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 829 records · Page 46

Conditional Generative Adversarial Networks (cGANs) for Near Real-Time Precipitation Estimation from Multispectral GOES-16 Satellite Imageries—PERSIANN-cGAN

In this paper, we present a state-of-the-art precipitation estimation framework which leverages advances in satellite remote sensing as well as Deep Learning (DL). The framework takes advantage of the improvements in spatial, spectral and temporal resolutions of the Advanced Baseline Imager (ABI) onboard the GOES-16 platform along with elevation information to improve the precipitation estimates. The procedure begins by first deriving a Rain/No Rain (R/NR) binary mask through classification of the pixels and then applying regression to estimate the amount of rainfall for rainy pixels. A Fully Convolutional Network is used as a regressor to predict precipitation estimates. The network is trained using the non-saturating conditional Generative Adversarial Network (cGAN) and Mean Squared Error (MSE) loss terms to generate results that better learn the complex distribution of precipitation in the observed data. Common verification metrics such as Probability Of Detection (POD), False Alarm Ratio (FAR), Critical Success Index (CSI), Bias, Correlation and MSE are used to evaluate the accuracy of both R/NR classification and real-valued precipitation estimates. Statistics and visualizations of the evaluation measures show improvements in the precipitation retrieval accuracy in the proposed framework compared to the baseline models trained using conventional MSE loss terms. This framework is proposed as an augmentation for PERSIANN-CCS (Precipitation Estimation from Remotely Sensed Information using Artificial Neural Network- Cloud Classification System) algorithm for estimating global precipitation.

42 ENGINEERING↗

Consideration for the application of artificial neural networks to criticality code validation - 14270

The artificial neural network (ANN) is a consistent example for non-parametric parameter estimation and regression, with powerful universal approximation properties, that is distribution independent. ANN application to criticality code validation centers on aligning mathematical relationships between code validation parameters and neural network prediction for those parameter values. Two specific goals are: (1) an appropriate ANN architecture to determine validation parameter values, and (2) bootstrapping individual ANNs as a 'Prediction Interval' (PI) technique to estimate the Calculation Margin and Upper Subcritical Limit. The individual ANN workflow is segregated into Training, Validation (network), and Testing Sets, where the network predictive properties and performance are expressed in the latter set. The Bootstrap ANN replicates a large set of individual ANNs (taken from the original data distribution) where (1-α/2)100% PI estimates can be determined. Results from the ANN method are compared to a variety of validation examples: a 'toy example' from ANSI/ANS-8.24, Appendix D, a variety of methods noted in a Nuclear Criticality Safety Division 2009 paper, and several validation campaigns for highly enriched uranium and plutonium systems. The ANN method is robust and can be applied to single or multivariate inputs. A trained ANN can provide both an average estimate (e.g., single value) and an estimate over a range of independent variable values where the kUSL can be formed in a regression relationship suitable for extrapolation. The input dependence has been tested, ranging from 15 to over 400 sample size distributions. An expanded Shapiro-Wilk test (for sample sizes up to 5000) was implemented to confirm that the ANN method is transparent to distribution function. The Principle Component Analysis method was applied as an input preprocessing step embedded within the ANN in order to reduce dimensionality and correlation for multivariable inputs. This can potentially aid in determining accurate margins over applying arbitrary margins. The automatic optimization of the Bootstrap ANN PI is left for future consideration. (authors)

42 ENGINEERING↗

Systematic softening in universal machine learning interatomic potentials

Machine learning interatomic potentials (MLIPs) have introduced a new paradigm for atomic simulations. Recent advancements have led to universal MLIPs (uMLIPs) that are pre-trained on diverse datasets, providing opportunities for universal force fields and foundational machine learning models. However, their performance in extrapolating to out-of-distribution complex atomic environments remains unclear. In this study, we highlight a consistent potential energy surface (PES) softening effect in three uMLIPs: M3GNet, CHGNet, and MACE-MP-0, which is characterized by energy and force underprediction in atomic-modeling benchmarks including surfaces, defects, solid-solution energetics, ion migration barriers, phonon vibration modes, and general high-energy states. The PES softening behavior originates primarily from the systematically underpredicted PES curvature, which derives from the biased sampling of near-equilibrium atomic arrangements in uMLIP pre-training datasets. Our findings suggest that a considerable fraction of uMLIP errors are highly systematic, and can therefore be efficiently corrected. We argue for the importance of a comprehensive materials dataset with improved PES sampling for next-generation foundational MLIPs.

