) based on C++ which enables us to easily interface to external programs such as HOPPET, APPLgrid and MCFM. Our results indicate that, as suggested by the proton data, the small x nuclear strange sea appears larger than previously expected, even when the normalization of the $$W^{\pm }/Z$$ W ± / Z data is accommodated in the fit. Extending the nCTEQ15 analysis to include LHC $$W^\pm /Z$$ W ± / Z data represents an important step as we advance toward the next generation of nPDFs.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