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 577 records · Page 32

Ultrasonic Measurements of Temperature Distribution and Heat Fluxes Across Containments of Extreme Environments

Extreme conditions are common in energy conversion, material processing, nuclear, airspace, and military applications. In such environments, the most hardened insertion sensors do not perform reliably for long. Ultrasonic measurements, on the other hand, can be acquired noninvasively, with sensitive components kept away from the damaging environment. We have previously developed the ultrasonic method for measuring the spatial distribution of temperatures in solid materials applicable in the cases when large thermal gradients are present. In the developed approach, we use the echogenically segmented ultrasound propagation path, structured to contain engineered or naturally occurring echogenic features, to produce a train of echoes in response to an external pulse of ultrasonic excitation. The delays between the echoes, which encode the information on the temperature distribution in the corresponding segments, is used to reconstruct unknown temperature profile. In this paper, we outline the results of pilot-scale testing of the developed approach and demonstrate its application to the measurements of the temperature distribution across the containment of a high-temperature combustion process. The validation results show that the estimated temperature profile is correctly captured, and the measurement accuracy can be comparable with traditional insertion sensors, such as thermocouples. Overall, the testing has confirmed that the developed approach has matured to become an attractive alternative to conventional sensing in solving challenging problems of long-term temperature measurements in extreme environments. Heat fluxes and thermal stresses in the structure can then be characterized noninvasively using the measured temperature distribution as the basis.

Jia, Yunlu↗

SU-G-206-01: A Fully Automated CT Tool to Facilitate Phantom Image QA for Quantitative Imaging in Clinical Trials

Purpose: The use of Quantitative Imaging (QI) methods in Clinical Trials requires both verification of adherence to a specified protocol and an assessment of scanner performance under that protocol, which are currently accomplished manually. This work introduces automated phantom identification and image QA measure extraction towards a fully-automated CT phantom QA system to perform these functions and facilitate the use of Quantitative Imaging methods in clinical trials. Methods: This study used a retrospective cohort of CT phantom scans from existing clinical trial protocols - totaling 84 phantoms, across 3 phantom types using various scanners and protocols. The QA system identifies the input phantom scan through an ensemble of threshold-based classifiers. Each classifier - corresponding to a phantom type - contains a template slice, which is compared to the input scan on a slice-by-slice basis, resulting in slice-wise similarity metric values for each slice compared. Pre-trained thresholds (established from a training set of phantom images matching the template type) are used to filter the similarity distribution, and the slice with the most optimal local mean similarity, with local neighboring slices meeting the threshold requirement, is chosen as the classifier’s matched slice (if it existed). The classifier with the matched slice possessing the most optimal local mean similarity is then chosen as the ensemble’s best matching slice. If the best matching slice exists, image QA algorithm and ROIs corresponding to the matching classifier extracted the image QA measures. Results: Automated phantom identification performed with 84.5% accuracy and 88.8% sensitivity on 84 phantoms. Automated image quality measurements (following standard protocol) on identified water phantoms (n=35) matched user QA decisions with 100% accuracy. Conclusion: We provide a fullyautomated CT phantom QA system consistent with manual QA performance. Further work will include parallel component to automatically verify image acquisition parameters and automated adherence to specifications. Institutional research agreement, Siemens Healthcare; Past recipient, research grant support, Siemens Healthcare; Consultant, Toshiba America Medical Systems; Consultant, Samsung Electronics; NIH Grant support from: U01 CA181156.

60 APPLIED LIFE SCIENCES↗

PickerXL, A Large Deep Learning Model to Measure Arrival Times from Noisy Seismic Signals

Precisely measuring seismic arrival times is a labor-intensive task but is critical for both earthquake monitoring and subsurface imaging. Recently published deep learning models have demonstrated superior performance compared to traditional automatic approaches for picking arrival times. Although existing deep learning models have shown promising results, further advancements are necessary as their performance is not yet satisfactory especially when applied to new regions and station networks. Increasing model size has led to improved performance in other machine learning applications. Here, we aimed to investigate whether enlarging deep learning models can increase performance on accepted benchmarks. We trained three models of varying sizes, small (1X), medium (4X), and large (16X), using globally distributed local and regional earthquake signals and background noise waveforms from a benchmark dataset, Stanford Earthquake Dataset. Our results indicate that the largest model (PickerXL) outperforms both the smaller models and Seisbench implementation of the PhaseNet model, which has the same number of parameters as our small model. The PickerXL model’s enhanced capacity to extract complex patterns from seismograms contributes to its superior arrival picking abilities compared to the smaller model.