36 MATERIALS SCIENCE↗

Attention Enabled Multi-Agent DRL for Decentralized Volt-VAR Control of Active Distribution System Using PV Inverters and SVCs

This paper proposes attention enabled multi-agent deep reinforcement learning (MADRL) framework for active distribution network decentralized Volt-VAR control. Using the unsupervised clustering, the whole distribution system can be decomposed into several sub-networks according to the voltage and reactive power sensitivity relationships. Then, the distributed control problem of each sub-network is modeled as Markov games and solved by the improved MADRL algorithm, where each sub-network is modeled as an adaptive agent. An attention mechanism is developed to help each agent focus on specific information that is mostly related to the reward. All agents are centrally trained offline to learn the optimal coordinated Volt-VAR control strategy and executed in a decentralized manner to make online decisions with only local information. Compared with other distributed control approaches, the proposed method can effectively deal with uncertainties, achieve fast decision makings, and significantly reduce the communication requirements. Comparison results with model-based and other data-driven methods on IEEE 33-bus and 123-bus systems demonstrate the benefits of the proposed approach.

distribution network↗

AMSR-2 Daily Snow Depth Data Product Using a Neural Network Algorithm Trained by Collocated ICESat-2 Measurements

By using diffusion theory and Monte Carlo lidar radiative transfer simulations, Hu 1 et al. (2022b) has derived snow depth from the first-, second- and third-order moments of the lidar backscattering pathlength distribution. Lu 2 et al. (2022,2024) calculated the snow depth by applying the methods to the satellite ICESat-2 lidar measurements over the Arctic sea ice, as well as land surfaces of Northern Hemisphere. In this paper, a neural network (NN) algorithm, employing several channels from AMSR-2 and the humidity vertical profiles GMAO GEOS-IT, is trained to determine snow depth identified by time and geolocation matched 2019 ICESat-2 snow-depth data during winter months over the Arctic sea ice. The trained NN snow-depth was applied to 2014-2020 AMSR-2 clear pixel data, although the algorithms perform reasonably well in thinner clouds. This paper used AMSR-2 data, a passive microwave instrument to generate a wide range of snow depth data, covering extensive spatial areas in the cross-orbit direction.

Neural Network↗

Energy Budget Constraints on the Time History of Aerosol Forcing and Climate Sensitivity

Abstract An observationally constrained time series of historical aerosol effective radiative forcing (ERF) from 1750 to 2019 is developed in this study. We find that the time history of aerosol ERFs diagnosed in CMIP6 models exhibits considerable variation and explore how the time history of aerosol forcing influences the probability distributions of present‐day aerosol forcing and emergent metrics such as climate sensitivity. Using a simple energy balance model, trained on CMIP6 climate models and constrained by observed near‐surface warming and ocean heat uptake, we derive estimates for the historical aerosol forcing. We find 2005–2014 mean aerosol ERF to be −1.1 (−1.8 to −0.5) W m −2 relative to 1750. Assuming recently published historical emissions from fossil fuel and industrial sectors and biomass burning emissions from SSP2‐4.5, aerosol ERF in 2019 is −0.9 (−1.5 to −0.4) W m −2 . There is a modest recovery in aerosol forcing (+0.025 W m −2 decade −1 ) between 1980 and 2014. This analysis also gives a 5%–95% range of equilibrium climate sensitivity of 1.8°C –5.1°C (best estimate 3.1°C) with a transient climate response of 1.2°C –2.6°C (best estimate 1.8°C).

54 ENVIRONMENTAL SCIENCES↗

Modelling baryonic physics in future weak lensing surveys

Modifications of the matter power spectrum due to baryonic physics are one of the major theoretical uncertainties in cosmological weak lensing measurements. Developing robust mitigation schemes for this source of systematic uncertainty increases the robustness of cosmological constraints, and may increase their precision if they enable the use of information from smaller scales. Here we explore the performance of two mitigation schemes for baryonic effects in weak lensing cosmic shear: the principal component analysis (PCA) method and the halo-model approach in hmcode. We construct mock tomographic shear power spectra from four hydrodynamical simulations, and run simulated likelihood analyses with cosmolike assuming LSST-like survey statistics. With an angular scale cut of ℓmax < 2000, both methods successfully remove the biases in cosmological parameters due to the various baryonic physics scenarios, with the PCA method causing less degradation in the parameter constraints than hmcode. For a more aggressive ℓmax = 5000, the PCA method performs well for all but one baryonic physics scenario, requiring additional training simulations to account for the extreme baryonic physics scenario of Illustris; hmcode exhibits tensions in the 2D posterior distributions of cosmological parameters due to lack of freedom in describing the power spectrum for $k \gt 10\ h^{-1}\, \mathrm{Mpc}$. We investigate variants of the PCA method and improve the bias mitigation through PCA by accounting for the noise properties in the data via Cholesky decomposition of the covariance matrix. Our improved PCA method allows us to retain more statistical constraining power while effectively mitigating baryonic uncertainties even for a broad range of baryonic physics scenarios.

