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 757 records · Page 42

redMaPPer. I. Algorithm and SDSS DR8 catalog

We describe redMaPPer, a new red sequence cluster finder specifically designed to make optimal use of ongoing and near-future large photometric surveys. The algorithm has multiple attractive features: (1) it can iteratively self-train the red sequence model based on a minimal spectroscopic training sample, an important feature for high-redshift surveys. (2) It can handle complex masks with varying depth. (3) It produces cluster-appropriate random points to enable large-scale structure studies. (4) All clusters are assigned a full redshift probability distribution P(z). (5) Similarly, clusters can have multiple candidate central galaxies, each with corresponding centering probabilities. (6) The algorithm is parallel and numerically efficient: it can run a Dark Energy Survey-like catalog in ∼500 CPU hours. (7) The algorithm exhibits excellent photometric redshift performance, the richness estimates are tightly correlated with external mass proxies, and the completeness and purity of the corresponding catalogs are superb. We apply the redMaPPer algorithm to ∼10, 000 deg{sup 2} of SDSS DR8 data and present the resulting catalog of ∼25,000 clusters over the redshift range z in [0.08, 0.55]. The redMaPPer photometric redshifts are nearly Gaussian, with a scatter σ {sub z} ≈ 0.006 at z ≈ 0.1, increasing to σ {sub z} ≈ 0.02 at z ≈ 0.5 due to increased photometric noise near the survey limit. The median value for |Δz|/(1 + z) for the full sample is 0.006. The incidence of projection effects is low (≤5%). Detailed performance comparisons of the redMaPPer DR8 cluster catalog to X-ray and Sunyaev-Zel'dovich catalogs are presented in a companion paper.

79 ASTRONOMY AND ASTROPHYSICS↗

Use of neural networks to analyze pulse shape data in low-background detectors

Pacific Northwest National Laboratory has accumulated years of data with ultra-low-background proportional counters collected in an on-site shallow underground laboratory. This large dataset of events is exploited to study the impact of using neural networks for data analysis compared to simple pulse shape discrimination (PSD). The PSD method can introduce false positives for overlapping event distributions; however, a neural network can separate and correctly classify these events. Here, this paper describes the training, testing, and validation of a neutral network, analysis of challenge datasets, and a comparison between the standard PSD approach and a dense, fully-connected neural network.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Deep reinforcement learning for class imbalance fault diagnosis of equipment in nuclear power plants

In equipment fault diagnosis in nuclear power plants, there may be far more samples in one class (e.g., a health state) than in another class (e.g., a fault state). The distribution of data in each class is highly skewed. Most machine learning algorithms are suitable for balanced training datasets. When faced with imbalanced samples, these algorithms tend to provide good identification for the majority classes and bias for the minority classes. However, the misclassification of minority classes can lead to high costs. To address the above problem, this paper develops a deep reinforcement learning-based diagnosis method that models fault diagnosis as a sequential decision-making process. At each time step, the agent receives the state of the environment represented by the training samples and then takes a diagnosis action guided by a policy. If the action is correct/incorrect, the agent receives a positive/negative reward. The reward for minority classes is higher than that for majority classes. The agent’s goal is to obtain as many cumulative rewards as possible in the process, i.e., to identify the sample as correctly as possible. Six demonstration scenarios are constructed, depending on the selected fault datasets and the designed model structures. Experiments show that the proposed method achieves a higher weighted-averaged F1 score than the classical supervised learning method in most cases of class imbalance. Finally, the proposed method has potential applications in the field of class imbalance fault diagnosis of equipment in nuclear power plants.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗

Teaching the Anatomy of Oncology: Evaluating the Impact of a Dedicated Oncoanatomy Course