Chai, Chengping [Oak Ridge National Laboratory (OR↗

Project 57 Air Monitoring Report: October 1, 2013, through December 31, 2014

On April 24, 1957, the Atomic Energy Commission (AEC, now the Department of Energy [DOE]) conducted the Project 57 safety experiment in western Emigrant Valley north east of the Nevada National Security Site (NNSS, formerly the Nevada Test Site) on lands withdrawn by the Department of Defense (DoD) for the Nevada Test and Training Range (NTTR). The test was undertaken to develop (1) a means of estimating plutonium distribution resulting from a nonnuclear detonation; (2) biomedical evaluation techniques for use in plutonium-laden environments; (3) methods of surface decontamination; and (4) instruments and field procedures for prompt estimation of alpha contamination (Shreve, 1958). Although the test did not result in the fission of nuclear materials, it did disseminate plutonium across the land surface. Following the experiment, the AEC fenced the contaminated area and returned control of the surrounding land to the DoD. Various radiological surveys have been performed in the area and in 2007, the DOE expanded the demarked contamination area by posting signs 200 to 400 feet (60 to 120 meters) outside of the original fence. Plutonium in soil is thought to attach preferentially to smaller particles. Therefore, redistribution of soil particulates by wind (dust) is the mechanism most likely to transport plutonium beyond the boundary of the Project 57 contamination area. In 2011, DRI installed two instrumentation towers to measure radiological, meteorological, and dust conditions. The monitoring activity was implemented to determine if radionuclide contamination was detectable in samples of airborne dust and characterize meteorological and environmental parameters that influence dust transport. Collected data also permits comparison of radiological conditions at the Project 57 monitoring stations to conditions observed at Community Environmental Monitoring Program (CEMP) stations around the NTTR. Biweekly samples of airborne particulates are submitted for laboratory assessment of gross alpha and gross beta radioactivity and for determination of gamma-emitting radionuclides. Annual average gross alpha values at the Project 57 monitoring stations are in the same range as the highest two values reported for the CEMP stations surrounding the NTTR. Annual average gross beta values at the Project 57 monitoring stations are slightly higher than the lowest value reported for the CEMP stations surrounding the NTTR. Gamma spectroscopy analyses on samples collected from the Project 57 stations identified only naturally occurring radionuclides. No manmade radionuclides were detected. Thermoluminescent dosimeters (TLDs) indicated that the average annual radioactivity dose at the monitoring stations is higher than the dose determined at surrounding CEMP stations but approximately half of the estimated national average dose received by the general public as a result of exposure to natural sources. The TLDs at the Project 57 monitoring stations are exposed to both natural sources (terrestrial and cosmic) and radioactive releases from the Project 57 contamination area. These comparisons show that the gross alpha, gross beta, and gamma spectroscopy levels at the Project 57 monitoring stations are similar to levels observed at the CEMP stations but that the average annual dose rate is higher than at the CEMP stations. Winds in excess of approximately 15 mph begin to generate dust movement by saltation (migration of sand at the ground surface) or direct suspension in the air. Saltated sand, PM10 (inhalable) dust, and PM2.5 (fine particulate dust) exhibit an approximately exponential increase with increasing wind speed. The greatest concentrations of dust occur for winds exceeding 20 mph. During the reporting period, winds in excess of 20 mph occurred approximately 1.6 percent of the time. Preliminary assessment of individual wind events suggests that dust generation is highly variable likely because of the influence of other meteorological and environmental parameters. Although winds sufficient to generate significant amounts of dust occur at the Project 57 site, they are infrequent and of short duration. Additionally, the potential for wind transport of dust is dependent on other parameters whose influence have not yet been assessed.