79 ASTRONOMY AND ASTROPHYSICS↗

Comparative time-resolved photoemission from the Cu(100) and Cu(111) surfaces

Motivated by the striking dependence of the valence electronic structure of transition metal surfaces on their crystallographic orientation, and by emerging experiments on laser-assisted extended ultraviolet (XUV) photoemission from solid surfaces, we calculate photoemission spectra from Cu(100) and Cu(111) surfaces as a function of the photoelectron final kinetic energy and the delay between the ionizing attosecond XUV pulse train and assisting infrared (IR) laser pulse. Our numerical simulations predict distinct differences in delay-dependent photoelectron energy distributions and photoemission time delays for Cu(100) and Cu(111) surfaces. Furthermore, these differences can be scrutinized experimentally with existing technology in a suggested in situ comparative RABBITT (reconstruction of attosecond beating by interference of two-photon transitions) configuration by placing the two surfaces on a sliding platform while keeping all optical components and pathlengths fixed. Our calculations also show that the inclusion of the Fresnel-reflected incident IR pulse at the metal-vacuum interface modifies photoelectron spectra and photoemission time delays in a characteristic way that reveals the degree of spatial location of the initial electronic states.

74 ATOMIC AND MOLECULAR PHYSICS↗

Neural network based analysis of multimodal bond distributions using extended x-ray absorption fine structure spectra

Knowledge of the local coordination environment around atomic species in functional materials is critical for understanding their mechanisms of operation. Heterogeneous mixtures of metal complexes are ubiquitous in catalysts, ionic liquids, molten salts, biological enzymes, and geochemical systems, among many others. Extracting information from ensemble-average measurements about the structural and compositional descriptors of each type of coordination complex comprising the mixture is not generally possible, especially when they possess multimodal bond-length distributions. Here, we developed a method that enables the mapping of an x-ray absorption spectrum on the radial distribution function describing the average environment of the metal ions. The supervised neural network based method utilizes an objective training set, for which the choice of the local structural motifs is completely agnostic to the theoretically expected structure and dynamics of the modeled system. The method was validated using first-principles modeling of structural dynamics of nickel complexation in molten salts, and it applies to a large class of heterogeneous systems, including those studied under in situ and operando conditions.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

The Bird project: Using Big Data tools to support Search Analytics

The Bird project explored the use of big data analytics tool to improve the findability of information within the Sandia internal network. We were able to perform query classification utilizing the supervised learning algorithms in the Apache Spark library. By relying on the distributed processing capabilities provided by the Apache Hadoop framework, we successfully processed the large query log files needed to train the models in this effort. The capabilities developed in this project are being used to enhance the effectiveness of the enterprise search engine.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗

DEEP CELLULAR RECURRENT NEURAL ARCHITECTURE FOR EFFICIENT MULTIDIMENSIONAL TIME-SERIES DATA PROCESSING

Efficient processing of time series data is a fundamental yet challenging problem in pattern recognition. Though recent developments in machine learning and deep learning have enabled remarkable improvements in processing large scale datasets in many application domains, most are designed and regulated to handle inputs that are static in time. Many real-world data, such as in biomedical, surveillance and security, financial, manufacturing and engineering applications, are rarely static in time, and demand models able to recognize patterns in both space and time. Current machine learning (ML) and deep learning (DL) models adapted for time series processing tend to grow in complexity and size to accommodate the additional dimensionality of time. Specifically, the biologically inspired learning based models known as artificial neural networks that have shown extraordinary success in pattern recognition, tend to grow prohibitively large and cumbersome in the presence of large scale multi-dimensional time series biomedical data such as EEG. Consequently, this work aims to develop representative ML and DL models for robust and efficient large scale time series processing. First, we design a novel ML pipeline with efficient feature engineering to process a large scale multi-channel scalp EEG dataset for automated detection of epileptic seizures. With the use of a sophisticated yet computationally efficient time-frequency analysis technique known as harmonic wavelet packet transform and an efficient self-similarity computation based on fractal dimension, we achieve state-of-the-art performance for automated seizure detection in EEG data. Subsequently, we investigate the development of a novel efficient deep recurrent learning model for large scale time series processing. For this, we first study the functionality and training of a biologically inspired neural network architecture known as cellular simultaneous recurrent neural network (CSRN). We obtain a generalization of this network for multiple topological image processing tasks and investigate the learning efficacy of the complex cellular architecture using several state-of-the?art training methods. Finally, we develop a novel deep cellular recurrent neural network (CDRNN) architecture based on the biologically inspired distributed processing used in CSRN for processing time series data. The proposed DCRNN leverages the cellular recurrent architecture to promote extensive weight sharing and efficient, individualized, synchronous processing of multi-source time series data. Experiments on a large scale multi-channel scalp EEG, and a machine fault detection dataset show that the proposed DCRNN offers state-of-the-art recognition performance while using substantially fewer trainable recurrent units.