Purpose: Anatomic considerations are often critical in multidisciplinary cancer care. We developed an anatomy-focused educational program for radiation oncology residents integrating cadaver dissection into the didactic review of diagnostic, surgical, radiologic, and treatment planning, and herein assess its efficacy. Methods and Materials: Monthly, anatomic-site based educational modules were designed and implemented during the 2008-2009 academic year at Duke University Medical Center. Ten radiation oncology residents participated in these modules consisting of a 1-hour didactic introduction followed by a 1-hour session in the gross anatomy lab with cadavers prepared by trained anatomists. Pretests and posttests were given for six modules, and post-module feedback surveys were distributed. Additional review questions testing knowledge from prior sessions were integrated into the later testing to evaluate knowledge retention. Paired analyses of pretests and postests were performed by Wilcoxon signed-rank test. Results: Ninety tests were collected and scored with 35 evaluable pretest and posttest pairs for six site-specific sessions. Posttests had significantly higher scores (median percentage correct 66% vs. 85%, p < 0.001). Of 47 evaluable paired pretest and review questions given 1-3 months after the intervention, correct responses rates were significantly higher for the later (59% vs. 86%, p = 0.008). Resident course satisfaction was high, with a median rating of 9 of 10 (IQR 8-9); with 1 being 'less effective than most educational interventions' and 10 being 'more effective than most educational interventions.' Conclusions: An integrated oncoanatomy course is associated with improved scores on post-intervention tests, sustained knowledge retention, and high resident satisfaction.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Saccharomycotina yeasts defy long-standing macroecological patterns

The Saccharomycotina yeasts (“yeasts” hereafter) are a fungal clade of scientific, economic, and medical significance. Yeasts are highly ecologically diverse, found across a broad range of environments in every biome and continent on earth; however, little is known about what rules govern the macroecology of yeast species and their range limits in the wild. Here, we trained machine learning models on 12,816 terrestrial occurrence records and 96 environmental variables to infer global distribution maps at ~1 km2 resolution for 186 yeast species (~15% of described species from 75% of orders) and to test environmental drivers of yeast biogeography and macroecology. We found that predicted yeast diversity hotspots occur in mixed montane forests in temperate climates. Diversity in vegetation type and topography were some of the greatest predictors of yeast species richness, suggesting that microhabitats and environmental clines are key to yeast diversity. We further found that range limits in yeasts are significantly influenced by carbon niche breadth and range overlap with other yeast species, with carbon specialists and species in high-diversity environments exhibiting reduced geographic ranges. Finally, yeasts contravene many long-standing macroecological principles, including the latitudinal diversity gradient, temperature-dependent species richness, and a positive relationship between latitude and range size (Rapoport’s rule). These results unveil how the environment governs the global diversity and distribution of species in the yeast subphylum. These high-resolution models of yeast species distributions will facilitate the prediction of economically relevant and emerging pathogenic species under current and future climate scenarios.

59 BASIC BIOLOGICAL SCIENCES↗

ACOUSTIC SCALE FROM THE ANGULAR POWER SPECTRA OF SDSS-III DR8 PHOTOMETRIC LUMINOUS GALAXIES

We measure the acoustic scale from the angular power spectra of the Sloan Digital Sky Survey III (SDSS-III) Data Release 8 imaging catalog that includes 872, 921 galaxies over {approx}10,000 deg{sup 2} between 0.45 < z < 0.65. The extensive spectroscopic training set of the Baryon Oscillation Spectroscopic Survey luminous galaxies allows precise estimates of the true redshift distributions of galaxies in our imaging catalog. Utilizing the redshift distribution information, we build templates and fit to the power spectra of the data, which are measured in our companion paper, to derive the location of Baryon acoustic oscillations (BAOs) while marginalizing over many free parameters to exclude nearly all of the non-BAO signal. We derive the ratio of the angular diameter distance to the sound horizon scale D{sub A} (z)/r{sub s} = 9.212{sup +0.416}{sub -{sub 0.404}} at z = 0.54, and therefore D{sub A} (z) = 1411 {+-} 65 Mpc at z = 0.54; the result is fairly independent of assumptions on the underlying cosmology. Our measurement of angular diameter distance D{sub A} (z) is 1.4{sigma} higher than what is expected for the concordance {Lambda}CDM, in accordance to the trend of other spectroscopic BAO measurements for z {approx}> 0.35. We report constraints on cosmological parameters from our measurement in combination with the WMAP7 data and the previous spectroscopic BAO measurements of SDSS and WiggleZ. We refer to our companion papers (Ho et al.; de Putter et al.) for investigations on information of the full power spectrum.