54 ENVIRONMENTAL SCIENCES↗

Project 57 Air Monitoring Report: January 1 through December 31, 2016

On April 24, 1957, the Atomic Energy Commission (AEC, now the Department of Energy [DOE]) conducted the Project 57 safety experiment in western Emigrant Valley northeast of the Nevada National Security Site (NNSS, formerly the Nevada Test Site) on lands withdrawn by the Department of Defense (DOD) for the Nevada Test and Training Range (NTTR). The test was undertaken to develop (1) a means of estimating plutonium distribution resulting from a non-nuclear detonation; (2) biomedical evaluation techniques for use in plutonium-laden environments; (3) methods of surface decontamination; and (4) instruments and field procedures for prompt estimation of alpha contamination (Shreve, 1958). Although the test did not result in the fission of nuclear materials, it did disseminate plutonium across the land surface. Following the experiment, the AEC fenced the contaminated area and returned control of the surrounding land to the DOD. Various radiological surveys were performed in the area and in 2007, the DOE expanded the demarked Contamination Area (CA) by posting signs 200 to 400 ft (60 to 120 m) outside of the original fence.

54 ENVIRONMENTAL SCIENCES↗

Project 57 Air Monitoring Report: January 1 through December 31, 2017

On April 24, 1957, the Atomic Energy Commission (AEC) (now the Department of Energy [DOE]) conducted the Project 57 safety experiment in western Emigrant Valley northeast of the Nevada National Security Site (NNSS, formerly the Nevada Test Site) on lands withdrawn by the Department of Defense (DOD) for the Nevada Test and Training Range (NTTR). The test was undertaken to develop (1) a means of estimating plutonium distribution resulting from a non-nuclear detonation; (2) biomedical evaluation techniques for use in plutonium-laden environments; (3) methods of surface decontamination; and (4) instruments and field procedures for prompt estimation of alpha contamination (Shreve, 1958). Although the test did not result in the fission of nuclear materials, it did disseminate plutonium across the land surface. Following the experiment, the AEC fenced the contaminated area and returned control of the surrounding land to the DOD. Various radiological surveys were performed in the area and in 2007, the DOE expanded the demarked Contamination Area (CA) by posting signs 200 to 400 ft (60 to 120 m) outside of the original fence. Plutonium in soil attaches preferentially to smaller particles (Tamura, 1985; Friesen, 1992; Murarik et al., 1992; and Misra et al., 1993). Therefore, redistribution of soil particles by wind (dust) and water are the mechanisms most likely to transport plutonium beyond the boundary of the Project 57 CA. Monitoring was implemented in 2011 by Desert Research Institute (DRI) to determine if radionuclide contamination was detectable in samples of airborne dust and to characterize meteorological and environmental parameters that influence dust transport. Initially, two monitoring stations consisting of radiological, meteorological, and dust sampling equipment were installed near the southeast and northeast corners of the CA. In January 2015, the original monitoring stations were dismantled and moved farther to the west along the CA boundary. This move was made to place the monitoring stations downwind of ground zero and the High Contamination Area (HCA) during the dominant northerly and southerly winds. Samples of particles suspended in the air are collected every two weeks and submitted for laboratory assessments of gross alpha and gross beta radioactivity, and for determinations of gamma-emitting radionuclides. In calendar year (CY) 2017, the mean gross alpha concentration at monitoring station P57-4 was approximately 4.25 times the value at monitoring station P57-3. In CY2015 and CY2016, the difference in mean gross alpha concentration at the two stations was approximately 1.5. The mean gross alpha concentrations at P57-3 and P57-4 were approximately 1.9 and 7.9 times, respectively, the mean gross alpha concentrations at the surrounding Community Environmental Monitoring Program (CEMP) stations. The minimum gross alpha concentrations reported for the Project 57 stations are in the range of the minimum values observed at the CEMP stations. However, maximum gross alpha concentrations are greater than the maximum concentrations observed at the surrounding CEMP stations. Gamma