Improving Object Detectors by Exploiting Bounding Boxes for Augmentation Design
Not Available
97 MATHEMATICS AND COMPUTING↗
SEARCH · Engineering Papers
Results for “Network data”
Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.
Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.
Data-Driven Validation of NOvA's Convolutional Neural Network for Electron (Anti)Neutrino Selection
NOvA is a long-baseline neutrino oscillation experiment, designed to make measurements of several oscillation parameters using muon neutrino disappearance and electron neutrino appearance. It consists of two functionally equivalent detectors and utilizes the Fermilab NuMI neutrino beam. NOvA uses a convolutional neural network for particle identification of electron neutrino events with a validation process that includes several data-driven techniques. These Muon Removed studies ensure that our classifier performs the same on data as it does on simulation. In particular, Muon Removed Electron-Added studies involve selecting muon neutrino charged current events from both data and simulation and replacing the muon with a simulated electron of similar energy. For Muon Removed Bremsstrahlung and Muon Removed Decay-in-Flight studies, we remove muonic hits from cosmic muons that have either experienced Bremsstrahlung radiation or decayed in flight, producing samples of pure electromagnetic showers. Each of these electron neutrino-like samples are then evaluated by our classifier to obtain selection efficiencies. Our most recent analysis showed good agreement in the electron selection efficiency between data and simulation using these techniques. Furthermore, these cross-checks can be extended to corrections to our predicted electron neutrino signal. The impact of one such set of corrections on the overall analysis results were also evaluated in thesis.
46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
Discovering New Strong Gravitational Lenses in the DESI Legacy Imaging Surveys
We have conducted a search for new strong gravitational lensing systems in the Dark Energy Spectroscopic Instrument Legacy Imaging Surveys' Data Release 8. We use deep residual neural networks, building on previous work presented by Huang et al. These surveys together cover approximately one-third of the sky visible from the Northern Hemisphere, reaching a z-band AB magnitude of ~22.5. We compile a training sample that consists of known lensing systems as well as non-lenses in the Legacy Surveys and the Dark Energy Survey. After applying our trained neural networks to the survey data, we visually inspect and rank images with probabilities above a threshold. In this work, we present 1210 new strong lens candidates.
79 ASTRONOMY AND ASTROPHYSICS↗
DESI Strong Lens Foundry. III. Keck Spectroscopy for Strong Lenses Discovered Using Residual Neural Networks
We present spectroscopic data of strong lenses and their source galaxies using the Keck Near-Infrared Echellette Spectrometer (NIRES) and the Dark Energy Spectroscopic Instrument (DESI), providing redshifts necessary for nearly all strong-lensing applications with these systems, especially the extraction of physical parameters from lensing modeling. These strong lenses were found in the DESI Legacy Imaging Surveys using residual neural networks and followed up by our Hubble Space Telescope program, with all systems displaying unambiguous lensed arcs. With NIRES, we target eight lensed sources at redshifts difficult to measure in the optical range and determine the source redshifts for six, between z s = 1.675 and 3.332. DESI observed one of the remaining source redshifts, as well as an additional source redshift within the six systems. The two systems with nondetections by NIRES were observed for a considerably shorter 600 s at high airmass. Combining NIRES infrared spectroscopy with optical spectroscopy from our DESI Strong Lensing Secondary Target Program, these results provide the complete lens and source redshifts for six systems, a resource for refining automated strong lens searches in future deep- and wide-field imaging surveys and addressing a range of questions in astrophysics and cosmology.
Agarwal, Shrihan [University of Chicago, IL (Unite↗
Machine learning based unfolding of x-ray spectra from filter stack spectrometer data
We demonstrate the application of neural networks to perform x-ray spectra unfolding from data collected by filter stack spectrometers. A filter stack spectrometer consists of a series of filter-detector pairs, where the detectors behind each filter measure the energy deposition through each layer as photo-stimulated luminescence (PSL). The network is trained on synthetic data, assuming x-rays of energies < 1 MeV and of two different distribution functions (Maxwellian and Gaussian) and the corresponding measured PSL values obtained from five different filter stack spectrometer designs. Predicted unfolds of single distributions are near identical reproductions of the ground truth spectra, with differences in the values lower than 20% at the higher energy end in some cases. The neural network has also demonstrated robustness to experimental measurement errors of < 5% and some capability of performing unfolds for linear combinations of the two distributions without previous training. The network can perform unfolds at rates > 1 Hz, ideal for application to some high-repetition-rate systems.