79 ASTRONOMY AND ASTROPHYSICS↗

DeepNeo: a webserver for predicting immunogenic neoantigens

Abstract Non-self epitopes, whether originated from foreign substances or somatic mutations, trigger immune responses when presented by major histocompatibility complex (MHC) molecules and recognized by T cells. Identification of immunogenically active neoepitopes has significant implications in cancer and virus medicine. However, current methods are mostly limited to predicting physical binding of mutant peptides and MHCs. We previously developed a deep-learning based model, DeepNeo, to identify immunogenic neoepitopes by capturing the structural properties of peptide-MHC pairs with T cell reactivity. Here, we upgraded our DeepNeo model with up-to-date training data. The upgraded model (DeepNeo-v2) was improved in evaluation metrics and showed prediction score distribution that better fits known neoantigen behavior. The immunogenic neoantigen prediction can be conducted at https://deepneo.net.

Kim, Jeong Yeon↗

Short-Term Probabilistic Solar Forecasting via Reinforcement Learning over ECMWF

In this paper, we present an innovative reinforcement learning approach for short-term solar forecasting, leveraging data from the European Centre for Medium-Range Weather Forecasts (ECMWF). The methodology begins with the application of the System Advisor Model (SAM) to transform various ECMWF numerical weather prediction members into predictive photovoltaic power generation. To enhance the precision of deterministic forecasting, we introduce a dynamic model selection algorithm based on Q-learning. This algorithm dynamically identifies and utilizes the most accurate ensemble member for forecasting purposes. Furthermore, we employ a support vector regression surrogate model with a Gaussian distribution to generate probabilistic forecasts, providing a holistic view of solar energy generation uncertainty. To expedite the training process and make it more practical for real-world applications, we integrate a rolling update workflow. This innovative workflow reduces the training period from months to a mere 19 days, making our method highly efficient. Numerical results of the case study show that in comparison to benchmark models, the proposed method improves the deterministic and probabilistic solar forecasting accuracy by up to 40.84% and 48.42%, respectively.

ensemble forecasting↗

A Weakly Supervised Machine Learning Procedure for Magnet Quench Diagnostics

Voltage taps remain the standard and reliable diagnostic tool for detecting quenches in superconducting magnets. However, they identify a quench only at the time of voltage rise and do not provide information on earlier physical precursors. In this work, we investigate whether acoustic emission data can reveal precursor activity that occurs before conventional voltage detection using machine learning techniques. We introduce an event selection method and a weakly supervised machine learning procedure to learn data-driven criteria for identifying potential acoustic precursors to quenches. Two Convolutional Neural Network (CNN) architectures are trained: one on acoustic sensor events from our selection procedure and one on the Fast Fourier Transforms (FFTs) of these events. Both networks are trained iteratively using confidence-weighted loss functions to associate certain subsets of training data with a precursor label. We evaluate the performance of these models by examining the time distribution of events classified as potential precursors relative to the quench onset. Results indicate that the proposed approach can possibly distinguish acoustic emission events occurring closer to the quench from earlier acoustic activity during ramping, suggesting the potential for flagging quench precursors in acoustic data.

Khan, Maira [Fermilab] (ORCID:0009000891602387)↗

The LCLStream Ecosystem for Multi-Institutional Dataset Exploration

We describe a new end-to-end experimental data streaming framework designed from the ground up to support new types of applications – AI training, extremely high-rate X-ray time-of-flight analysis, crystal structure determination with distributed processing, and custom data science applications and visualizers yet to be created. Throughout, we use design choices merging cloud microservices with traditional HPC batch execution models for security and flexibility. This project makes a unique contribution to the DOE Integrated Research Infrastructure (IRI) landscape. By creating a flexible, API-driven data request service, we address a significant need for high-speed data streaming sources for the X-ray science data analysis community. With the combination of data request API, mutual authentication web security framework, job queue system, high-rate data buffer, and complementary nature to facility infrastructure, the LCLStreamer framework has prototyped and implemented several new paradigms critical for future generation experiments.