spectroscopy analyses resulted in the detection of seven radionuclides. Except for americium-241 (Am-241), all reported radionuclides occur naturally in the environment. The Am-241 detection by gamma spectroscopy was confirmed by alpha spectroscopy. During each quarter of CY2017, four suspended particulate matter samples were selected for alpha spectroscopy analysis. Two were selected each quarter from the regular biweekly samples collected at each of the two monitoring stations. Of the eight samples from P57-3, one was reported to have plutonium-238 (Pu-238) above the minimum detectable activity (MDA) and five were reported to have plutonium 239/240 (Pu-239/240) above the MDA. Of the eight samples from P57-4, three were reported to have Pu-238 above the MDA and six were reported to have Pu-239/240 above the MDA. Soil material is also transported by saltation, which is a wind driven phenomena that bounces sand-sized soil particles across the land surface because they are too heavy to be suspended in the air. Samples of particles transported by saltation were collected downwind and upwind of the CA at both monitoring stations in May 2017 after a 190-day deployment and again in September 2017 after a 114-day deployment. Mass of the saltation samples was determined after oven drying. The September sample had greater mass than the May sample. The same relationship was observed for the suspended particulate matter samples during periods of saltation sample collection. The difference in the collected mass appears to be because of the amount of soil moisture. Higher soil moisture exerts additional isotopic bonds between soil particles and water molecules, and between water molecules that envelop soil particles, making it more difficult for wind to raise the particles as dust. In general, samples collected from saltation traps facing south contained more material than samples collected from traps facing north. This suggests that although saltation material may have been moving back and forth in conjunction with the two dominant wind directions, there was a net trend for saltation material to be transported toward the north. Radiological analyses of the saltation samples show that the smaller particle size faction (<63 μm) generally produced the highest activity levels of Am-241, Pu-238, and Pu-239/240. In general, the isotope activity levels decreased as the particle size increased. These results are consistent with the expectation that the greatest potential for transport of radiological contamination is with the smaller particles. Thermoluminescent dosimeters (TLDs) indicated that the average annual external radioactivity dose at the monitoring stations is slightly higher than the dose determined at the surrounding CEMP stations, but approximately half of the estimated national average dose received by the general public from exposure to natural sources. The TLDs at the Project 57 monitoring stations are exposed to both natural sources (terrestrial and cosmic) and radioactive releases from the Project 57 CA. Winds in excess of approximately 15 mph (24 km/hr) begin to generate dust movement by saltation or suspension, as determined by the monitoring instruments. Saltated particles, PM10 (i.e., inhalable dust), and PM2.5 (i.e., fine particulate dust) exhibit an approximately exponential increase with increasing wind speed. The greatest concentrations of dust occurred for winds exceeding 20 mph (32 km/hr). When the wind/dust analysis was performed for winds separated into the dominant northerly and southerly wind directions, it was evident that the northerly winds generated the higher PM10 concentrations and had the dominate influence on the PM10 concentration determined for all wind speeds when all wind directions were evaluated together. During the year, winds in excess of 20 mph (32 km/hr) occurred approximately one percent of the time. Although winds sufficient to generate dust occur at the Project 57 site, they are infrequent and of short duration. A preliminary assessment of individual wind events suggests that dust generation in response to specific wind conditions is highly variable. Wind speeds that would be expected to generate noticeable dust may not do so in every instance. Additionally, saltation transport in response to wind conditions was less common than expected. These variations were likely because of the influence of meteorological and environmental parameters other than wind.