47 OTHER INSTRUMENTATION↗
Distributed Resilience in High-Energy Physics Data Acquisition
Historical experience in the High-Performance Computing community teaches us that as computing systems grow, the instance of failures goes from rare to a regular occurrence. A survey of the growth in the size and complexity of Data AcQuisition (DAQ) networks in High-Energy Physics (HEP) experiments reveals that these networks are scaling exponentially, trending to a point where automated fault handling should be considered over the current manual practice, especially given the rarity of data such as in DUNE's mission to observe core-collapse supernovae. We propose a general system, DiDAQt, which is designed to provide fault detection and handling in HEP DAQs specifically, through MPI-like primitives that allow it to be added easily to existing systems. We evaluate the scalability and response time of a prototype on the FABRIC national testbed, with results indicating sufficient scalability for current and near-future DAQs as well as practical response times (under 1 microsecond decision time).
Wolosewicz, A. [IIT, Chicago]↗
Neural Network Code MATLAB
SAND2022-12606 O Neural Network Code MATLAB reads in an excel file, processes the data, trains a neural network, and tests the neural network. The code generates predictions of diffusion constants based on the data in the excel file. 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.
Allers, Joshua↗
Multiresolution convolutional autoencoders
Herein we propose a multi-resolution convolutional autoencoder (MrCAE) architecture that integrates and leverages three highly successful mathematical architectures: (i) multigrid methods, (ii) convolutional autoencoders and (iii) transfer learning. The method provides an adaptive, hierarchical architecture that capitalizes on a progressive training approach for multiscale spatio-temporal data. This framework allows for inputs across multiple scales: starting from a compact (small number of weights) network architecture and low-resolution data, our network progressively deepens and widens itself in a principled manner to encode new information in the higher resolution data based on its current performance of reconstruction. Basic transfer learning techniques are applied to ensure information learned from previous training steps can be rapidly transferred to the larger network. As a result, the network can dynamically capture different scaled features at different depths of the network. The performance gains of this adaptive multiscale architecture are illustrated through a sequence of numerical experiments on synthetic examples and real-world spatial-temporal data.
97 MATHEMATICS AND COMPUTING↗
Moving small files in a networked environment
Globally distributed computing infrastructures, such as clouds and supercomputers, are currently used to manage data that is generated with an unprecedented speed from a variety of resources. Coping with this trend, the volume of data exchanged across distant sites increases substantially. To accelerate data transfer, high-speed networks are provided to connect remote sites. Most existing data movement solutions are optimized for moving large files. However, it is still challenging to transfer a large number of small files across networks. This disadvantage not only lowers data transfer performance, but also decreases overall system utilization. Here, we identify that moving small files is mainly constrained by degraded file system throughput, not just network performance as might be suspected. We have built a data transfer pipeline model to analyze the impact of small network I/O and storage I/O on data movement. Extending one of the widely used open source data movement solutions, GridFTP, we demonstrate several appropriate engineering approaches that mitigate the bottleneck and increase data transfer efficiency. We show optimizations that improve data transfer performance more than 5 times. In comparison to existing solutions, our approaches can save a significant amount of system resources for moving lots of small files.
97 MATHEMATICS AND COMPUTING↗
Hydrological Perspectives on Integrated, Coordinated, Open, Networked (ICON) Science
Hydrologic sciences depend on data monitoring, analyses, and simulations of hydrologic processes to ensure safe, sufficient, and equal water distribution. These hydrologic data come from but are not limited to primary (lab, plot, and field experiments) and secondary sources (remote sensing, UAVs, hydrologic models) that typically follow FAIR Principles (Findable, Accessible, Interoperable, and Reusable: (go-fair.org)). Easy availability of FAIR data has become possible because the hydrology-oriented organizations have pushed the community to increase coordination of the protocols for generating data and sharing model platforms. In addition, networking at all levels has emerged with an invigorated effort to activate community science efforts that complement conventional data collection methods. However, it has become difficult to decipher various complex hydrologic processes with increasing data. Machine learning, a branch of artificial intelligence, provide more accurate and faster alternatives to better understand different hydrological processes. The Integrated, Coordinated, Open, Networked (ICON) framework provides a pathway for water users to include and respect diversity, equity, and inclusivity. In addition, ICONs support the integration of peoples with historically marginalized identities into this professional discipline of water sciences. This article comprises three independent commentaries about the state of ICON principles in hydrology and discusses the opportunities and challenges of adopting them.
