Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “AUGMENTATION”

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 1,441 records · Page 80
All sourcesNASA NTRSDOE OSTI
DOE OSTI2021

Changes in fire weather climatology under 1.5 °C and 2.0 °C warming

Abstract The 2015 Paris Agreement led to a number of studies that assessed the impact of the 1.5 °C and 2.0 °C increases in global temperature over preindustrial levels. However, those assessments have not actively investigated the impact of these levels of warming on fire weather. In view of a recent series of high-profile wildfire events worldwide, we access fire weather sensitivity based on a set of multi-model large ensemble climate simulations for these low-emission scenarios. The results indicate that the half degree difference between these two thresholds may lead to a significantly increased hazard of wildfire in certain parts of the world, particularly the Amazon, African savanna and Mediterranean. Although further experiments focused on human land use are needed to depict future fire activity, considering that rising temperatures are the most influential factor in augmenting the danger of fire weather, limiting global warming to 1.5 °C would alleviate some risk in these parts of the world.

Son, Rackhun (ORCID:000000023366495X)↗
DOE OSTI2022

Suppressing simulation bias in multi-modal data using transfer learning

Abstract Many problems in science and engineering require making predictions based on few observations. To build a robust predictive model, these sparse data may need to be augmented with simulated data, especially when the design space is multi-dimensional. Simulations, however, often suffer from an inherent bias. Estimation of this bias may be poorly constrained not only because of data sparsity, but also because traditional predictive models fit only one type of observed outputs, such as scalars or images, instead of all available output data modalities, which might have been acquired and simulated at great cost. To break this limitation and open up the path for multi-modal calibration, we propose to combine a novel, transfer learning technique for suppressing the bias with recent developments in deep learning, which allow building predictive models with multi-modal outputs. First, we train an initial neural network model on simulated data to learn important correlations between different output modalities and between simulation inputs and outputs. Then, the model is partially retrained, or transfer learned, to fit the experiments; a method that has never been implemented in this type of architecture. Using fewer than 10 inertial confinement fusion experiments for training, transfer learning systematically improves the simulation predictions while a simple output calibration, which we design as a baseline, makes the predictions worse. We also offer extensive cross-validation with real and carefully designed synthetic data. The method described in this paper can be applied to a wide range of problems that require transferring knowledge from simulations to the domain of experiments.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2023

A detailed study of interpretability of deep neural network based top taggers

Abstract Recent developments in the methods of explainable artificial intelligence (XAI) allow researchers to explore the inner workings of deep neural networks (DNNs), revealing crucial information about input–output relationships and realizing how data connects with machine learning models. In this paper we explore interpretability of DNN models designed to identify jets coming from top quark decay in high energy proton–proton collisions at the Large Hadron Collider. We review a subset of existing top tagger models and explore different quantitative methods to identify which features play the most important roles in identifying the top jets. We also investigate how and why feature importance varies across different XAI metrics, how correlations among features impact their explainability, and how latent space representations encode information as well as correlate with physically meaningful quantities. Our studies uncover some major pitfalls of existing XAI methods and illustrate how they can be overcome to obtain consistent and meaningful interpretation of these models. We additionally illustrate the activity of hidden layers as neural activation pattern diagrams and demonstrate how they can be used to understand how DNNs relay information across the layers and how this understanding can help to make such models significantly simpler by allowing effective model reoptimization and hyperparameter tuning. These studies not only facilitate a methodological approach to interpreting models but also unveil new insights about what these models learn. Incorporating these observations into augmented model design, we propose the particle flow interaction network model and demonstrate how interpretability-inspired model augmentation can improve top tagging performance.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Transforming microseismic clouds into near real-time visualization of the growing hydraulic fracture

SUMMARY Microseismic observations during unconventional reservoir stimulation are typically seen as a proxy for clusters of hydraulic fractures and the extent of the stimulated reservoir. Such straightforward interpretation is often misleading and fails to provide a physically reasonable image of the fracturing process. This paper demonstrates the application of a physics-based machine learning algorithm which enables a rapid and accurate fracture mapping from the microseismic data. Our training and validation data set relies on a history-matched geomechanical modelling workflow implemented in GEOS software for the Hydraulic Fracturing Test Site 1 (HFTS-1) project. For this study we augmented the simulated fracture growth through geostatistical modelling of induced seismicity, so that the synthetic microseismic catalogue matches the main statistical properties of the field observations. We formulated the problem of mapping the actual fracture in the clutter of events to parallel common video segmentation workflows: several past video frames (microseismic density snapshots) are passed through a deep convolutional network to classify whether a given voxel is associated with a fracture or intact rock. We found that for accurate fracture mapping, the network’s input and architecture must be augmented to incorporate the fluid injection parameters (pressure, rate, concentration of proppant, and location of the perforation within the cluster). The error rate for the network reached as little as 10 per cent of the fracture area, while a conventional microseismic interpretation approach yielded ∼300 per cent. Our approach also yields must faster predictions than conventional methods (minutes instead of weeks), and could enable engineers to make rapid decisions regarding engineering parameters (pumping rate, viscosity) in real time during stimulation.