54 ENVIRONMENTAL SCIENCES↗

Project 57 Air Monitoring Report: January 1 through December 31, 2019

On April 24, 1957, the Atomic Energy Commission (AEC) (now the Department of Energy [DOE]) conducted the Project 57 safety experiment in western Emigrant Valley northeast of the Nevada National Security Site (NNSS) (formerly the Nevada Test Site) on lands withdrawn by the Department of Defense (DOD) for the Nevada Test and Training Range (NTTR). The test was performed to (1) assess a technique for estimating plutonium distribution resulting from a nonnuclear detonation, (2) develop biomedical evaluation techniques for use in plutonium-laden environments, (3) evaluate methods of surface decontamination, and (4) evaluate instruments and field procedures for the prompt estimation of alpha contamination (Shreve, 1958). Although the test did not result in the fission of nuclear materials, it did disseminate plutonium across the land surface. Following the experiment, the AEC fenced the contaminated area and returned control of the surrounding land to the DOD. Various radiological surveys were performed in the area and the DOE expanded the demarked Contamination Area (CA) in 2007 by posting signs 200 ft to 400 ft (60 m to 120 m) outside of the original fence.

54 ENVIRONMENTAL SCIENCES↗

Grid-Integrated Production of Fischer-Tropsch Synfuels from Nuclear Power

Idaho National Laboratory (INL) investigates the relative economic profitability of an integrated energy system (IES) coupling an NPP with a synfuel production process at selected case study locations across the United States. In the synfuel IES, a high-temperature steam electrolysis (HTSE) plant is thermally and electrically coupled with an NPP to produce zero-carbon hydrogen. The synthetic fuel is produced from this H 2 combined with a CO 2 supply using the reverse water gas shift process followed by the Fischer-Tropsch (FT) reaction. This analysis considers a system in which the CO 2 is sourced from regional CO 2 emitters via the construction and operation of pipeline-based CO 2 supply networks. Locating the FT plant at the same site as the NPP and HTSE plants enables the NPP to provide zero-carbon heat and power to the HTSE plant and zero-carbon power to the FT plant as well as avoid the requirement for long-distance H 2 product transport from the HTSE plant to the FT plant. Hydrogen storage is used to enable the NPP to dispatch power to the electrical grid (instead of the HTSE plant) when grid demand increases, thus enabling the FT plant to continue to operate in a steady-state production mode. The ability to cease hydrogen production for several hours within each day enables the NPP to provide power to the grid to balance the electricity market during peak periods and maximize revenues for the nuclear synfuel IES. The FT process design considered has a 99% carbon conversion efficiency. The use of nuclear energy and nuclear energy-derived hydrogen enables synfuel production to achieve this high level of carbon utilization. Additionally, the life-cycle carbon emissions of the nuclear-based synfuel production process are very low, with WTW emissions of approximately 25 gCO 2 e/MJ, including steam credits (generated from FT process excess heat), and approximately 7 gCO 2 e/MJ, if steam credits are excluded. This compares favorably with the WTW emissions of 90.5 gCO 2 e/MJ for a compression-ignition, direct injection (CIDI) vehicle with a fuel economy of 31.6 miles per gallon gasoline equivalent (MPGGE), using low-sulfur diesel produced using conventional petroleum production and refining processes. Several NPPs in various regions of the U.S. are considered as case study analyses. Supply locations and transportation via pipeline of the CO 2 feedstock to the NPP site are analyzed through the National Energy Technology Laboratory (NETL) CO 2 Transport Cost model. The team finds that the amount of CO 2 generated by different sectors is sufficient for the synfuel production process at all locations considered. The CO 2 transportation costs are functions of the distance of the source to the NPP location, the CO 2 capture cost at the source, and the quantity of CO 2 transported. Historical electricity prices for the NPP case study locations are collected and analyzed. Monthly average prices, price range, and duration of negative-price periods vary among these locations. For each location, an auto-regressive moving average (ARMA) model is trained on historical electricity price data. ARMA validation is done to ensure the synthetic price distributions represent one of historical prices with high fidelity. Synthetic time series from these ARMA models are used in a coupled dispatch and system optimization in the Holistic Energy Resource Optimization Network (HERON) to compute the differential net present value (NPV) of the IES. The team finds that this econometric is positive, ranging from $14M–1.3bn (2020) depending on the location. The optimal synfuel IES configuration to obtain this increase in NPV often maximizes the size of the synfuel production process with regards to the size of the NPP. However, the team shows that the NPP still plays a stabilizing role for the grid: In periods of high prices and high loads, more electricity from the NPP is sent to the grid. A high variability of electricity prices and extreme maximum prices tend to drive up electricity production. While it requires significant investment, the synfuel IES could increase the economic profitability for the existing fleet of LWRs across the country while still maintaining the grid stabilizer role of NPPs. During its lifetime, the main costs for the nuclear synfuel IES are the carbon feedstock transportation costs, followed by the capital expenses (CAPEX) and operation and maintenance (O&M) costs while the revenue comes first from the IRA H 2 production tax credit (PTC) and then from the sales of synfuel products. The profitability of the synfuel IES is most sensitive to the value of the hydrogen PTC and the synfuel products as well as the cost of the carbon feedstock, highlighting the importance of governmental incentives regarding hydrogen, carbon emissions, and synfuel in driving the deployment of future nuclear synfuel IESs.