(ICON) principles to address↗
RouteE-Powertrain [SWR-19-19]
RouteE-Powertrain is a tool for predicting energy usage over a set of road links. RouteE-Powertrain is a Python package that allows users to work with a set of pre-trained mesoscopic vehicle energy prediction models for a varity of vehicle types. Additionally, users can train their own models if "ground truth" energy consumption and driving data are available. RouteE-Powertrain models predict vehicle energy consumption over links in a road network, so the features considered for prediction often include traffic speeds, road grade, turns, etc. The typical user will utilize RouteE's catalog of pre-trained models. Currently, the catalog consists of light-duty vehicle models, including conventional gasoline, diesel, hybrid electric (HEV), and battery electric (BEV). These models can be applied to link-level driving data (in the form of pandas dataframes) to output energy consumption predictions. Users that wish to train new RouteE models can do so. The model training function of RouteE enables users to use their own drive-cycle data, powertrain modeling system, and road network data to train custom models. https://pypi.org/project/nrel.routee.powertrain/ pip install nrel.routee.powertrain
Holden, Jacob↗
Deep Learning At Depth: Estimating subsurface parameters from geophysical monitoring data
Geophysical imaging techniques are a non-invasive way to image the subsurface and understand both subsurface solid (rock/soil) and fluid property distributions and their evolution in time. Inversions of the geophysical data, such as Electrical Resistance Tomography (ERT) data, are solved to estimate the subsurface property distributions, such as conductivity, and many inversion techniques smooth out sharp gradients in rock or fluid property distributions. Sharp gradients in subsurface properties tend to be present in situations with complex subsurface structures, which are common in many subsurface applications. We have successfully demonstrated that it is possible to inform, or constrain, inversions with neural networks trained on synthetic data with complex subsurface structures. Initial results suggest this process may be optimizable to yield property distributions that better represent the true property distributions than the same inversion process without the neural network constraint. Future work would optimize the neural network performance for this application and then apply the synthetic-data trained neural network to real data to understand the utility and performance of this technique for real data sets.
47 OTHER INSTRUMENTATION↗
A Synoptic System for Capturing Ecosystem Control Points Across Terrestrial‐Aquatic Interfaces
Interconnected landscape features such as terrestrial‐aquatic interfaces play an outsized role in biogeochemical cycles as ecosystem control points, but it is notoriously challenging to characterize these. Here, we document a synoptic sensor network design that is (a) flexible to accommodate diverse ecosystem interfaces and gradients, (b) adaptable to monitoring and modeling needs of small and large projects alike, (c) standardized for intercomparability across sites and field experiments, and (d) adequately replicated to capture heterogeneity of each parameter monitored. This real‐time monitoring of surface water, groundwater, soil, and vegetation supports configuration and evaluation of models that span upland, wetland, open water strata, and transitions between them. We established the network at seven sites along the Chesapeake Bay and Lake Erie coastlines, including large‐scale flood manipulation experiments in both regions. A central design element is “one data logger program to rule them all”—a collection of sensor‐specific modules deployed on 40 loggers controlling ∼2,000 sensors, with the goal of streamlining maintenance, debugging, and reproducible data processing. The network generates ∼6 M observations per month, capturing system dynamics at the broad spatial and fine temporal scales needed to initialize and benchmark models; measurement frequency can be modified remotely to capture events. This network design has also revealed behaviors not represented in Earth system models, such as transient groundwater oxygen pulses. Completely documented and open source, this standardized, flexible, and efficient sensor network design can reduce barriers to understanding environmental changes and ecosystem responses across systems and scales.
Ward, Nicholas D. [Pacific Northwest National Labo↗
Time-lapse seismic inversion for CO 2 saturation with SeisCO2Net: An application to Frio-II site
Seismic monitoring of geological CO 2 storage (GCS) involves highly nonlinear seismic inversion and petrophysical inversion, making it challenging to estimate CO 2 volume efficiently and detect possible early CO 2 leakages. Deep learning (DL) using convolutional neural networks (CNNs) has shown promise in solving highly nonlinear seismic inversion problems. However, direct estimation of CO 2 plume extent/saturation from time-lapse seismic gathers using DL is still underexplored, with no reported field applications to date. The investigation of field data is primarily hindered by scarcity of field data for neural network training. Other obstacles include highly nonlinear seismic-petrophysics inverse relationship, and presence of noise in field seismic data. We introduce SeisCO2Net, a deep CNN that predicts CO 2 saturation maps directly from time-lapse full waveform shot gathers. For training, we use site-specific geological information, fluid flow physics, rock physics, and seismic modeling to generate synthetic datasets that closely resemble the CO 2 storage site. Synthetic tests show promising results, inspiring us to apply SeisCO2Net's trained weights on field data collected at Frio-II GCS site by leveraging transfer learning principles. As reference, we compare SeisCO2Net's predicted CO 2 saturation maps with results obtained from physics-based inversion. Our analyses show both methods display similar CO 2 plume shapes, reasonable CO 2 plume characteristics, and comparable saturation values. Our results suggest pre-training CNNs on physics-informed synthetic datasets and then applying the learned weights to field data is a viable approach to estimating field CO 2 saturation. This method effectively addresses the scarcity of field training data, thus encouraging the feasibility of long-term GCS monitoring.