58 GEOSCIENCES↗
DOE OSTI2020

Three new symbiotic crabs of the genus Glassella Campos & Wicksten, 1997 from Atlantic and Gulf of Mexico coasts of Florida, USA (Decapoda: Brachyura: Pinnotheridae)

Abstract New species of the pinnotherid crab genus GlassellaCampos & Wicksten, 1997 are described from western Atlantic waters along the east and west coasts of Florida, with the generic assignment of one being provisional. Glassella chaneyin. sp., Glassella martinin. sp., and Glassella taylorin. sp., all morphologically resemble the long-known species G. floridana (Rathbun, 1918) and overlap part of its distributional range, there occupying similar habitats and at least sometimes found with similar hosts. While genomic DNA sequencing has previously established the generic assignment of G. floridana, small sizes and suboptimal preservation histories of specimens representing the three new species have rendered all sequencing attempts unsuccessful, and thus not allowed their inclusion in molecular phylogenetic analyses. To facilitate present morphological comparisons, a rediagnosis of G. floridana was undertaken, and previously published illustrations were augmented, the latter now including figures of its previously undescribed male first gonopod and gonopodal plate. Comparisons of G. floridana to the three new species reveal striking diagnostic differences between all four species in their male first gonopods and varied configurations in the gonopodal plate or its probable homologs. These characters support the otherwise established separation of G. floridana from its congeners on the basis of its more strongly armed flexor margins of the fourth and fifth pereopods. In G. taylorin. sp., representing the smallest known member of Glassella, development of the third maxilliped and male first gonopod is so exceptional as to suggest the species may warrant eventual assignment to a separate genus.

Marine & Freshwater Biology↗
DOE OSTI2021

Optimizing a magnitude-limited spectroscopic training sample for photometric classification of supernovae

ABSTRACT In preparation for photometric classification of transients from the Legacy Survey of Space and Time (LSST) we run tests with different training data sets. Using estimates of the depth to which the 4-m Multi-Object Spectroscopic Telescope (4MOST) Time Domain Extragalactic Survey (TiDES) can classify transients, we simulate a magnitude-limited sample reaching rAB ≈ 22.5 mag. We run our simulations with the software snmachine, a photometric classification pipeline using machine learning. The machine-learning algorithms struggle to classify supernovae when the training sample is magnitude limited, in contrast to representative training samples. Classification performance noticeably improves when we combine the magnitude-limited training sample with a simulated realistic sample of faint high-redshift supernovae observed from larger spectroscopic facilities; the algorithms’ range of average area under receiver operator characteristic curve (AUC) scores over 10 runs increases from 0.547–0.628 to 0.946–0.969 and purity of the classified sample reaches 95 per cent in all runs for two of the four algorithms. By creating new, artificial light curves using the augmentation software avocado, we achieve a purity in our classified sample of 95 per cent in all 10 runs performed for all machine-learning algorithms considered. We also reach a highest average AUC score of 0.986 with the artificial neural network algorithm. Having ‘true’ faint supernovae to complement our magnitude-limited sample is a crucial requirement in optimization of a 4MOST spectroscopic sample. However, our results are a proof of concept that augmentation is also necessary to achieve the best classification results.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2021

Fast and robust all-electron density functional theory calculations in solids using orthogonalized enriched finite elements

Here, we present a computationally efficient approach to perform systematically convergent real-space all-electron Kohn-Sham density functional theory calculations for solids using an enriched finite element (FE) basis. The enriched FE basis is constructed by augmenting the classical FE basis with atom-centered numerical basis functions, comprising of atomic solutions to the Kohn-Sham problem. Notably, to improve the conditioning, we orthogonalize the enrichment functions with respect to the classical FE basis, without sacrificing the locality of the resultant basis. In addition to improved conditioning, this orthogonalization procedure also renders the overlap matrix block diagonal, greatly simplifying its inversion. Subsequently, we use a Chebyshev polynomial based filtering technique to efficiently compute the occupied eigenspace in each self-consistent field iteration. We demonstrate the accuracy and efficiency of the proposed approach on periodic unit cells and supercells. The benchmark studies show a staggering 130× speedup of the orthogonalized enriched FE basis over the classical FE basis. We also present a comparison of the orthogonalized enriched FE basis with the linearized augmented plane-wave + local orbitals basis, both in terms of accuracy and efficiency. Notably, we demonstrate that the orthogonalized enriched FE basis can handle large system sizes of ~10 000 electrons. Finally, we observe good parallel scalability of our implementation with 92% efficiency at 22× speedup for a system with 620 electrons