08 HYDROGEN↗

A Search for Heavy Neutral Leptons Decaying to Electron-Positron Pairs and Neutral Pions in the MicroBooNE Detector

This thesis presents a search for heavy neutral leptons (HNLs) decaying inside the MicroBooNE detector. The MicroBooNE detector is a liquid-argon time projection chamber located at Fermilab that receives flux from two neutrino beams; the booster neutrino beam (BNB) and the neutrinos at the main injector (NuMI) beam. The search uses data taken when the NuMI beam was on, with a total exposure of $7.01\times10^{20}$ protons on target. HNLs would be produced in kaon decays, and the source of HNLs targeted in this search is kaons decaying at rest in the NuMI hadron absorber. The kinematics of the HNLs produced in this way allow their decays to be distinguished from the majority of beam-neutrino interactions and cosmic-ray activity that constitute the background. Two HNL decay channels are studied, $\nu$\ee and \vpi. Boosted decision trees (BDTs) are trained to separate the simulated HNL decays from the expected background events. The BDT score distributions are used to calculate upper limits on the mixing angle \umusq in the mass range $10\le m_{\rm HNL}\le 245$~MeV. This is the first direct search for HNL decays to the \vpi channel, and the limits provide the most stringent constraints on \umusq in the mass range $35<\mhnl<175$~MeV.

43 PARTICLE ACCELERATORS↗

Radiation Simulation using Wi-Fi Signal Strength and Frequency

For routine radiological operations, lost radioactive sources, decommissioning and cleanup of nuclear facilities, and radiological terrorist events such as Radioactive Dispersive Devices (RDDs) or Radiological Exposure Devices (REDs), individuals are tasked with accurately locating both point and distributed sources of radiation. Radiation workers must often practice these tasks, whether part of initial training or periodically as part of formal or informal exercises or drills. In such circumstances, it is desirable to have an accurate recreation of a radioactive source, including a method of detecting it, which does not include dangerous amounts of radiation. The goal of this research was to develop a radiation simulation technology that uses IEEE 802.11x W-LAN protocol, i.e. Wi-Fi sources and detectors for these, as an inexpensive, precise and accurate method of replicating sources of gamma radiation. For this work, existing 802.11x sources were used. Software was developed for use with an Android smartphone to detect the presence of these sources. The measurements followed the expected behavior as a function of distance from the sources, mimicking that of gamma radiation, thus demonstrating the fundamental principle of operation. The ultimate system will be used in an outreach program to interest students in the radiation protection field.

07 ISOTOPE AND RADIATION SOURCES↗

FedOSAA: Improving Federated Learning with One-Step Anderson Acceleration

Federated learning (FL) is a distributed machine learning approach that enables multiple local clients and a central server to collaboratively train a model while keeping the data on their own devices. First-order methods, particularly those incorporating variance reduction techniques, are the most widely used FL algorithms due to their simple implementation and stable performance. However, these methods tend to be slow and require a large number of communication rounds to reach the global minimizer. We propose FedOSAA, a novel approach that preserves the simplicity of first-order methods while achieving the rapid convergence typically associated with second-order methods. Our approach applies one Anderson acceleration (AA) step following classical local updates based on first-order methods with variance reduction, such as FedSVRG and SCAFFOLD, during local training. This AA step is able to leverage curvature information from the history points and gives a new update that approximates the Newton-GMRES direction, thereby significantly improving the convergence. We establish a local linear convergence rate to the global minimizer of FedOSAA for smooth and strongly convex loss functions. Numerical comparisons show that FedOSAA substantially improves the communication and computation efficiency of the original first-order methods, achieving performance comparable to second-order methods like GIANT.

Feng, Xue [University of California, Davis]↗

Simulations and cosmological inference: A statistical model for power spectra means and covariances

We describe an approximate statistical model for the sample variance distribution of the nonlinear matter power spectrum that can be calibrated from limited numbers of simulations. Our model retains the common assumption of a multivariate normal distribution for the power spectrum band powers but takes full account of the (parameter-dependent) power spectrum covariance. The model is calibrated using an extension of the framework in Habib et al. (2007) to train Gaussian processes for the power spectrum mean and covariance given a set of simulation runs over a hypercube in parameter space. We demonstrate the performance of this machinery by estimating the parameters of a power-law model for the power spectrum. Within this framework, our calibrated sample variance distribution is robust to errors in the estimated covariance and shows rapid convergence of the posterior parameter constraints with the number of training simulations.