Rogers, David [ORNL] (ORCID:0000000251871768)↗

Avatar Tools

Supervised machine learning is the process of using past experience to predict the future. "Ensembles" are a machine-learning meta-method that can be applied to most machine learning algorithms. Ensembles generally greatly improve accuracy, reduce or remove most of the design issues presented by machine learning, and are admirably suited to parallel and distributed computation. The Avatar Tools codes are an implementation of ensembles specifically for decision trees. Some features that distinguish Avatar Tools from other "ensembles for decision trees" codes are: (1) Does the bookkeeping necessary for out of bag (OOB) validation. (2) Can use OOB validation to automatically determine optimal ensemble size. (3) Provides an MPI-based parallel implementation, for distributed operation. (4) Provides convenient tools for cross-validation, to assess the accuracy provided by a training set. SAND2020-3858 M Sandia National Laboratories is a multimission laboratory managed and operated by National Technology & Engineering Solutions of Sandia, LLC, a wholly owned subsidiary of Honeywell International Inc., for the U.S. Department of Energy’s National Nuclear Security Administration under contract DE-NA0003525.

Siefert, Christopher↗

AADL: Anderson Accelerated Deep Learning

We propose a stable, distributed approach to perform AA that accelerates the convergence rate of stochastic first-order optimizers to train neural networks. Differently from previous works, we do not alter neither the scheme to perform AA nor the loss function minimized during the training. To improve robustness against stagnation, we customize general guidelines that suggest to relax the frequency of AA corrections by performing AA only at the end of an entire training epoch. To improve robustness of AA against the stochastic oscillations of first-order optimizers, we average the gradients computed on consecutive stochastic optimization updates. The improved regularity of the converging sequence and the reduced amplitude of stochastic oscillations across consecutive optimization steps allows AA to efficiently extrapolate an improved converging sequence, thereby overcoming limitations of existing approaches to perform AA on stochastic optimization.

Lupo Pasini, Massimiliano [Oak Ridge National Lab.↗

Texas Solar Collaboration DOE Rooftop Solar Challenge City of Houston Project Summary

The City of Houston is committed to achieving a sustainable solar infrastructure. In 2008, Houston was named a United States Department of Energy (DOE) Solar America City. As a Solar America City, Houston teamed with the Houston Advanced Research Center (HARC), Sandia National Laboratory (Sandia), industry, and academia, to implement the Solar Houston Initiative and prepare the Solar Houston Plan. The Solar Houston initiative was focused on identifying and overcoming barriers associated with establishing a solar infrastructure that is incorporated into the City of Houston’s overall energy plan. A broad group of Houston area stakeholders, facilitated by HARC, came together to develop a comprehensive solar plan that went beyond technology to address barriers and establish demonstrations, public outreach, education programs and other activities. The plan included proposed scopes of work in four program areas: policies, solar integration, public outreach, and education. Through the support of the DOE SunShot Rooftop Solar Challenge (RSC) grant to the Texas Collaboration (San Antonio, Austin, and Hosuton), Houston has been able to implement several of the recommendations of the Solar Houston Plan. Specific recommendations that this project was able to support include; Working with the other Texas Solar America Cities (San Antonio and Austin), to harmonize permitting and inspection processes to simplify for installers and lower soft costs of installation; Participating in state level solar policy groups such as the Texas Renewable Energy Industries Association (TRIEA); Continued coordination with the local transmission and distribution utility (CenterPoint) and retail electric providers (REP); Identification of opportunities to improve permitting and interconnection; Providing training on PV systems to City inspectors; Educating the public by continuing outreach, training, and workshops, particularly using the the Green Building Resources Center; Evaluating methods of addressing financial barriers to residential solar; Maintaining www.solarhoustontx.org; and Continuing meetings with stakeholders to get ongoing feedback from the solar community on their needs. The following sections provide a brief summary of the activities completed under each of the nine tasks specifically related to the RSC grant. Reports and other backup information are included in the appendices.