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗
DOE OSTI2015

Nucleon-gold collisions at 200A GeV using tagged d + Au interactions in the PHOBOS detector

Forward calorimetry in the PHOBOS detector has been used to study charged hadron production in d+Au, p+Au, and n+Au collisions at √s NN =200GeV. The forward proton calorimeter detectors are described and a procedure for determining collision centrality with these detectors is detailed. The deposition of energy by deuteron spectator nucleons in the forward calorimeters is used to identify p+Au and n+Au collisions in the data. A weighted combination of the yield of p+Au and n+Au is constructed to build a reference for Au+Au collisions that better matches the isospin composition of the gold nucleus. The p T and centrality dependence of the yield of this improved reference system is found to match that of d+Au. The shape of the charged-particle transverse momentum distribution is observed to extrapolate smoothly from p+p¯ to central d+Au as a function of the charged-particle pseudorapidity density. The asymmetry of positively and negatively charged hadron production in p+Au is compared to that of n+Au. No significant asymmetry is observed at midrapidity. In conclusion, these studies augment recent results from experiments at the CERN Large Hadron Collider and BNL Relativistic Heavy Ion Collider facilities to give a more complete description of particle production in p+A and d+A collisions, essential for the understanding the medium produced in high-energy nucleus-nucleus collisions.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2020

Calorimetry for low-energy electrons using charge and light in liquid argon

Precise calorimetric reconstruction of 5–50 MeV electrons in liquid argon time projection chambers (LArTPCs) will enable the study of astrophysical neutrinos in DUNE and could enhance the physics reach of oscillation analyses. Liquid argon scintillation light has the potential to improve energy reconstruction for low-energy electrons over charge-based measurements alone. Here we demonstrate light-augmented calorimetry for low-energy electrons in a single-phase LArTPC using a sample of Michel electrons from decays of stopping cosmic muons in the LArIAT experiment at Fermilab. Michel electron energy spectra are reconstructed using both a traditional charge-based approach as well as a more holistic approach that incorporates both charge and light. A maximum-likelihood fitter, using LArIAT’s well-tuned simulation, is developed for combining these quantities to achieve optimal energy resolution. A sample of isolated electrons is simulated to better determine the energy resolution expected for astrophysical electron-neutrino charged-current interaction final states. In LArIAT, which has very low wire noise and an average light yield of 18 pe/MeV, an energy resolution of σ/E≃9.3%/E⊕1.3% is achieved. Samples are then generated with varying wire noise levels and light yields to gauge the impact of light-augmented calorimetry in larger LArTPCs. At a charge-readout signal-to-noise of S/N≃30, for example, the energy resolution for electrons below 40 MeV is improved by ≈10%, ≈20%, and ≈40% over charge-only calorimetry for average light yields of 10 pe/MeV, 20 pe/MeV, and 100 pe/MeV, respectively.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2025

Resimulation-based self-supervised learning for pretraining physics foundation models

Self-supervised learning (SSL) is at the core of training modern large machine learning models, providing a scheme for learning powerful representations that can be used in a variety of downstream tasks. However, SSL strategies must be adapted to the type of training data and downstream tasks required. We propose resimulation-based self-supervised representation learning (RS3L), a novel simulation-based SSL strategy that employs a method of resimulation to drive data augmentation for contrastive learning in the physical sciences, particularly, in fields that rely on stochastic simulators. By intervening in the middle of the simulation process and rerunning simulation components downstream of the intervention, we generate multiple realizations of an event, thus producing a set of augmentations covering all physics-driven variations available in the simulator. Using experiments from high-energy physics, we explore how this strategy may enable the development of a foundation model; we show how RS3L pretraining enables powerful performance in downstream tasks such as discrimination of a variety of objects and uncertainty mitigation. In addition to our results, we make the RS3L dataset publicly available for further studies on how to improve SSL strategies.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