79 ASTRONOMY AND ASTROPHYSICS↗

Fast and accurate learned multiresolution dynamical downscaling for precipitation

Abstract. This study develops a neural-network-based approach for emulating high-resolution modeled precipitation data with comparable statistical properties but at greatly reduced computational cost. The key idea is to use combination of low- and high-resolution simulations (that differ not only in spatial resolution but also in geospatial patterns) to train a neural network to map from the former to the latter. Specifically, we define two types of CNNs, one that stacks variables directly and one that encodes each variable before stacking, and we train each CNN type both with a conventional loss function, such as mean square error (MSE), and with a conditional generative adversarial network (CGAN), for a total of four CNN variants. We compare the four new CNN-derived high-resolution precipitation results with precipitation generated from original high-resolution simulations, a bilinear interpolater and the state-of-the-art CNN-based super-resolution (SR) technique. Results show that the SR technique produces results similar to those of the bilinear interpolator with smoother spatial and temporal distributions and smaller data variabilities and extremes than the original high-resolution simulations. While the new CNNs trained by MSE generate better results over some regions than the interpolator and SR technique do, their predictions are still biased from the original high-resolution simulations. The CNNs trained by CGAN generate more realistic and physically reasonable results, better capturing not only data variability in time and space but also extremes such as intense and long-lasting storms. The new proposed CNN-based downscaling approach can downscale precipitation from 50 to 12 km in 14 min for 30 years once the network is trained (training takes 4 h using 1 GPU), while the conventional dynamical downscaling would take 1 month using 600 CPU cores to generate simulations at the resolution of 12 km over the contiguous United States.

54 ENVIRONMENTAL SCIENCES↗

Sub-daily Statistical Downscaling of Meteorological Variables Using Neural Networks

A new open source neural network temporal downscaling model is described and tested using CRU-NCEP reanal ysis and CCSM3 climate model output. We downscaled multiple meteorological variables in tandem from monthly to sub-daily time steps while also retaining consistent correlations between variables. We found that our feed forward, error backpropagation approach produced synthetic 6 hourly meteorology with biases no greater than 0.6% across all variables and variance that was accurate within 1% for all variables except atmospheric pressure, wind speed, and precipitation. Correlations between downscaled output and the expected (original) monthly means exceeded 0.99 for all variables, which indicates that this approach would work well for generating atmospheric forcing data consistent with mass and energy conserved GCM output. Our neural network approach performed well for variables that had correlations to other variables of about 0.3 and better and its skill was increased by downscaling multiple correlated variables together. Poor replication of precipitation intensity however required further post-processing in order to obtain the expected probability distribution. The concurrence of precipitation events with expected changes in sub ordinate variables (e.g., less incident shortwave radiation during precipitation events) were nearly as consistent in the downscaled data as in the training data with probabilities that differed by no more than 6%. Our downscaling approach requires training data at the target time step and relies on a weak assumption that climate variability in the extrapolated data is similar to variability in the training data.

54 ENVIRONMENTAL SCIENCES↗

ML-Based Pebble Power Reconstruction for Pebble Bed Reactor Analysis

Pebble power reconstruction has been explored to complement the conventional homogenized modeling approach in pebble bed reactor (PBR) analysis, as detailed heterogeneous geometry calculations are computationally expensive. The random distribution of pebble fuels within the core challenges the application of conventional pin power reconstruction methods. To address this, we introduce a machine learning approach based on the transformer model, composed of encoder and decoder layers, to estimate the flux and power form functions for reconstructing individual pebble neutron fluxes and powers. The homogeneous neutron flux distribution within each spectral zone (SZ) is obtained from finite element solutions of global diffusion or transport calculations. Verification tests demonstrate that the trained transformer model accurately predicts power form functions over a range of conditions, including variations in pebble enrichment, location, type, SZ size, and burnup. In particular, verification using a three-dimensional PBR benchmark with burned pebbles shows good agreement in heterogeneous pebble power distributions between Griffin and Serpent. These results highlight the potential of applying conventional pin power reconstruction approaches to PBR cores with randomly distributed pebbles.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