Vidyaratne, Lasitha S.↗

Ar Atmosphere: Implications for Structure and Composition of Mercury's Crust

We examine the possibilities of sustaining an argon atmosphere by diffusion from the upper 10 km of crust, and alternatively by effusion from a molten or previously molten area at great depth . Ar-40 in the atmospheres of the planets is a measure of potassium abundance in the interiors since Ar-40 is a product of radiogenic decay of K-40 by electron capture with the subsequent emission of a 1.46 eV gamma-ray. Although the Ar-40 in the earth's atmosphere is expected to have accumulated since the late bombardment, Ar-40 in surface-bounded exospheres is eroded quickly by photoionization and electron impact ionization. Thus, the argon content in the exospheres of the Moon, Mercury and probably Europa is representative of current effusion rather than accumulation over the lifetime of the body. Argon content will be a function of K content, temperature, grain size distribution, connected pore volume and possible seismic activity. Although Mercury and the Moon differ in many details, we can train the solutions to diffusion equations to predict the average lunar atmosphere. Then these parameters can be varied for Hermean conditions. Assuming a lunar crustal potassium abundance of 300 ppm, the observed argon atmosphere requires equilibrium between the argon production in the upper 9 Km of the moon (1.135 x 10(exp -3) cm(exp -3) s(exp -1)) and its loss. Hodges et al. conclude that this loss rate and the observed time variability requires argon release through seismic activity, tapping a deep argon source. An important observation is that the extreme surface of the Moon is enhanced in argon rather than depleted, as one would expect from outgassing of radiogenic argon. Manka and Michel concluded that ion implantation explains the surface enhancement of Ar-40. About half of the argon ions produced in the lunar atmosphere would return to the surface, where they would become embedded in the rocks. Similarly, at Mercury we expect the surface rocks to be enhanced in Ar-40 wherever the magnetosphere has been open over time. Thus the measurement of surface composition will reveal the long-term effects of solar wind-magnetosphere interaction. Additional information is contained in the original extended abstract.

Killen, R. M.↗

Conflict Resolution Performance in an Experimental Study of En Route Free Maneuvering Operations

NASA has developed a far-term air traffic management concept, termed Distributed Air/Ground Traffic Management (DAG-TM). One component of DAG-TM, En Route Free Maneuvering, allows properly trained flight crews of equipped autonomous aircraft to assume responsibility for separation from other autonomous aircraft and from Instrument Flight Rules (IFR) aircraft. Ground-based air traffic controllers continue to separate IFR traffic and issue flow management constraints to all aircraft. To examine En Route Free Maneuvering operations, a joint human-in-the-loop experiment was conducted in summer 2004 at the NASA Ames and Langley Research Centers. Test subject pilots used desktop flight simulators to resolve traffic conflicts and adhere to air traffic flow constraints issued by subject controllers. The experimental airspace integrated both autonomous and IFR aircraft at varying traffic densities. This paper presents a subset of the En Route Free Maneuvering experimental results, focusing on airborne and ground-based conflict resolution, and the effects of increased traffic levels on the ability of pilots and air traffic controllers to perform this task. The results show that, in general, increases in autonomous traffic do not significantly impact conflict resolution performance. In addition, pilot acceptability of autonomous operations remains high throughout the range of traffic densities studied. Together with previously reported findings, these results continue to support the feasibility of the En Route Free Maneuvering component of DAG-TM.

Doble, Nathan A.↗

Operational Characteristics and Plasma Measurements in a Low-Energy FARAD Thruster