14 SOLAR ENERGY↗

Energy Savings From System Efficiency Improvements in Iowa's HVAC SAVE Program

The objective of this project is to explore the energy savings potential of maximizing furnace and distribution system performance by adjusting operating, installation, and distribution conditions. The goal of the Iowa HVAC System Adjusted and Verified Efficiency (SAVE) program is to train contractors to measure installed system efficiency as a diagnostic tool to ensure that the homeowner achieves the energy reduction target for the home rather than simply performing a tune-up on the furnace or having a replacement furnace added to a leaky system. The PARR research team first examined baseline energy usage from a sample of 48 existing homes, before any repairs or adjustments were made, to calculate an average energy savings potential and to determine which system deficiencies were prevalent. The results of the baseline study of these homes found that, on average, about 10% of the space heating energy available from the furnace was not reaching the conditioned space. In the second part of the project, the team examined a sample of 10 homes that had completed the initial evaluation for more in-depth study. For these homes, the diagnostic data shows that it is possible to deliver up to 23% more energy from the furnace to the conditioned space by doing system tune ups with or without upgrading the furnace. Replacing the furnace provides additional energy reduction. The results support the author's belief that residential heating and cooling equipment should be tested and improved as a system rather than a collection of individual components.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Stochastic Ensemble Generation for Improved Characterization of Representing Geologic Variability in a Reservoir: IBDP Case Study for SMART Initiative

This document is a poster covering the findings from activities on training data generation, specifically geologic ensemble generation. The generated geologic realizations captured the range of possible permeability distributions of the subsurface at the Illinois Basin - Decatur Project (IBDP) site, based on available well log variabilities. The percentages of reservoirs and baffles in the injection zone and a truncation of baffle permeability led to more variance in the simulations. This will be used to build forward modeling, history matching, and optimization workflows. The geologic realizations were also ranked according to dynamic measures of hydraulic diffusivity, and simulations confirm a greater contrast between the reservoir and the baffles during injection.

stochastic ensemble generation↗

Towards Scaling Law Analysis For Spatiotemporal Weather Data

Compute-optimal scaling laws are relatively well studied for NLP and CV, where objectives are typically single-step and targets are comparatively homogeneous. Weather forecasting is harder to characterize in the same framework: autoregressive rollouts compound errors over long horizons, outputs couple many physical channels with disparate scales and predictability, and globally pooled test metrics can disagree sharply with per-channel, late-lead behavior implied by short-horizon training. We extend neural scaling analysis for autoregressive weather forecasting from single-step training loss to long rollouts and per-channel metrics. We quantify (1) how prediction error is distributed across channels and how its growth rate evolves with forecast horizon, (2) if power law scaling holds for test error, relative to rollout length when error is pooled globally, and (3) how that fit varies jointly with horizon and channel for parameter, data, and compute-based scaling axes. We find strong cross-channel and cross-horizon heterogeneity: pooled scaling can look favorable while many channels degrade at late leads. We discuss implications for weighted objectives, horizon-aware curricula, and resource allocation across outputs.

Kiefer Jr, Alexander [ORNL] (ORCID:000000025398874↗

Predicting Rare Earth Element Potential in Produced and Geothermal Waters of the United States via Emergent Self-Organizing Maps

This work applies emergent self-organizing map (ESOM) techniques, a form of machine learning, in the multidimensional interpretation and prediction of rare earth element (REE) abundance in produced and geothermal waters in the United States. Visualization of the variables in the ESOM trained using the input data shows that each REE, with the exception of Eu, follows the same distribution patterns and that no single parameter appears to control their distribution. Cross-validation, using a random subsample of the starting data and only using major ions, shows that predictions are generally accurate to within an order of magnitude. Using the same approach, an abridged version of the U.S. Geological Survey Produced Waters Database, Version 2.3 (which includes both data from produced and geothermal waters) was mapped to the ESOM and predicted values were generated for samples that contained enough variables to be effectively mapped. Results show that in general, produced and geothermal waters are predicted to be enriched in REEs by an order of magnitude or more relative to seawater, with maximum predicted enrichments in excess of 1000-fold. Cartographic mapping of the resulting predictions indicates that maximum REE concentrations exceed values in seawater across the majority of geologic basins investigated and that REEs are typically spatially co-associated. The factors causing this co-association were not determined from ESOM analysis, but based on the information currently available, REE content in produced and geothermal waters is not directly controlled by lithology, reservoir temperature, or salinity.

Engle, Mark A. (ORCID:0000000152587374)↗