Energy Efficiency Services Sector: Workforce Education and Training Needs

This report provides a baseline assessment of the current state of energy efficiency-related education and training programs and analyzes training and education needs to support expected growth in the energy efficiency services workforce. In the last year, there has been a significant increase in funding for 'green job' training and workforce development (including energy efficiency), through the American Recovery and Reinvestment Act (ARRA). Key segments of the energy efficiency services sector (EESS) have experienced significant growth during the past several years, and this growth is projected to continue and accelerate over the next decade. In a companion study (Goldman et al. 2009), our research team estimated that the EESS will increase two- to four-fold by 2020, to 220,000 person-years of employment (PYE) (low-growth scenario) or up to 380,000 PYE (high-growth scenario), which may represent as many as 1.3 million individuals. In assessing energy efficiency workforce education and training needs, we focus on energy-efficiency services-related jobs that are required to improve the efficiency of residential and nonresidential buildings. Figure ES-1 shows the market value chain for the EESS, sub-sectors included in this study, as well as the types of market players and specific occupations. Our assessment does not include the manufacturing, wholesale, and retail distribution subsectors, or energy efficiency-focused operations and maintenance performed by facility managers.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

QuantumNAT: quantum noise-aware training with noise injection, quantization and normalization

Parameterized Quantum Circuits (PQC) are promising towards quantum advantage on near-term quantum hardware. However, due to the large quantum noises (errors), the performance of PQC models has a severe degradation on real quantum devices. Take Quantum Neural Network (QNN) as an example, the accuracy gap between noise-free simulation and noisy results on IBMQ-Yorktown for MNIST-4 classification is over 60%. Existing noise mitigation methods are general ones without leveraging unique characteristics of PQC; on the other hand, existing PQC work does not consider noise effect. To this end, we present QuantumNAT, a PQC-specific framework to perform noise-aware optimizations in both training and inference stages to improve robustness. We experimentally observe that the effect of quantum noise to PQC measurement outcome is a linear map from noise-free outcome with a scaling and a shift factor. Motivated by that, we propose post-measurement normalization to mitigate the feature distribution differences between noise-free and noisy scenarios. Furthermore, to improve the robustness against noise, we propose noise injection to the training process by inserting quantum error gates to PQC according to realistic noise models of quantum hardware. Lastly, post-measurement quantization is introduced to quantize the measurement outcomes to discrete values, achieving the denoising effect. Extensive experiments on 8 classification tasks using 6 quantum devices demonstrate that QuantumNAT improves accuracy by up to 43%, and achieves over 94% 2-class, 80% 4-class, and 34% 10-class classification accuracy measured on real quantum computers. The code for construction and noise-aware training of PQC is available in the TorchQuantum library.

Wang, Hanrui↗

Development of an Integrated Distribution Management System

This final report details the components, functionality, costs, schedule and benefits of developing an Integrated Distribution Management System (IDMS) for power distribution system operation. The Distribution Automation (DA) and Supervisory Control and Data Acquisition (SCADA) systems used by electric power companies to manage the distribution of electric power to retail energy consumers are vital components of the Nation’s critical infrastructure. Providing electricity is an essential public service and a disruption in that service, if not quickly restored, could threaten the public safety and the Nation’s economic security. Our Nation’s economic prosperity and quality of life have long depended on the essential services that utilities provide; therefore, it is necessary to ensure that electric utilities are able to conduct their operations safely and efficiently. A fully integrated technology of applications is needed to link various remote sensing, communications and control devices with other information tools that help guide Power Distribution Operations personnel. A fully implemented IDMS will provide this, a seamlessly integrated set of applications to raise electric system operating intelligence. IDMS will enhance DA and SCADA through integration of applications such as Geographic Information Systems, Outage Management Systems, Switching Management and Analysis, Operator Training Simulator, and other Advanced Applications, including unbalanced load flow and fault isolation/service restoration. These apps are capable of utilizing and obtaining information from appropriately installed DER, and by integrating disparate systems, the Distribution Operators will benefit from advanced capabilities when analyzing, controlling and operating the electric system.

24 POWER TRANSMISSION AND DISTRIBUTION↗