Pulsed inductive plasma accelerators are spacecraft propulsion devices in which energy is stored in a capacitor and then discharged through an inductive coil. The device is electrodeless, inducing a plasma current sheet in propellant located near the face of the coil. The propellant is accelerated and expelled at a high exhaust velocity (order of 10 km/s) through the interaction of the plasma current with an induced magnetic field. The Faraday Accelerator with RF-Assisted Discharge (FARAD) thruster is a type of pulsed inductive plasma accelerator in which the plasma is preionized by a mechanism separate from that used to form the current sheet and accelerate the gas. Employing a separate preionization mechanism in this manner allows for the formation of an inductive current sheet at much lower discharge energies and voltages than those found in previous pulsed inductive accelerators like the Pulsed Inductive Thruster (PIT). In this paper, we present measurements aimed at quantifying the thruster's overall operational characteristics and providing additional insight into the nature of operation. Measurements of the terminal current and voltage characteristics during the pulse help quantify the output of the pulsed power train driving the acceleration coil. A fast ionization gauge is used to measure the evolution of the neutral gas distribution in the accelerator prior to a pulse. The preionization process is diagnosed by monitoring light emission from the gas using a photodiode, and a time-resolved global view of the evolving, accelerating current sheet is obtained using a fast-framing camera. Local plasma and field measurements are obtained using an array of intrusive probes. The local induced magnetic field and azimuthal current density are measured using B-dot probes and mini-Rogowski coils, respectively. Direct probing of the number density and electron temperature is performed using a triple probe.

Polzin, K. A.↗

Evaluation of the Cloud Fields in the UK Met Office HadGEM3-UKCA Model Using the CCCM Satellite Data Product to Advance Our Understanding of the Influence of Clouds on Tropospheric Composition and Chemistry

To determine the role of clouds in driving inter-annual and inter-seasonal variability of trace gases in the troposphere and lower stratosphere with a particular focus on the importance of cloud modification of photolysis. To evaluate the cloud fields and their vertical distribution in the HadGEM3 model utilizing CCCM, a unique 3-D cloud data product merged from multiple A-Train satellites (CERES, CloudSat, CALIPSO, and MODIS) developed at the NASA Langley Research Center.

Varma, Sunil↗

Uncertainties in Air Exchange using Continuous-Injection, Long-Term Sampling Tracer-Gas Methods

The PerFluorocarbon Tracer (PFT) method is a low-cost approach commonly used for measuring air exchange in buildings using tracer gases. It is a specific application of the more general Continuous-Injection, Long-Term Sampling (CILTS) method. The technique is widely used but there has been little work on understanding the uncertainties (both precision and bias) associated with its use, particularly given that it is typically deployed by untrained or lightly trained people to minimize experimental costs. In this article we will conduct a first-principles error analysis to estimate the uncertainties and then compare that analysis to CILTS measurements that were over-sampled, through the use of multiple tracers and emitter and sampler distribution patterns, in three houses. We find that the CILTS method can have an overall uncertainty of 10-15percent in ideal circumstances, but that even in highly controlled field experiments done by trained experimenters expected uncertainties are about 20percent. In addition, there are many field conditions (such as open windows) where CILTS is not likely to provide any quantitative data. Even avoiding the worst situations of assumption violations CILTS should be considered as having a something like a ?factor of two? uncertainty for the broad field trials that it is typically used in. We provide guidance on how to deploy CILTS and design the experiment to minimize uncertainties.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Stay Alive--Simulation for Situational Safety Awareness

STAY ALIVE is an idea for a safety awareness simulation prototype, powered by gaming technology, that would make safety training enlightening, engaging and fun. Recalling initial instructions and using situational awareness principles, participants would escape a fire by choosing the appropriate door. Escape times would be measured while stressors increased. This presentation describes how STAY ALIVE utilizes first person point of view (PoV), a generic scenario, immersion- and presence-enhancing design, and ease of distribution to provide more people opportunity to realize, review, analyze and practice effective awareness behaviors. The goals for this prototype include facilitating interest in first-person PoV safety training and eliciting further suggestions on prevention technologies.

Ruder, Michelle↗

Hydrologic and Erosion Models To Assess Land Use and Management Practices Affecting Soil Erosion

We developed a new, coupled, hydrologic-erosion modeling and a targeted field data-collection program to quantify soil erosion rates and sediment yield in arid regions. While the methodology has a wide range of actual and potential applications, we use military training activities as an example. The methodology is applied at the Yakima Training Center (YTC) in south-central Washington, USA where most erosion and transport occurs during extreme events of short duration, often associated with rapid rain-induced snowmelt on frozen soil. The distributed hydrologic and soil erosion modeling system is used to simulate continuous water balance and soil thermal state throughout all seasons of the year. We estimated surface runoff and sediment yield for relatively undisturbed areas as well as from roads, firebreaks, and vehicle tracks associated with training activities at the site. Field data were collected on over 100 hillslope profile transects across the YTC to parameterize, test, and evaluate the linked modeling system. We successfully validated the modeling system against measured sediment yield from twelve sedimentation ponds within the YTC. The simulation results are superior to those from two currently used models, which help to illustrate applicability of the new erosion prediction technology.

54 ENVIRONMENTAL SCIENCES↗