58 GEOSCIENCES↗
Neural Networks for Nuclear Reactions in MAESTROeX
We demonstrate the use of neural networks to accelerate the reaction steps in the MAESTROeX stellar hydrodynamics code. A traditional MAESTROeX simulation uses a stiff ODE integrator for the reactions; here, we employ a ResNet architecture and describe details relating to the architecture, training, and validation of our networks. Our customized approach includes options for the form of the loss functions, a demonstration that the use of parallel neural networks leads to increased accuracy, and a description of a perturbational approach in the training step that robustifies the model. We test our approach on millimeter-scale flames using a single-step, 3-isotope network describing the first stages of carbon fusion occurring in Type Ia supernovae. We train the neural networks using simulation data from a standard MAESTROeX simulation, and show that the resulting model can be effectively applied to different flame configurations. This work lays the groundwork for more complex networks, and iterative time-integration strategies that can leverage the efficiency of the neural networks.
79 ASTRONOMY AND ASTROPHYSICS↗
PruningAMR
PruningAMR is an algorithm that reads in data stored as a neural network and outputs an adaptive mesh with values of the neural network stored at its vertices. Examples of input data include implicit neural representations (INRs) and physics-informed neural networks (PINNs). The output mesh is a grid-based adaptive mesh with larger elements for regions in which the neural network has coarse-scale variation and smaller elements for regions with fine scale variation. The goal of the software is to discretize the neural network to a mesh that faithfully captures the details encoded in the data without resorting a fine scale mesh.
Zvonek, JenniferE [Lawrence Livermore National Lab↗
Ensemble Federated Machine Learning‐Based Cybersecurity Situational Awareness in Microgrid Network
Cyber-physical microgrids are vulnerable to stealthy cybersecurity threats that disguise their actions through the exploitation of system knowledge. Such actions can severely impacts microgrids deployed in defense bases, slowing the response time of military forces during national emergencies. Several machine-learning algorithms have been proposed to detect intrusions in the grid networks; however, these traditional machine-learning algorithms lack data privacy and are subject to several adversarial machine-learning threats. This paper proposes a novel federated machine learning (FML)-based three-model framework to detect and identify stealthy data-integrity attacks while ensuring data privacy in microgrid networks. The proposed architecture uses a variational mode decomposition technique to extract derived features from incoming measurement and control datasets. The extraction of these derived features allows FML models to learn minute variations in data patterns that allow them to perform significantly better than the models trained with generic datasets consisting of raw features. Our experimental results show the efficient performance of the proposed methodology against different types of data integrity attacks while considering primary and secondary controllers in microgrids. Further, the applied FML-integrated random forest ensemble algorithm outperforms the existing generic FML algorithms during noisy and noise-free datasets with prediction latencies of only 91–134 µs per sample within the 0.1 s sampling interval and requires communication bandwidth of around ∼8.25 KB/s at the control center and ∼2.7 KB/s per edge client for communication.
24 POWER TRANSMISSION AND DISTRIBUTION↗
A Comprehensive Analysis of Real-World Accelerometer Data Quality in a Global Smartphone-based Seismic Network
The proliferation of low-cost sensors in smartphones has facilitated numerous applications; however, large-scale deployments often encounter performance issues. Sensing heterogeneity, which refers to varying data quality due to factors such as device differences and user behaviors, presents a significant challenge. In this research, we perform an extensive analysis of 3-axis accelerometer data from the MyShake system, a global seismic network utilizing smartphones. We systematically evaluate the quality of approximately 22 million 3-axis acceleration waveforms from over 81 thousand smartphone devices worldwide, using metrics that represent sampling rate and noise level. We explore a broad range of factors influencing accelerometer data quality, including smartphone and accelerometer manufacturers, phone specifications (release year, RAM, battery), geolocation, and time. Our findings indicate that multiple factors affect data quality, with accelerometer model and smartphone specifications being the most critical. In addition, we examine the influence of data quality on earthquake parameter estimation and show that removing low-quality accelerometer data enhances the accuracy of earthquake magnitude estimation.
58 GEOSCIENCES↗