OASIS: Offsetting Active Reconstruction Attacks in Federated Learning

Federated Learning (FL) has garnered significant attention for its potential to protect user privacy while enhancing model training efficiency. For that reason, FL has found its use in various domains, from health care to industrial engineering, especially where data cannot be easily exchanged due to sensitive information or privacy laws. However, recent research has demonstrated that FL protocols can be easily compromised by active reconstruction attacks executed by dishonest servers. These attacks involve the malicious modification of global model parameters, allowing the server to obtain a verbatim copy of users' private data by inverting their gradient updates. Tackling this class of attack remains a crucial challenge due to the strong threat model. In this paper, we propose a defense mechanism, namely OASIS, based on image augmentation that effectively counteracts active reconstruction attacks while preserving model performance. We first uncover the core principle of gradient inversion that enables these attacks and theoretically identify the main conditions by which the defense can be robust regardless of the attack strategies. We then construct our defense with image augmentation showing that it can undermine the attack principle. Comprehensive evaluations demonstrate the efficacy of the defense mechanism highlighting its feasibility as a solution.

deep neural networks↗
DOE OSTI2023

Clustering High-dimensional Toxicogenomics Data with Rare Signals

Toxicogenomics studies the gene and protein activities to drug treatments or toxic exposures. As the drugs and genes are numerous, toxicogenomics data are naturally high dimensional, with dimension sizes up to millions. In addition, the distribution of toxicogenomics data is oftentimes skewed, and they contain rare but important signals representing a cell or organism’s response to toxicity. The combination of high dimension and extremely skewed distribution of toxicogenomics data makes clustering analysis extremely challenging.We present our study of clustering toxicogenomics data using classical approaches such as principal component analysis as well as deep learning approaches such as auto-encoders. Our experiments show that these approaches fail to preserve rare signals and produce high-quality clusters. We then explore augmenting matrix factorization with deep learning techniques such as attention mechanism to produce latent representations for clustering. Our technique is able to better preserve rare signals after dimensionality reduction than prior approaches. Furthermore, we combine our augmented matrix factorization with a mechanism similar to autoencoder to balance separable clusters and low regeneration errors. Our experiments demonstrate better clustering with our proposed approach.

Cong, Guojing↗
DOE OSTI2012

Multithreaded Algorithms for Maximum Matching in Bipartite Graphs

Abstract—We design, implement, and evaluate algorithms for computing a matching of maximum cardinality in a bipartite graph on multi-core and massively multithreaded computers. As computers with larger number of slower cores dominate the commodity processor market, the design of multithreaded algorithms to solve large matching problems becomes a necessity. Recent work on serial algorithms based on searching for augmenting paths for this problem have shown that their performance is sensitive to the order in which the vertices are processed for matching. In a multithreaded environment, imposing a serial order in which vertices are considered for matching would lead to loss of concurrency and performance. But this raises the question: Would parallel matching algorithms on multithreaded machines improve performance over a serial algorithm? We answer this question in the affirmative. We report efficient multithreaded implementations of two key algorithms (Hopcroft- Karp based on breadth-first-search, and Pothen-Fan based on depth-first-search) and their variants, combined with the Karp- Sipser initialization algorithm. We report extensive results and insights using three shared-memory platforms (a 48-core AMD Opteron, a 32-core Intel Nehalem, and a 128-processor Cray XMT) on a representative set of real-world and synthetic graphs. To the best of our knowledge, this is the first extensive study of augmentation-based parallel algorithms for bipartite cardinality matching.

Azad, Md Ariful↗
DOE OSTI2018

Runtime Scheduling Policies for Distributed Graph Algorithms

In this paper we explore scheduling and runtime system support for unordered distributed graph computations that rely on optimistic (speculative) execution. Performance of such algorithms is impacted by two competing trends: the higher degree of parallelism enabled by optimistic execution in turn requires substantial runtime support. To address the potentially high overhead and scheduling complexity introduced by the runtime, we investigate customizable scheduling policies that augment the scheduler of the underlying runtime to adapt it to a specific graph application. We present several implementations of Distributed Control (DC), a data-driven unordered approach with work prioritization and demonstrate that customizable scheduling policies result in the most efficient implementation, outperforming the well-known -stepping Single-Source Shortest Paths (SSSP) and Jones-Plassmann vertex-coloring algorithms. We apply two scheduling techniques, flow control and adaptive frequency of network progress, which allow application-level control over the balance of domain work and the runtime work. Experimental results show the benefit of such application-aware scheduling for irregular distributed graph algorithms.

Firoz, Jesun S.↗
DOE OSTI2026

SO(3)-invariant PCA with application to molecular data

Principal component analysis (PCA) is a fundamental technique for dimensionality reduction and denoising; however, its application to three-dimensional data with arbitrary orientations -- common in structural biology -- presents significant challenges. A naive approach requires augmenting the dataset with many rotated copies of each sample, incurring prohibitive computational costs. In this paper, we extend PCA to 3D volumetric datasets with unknown orientations by developing an efficient and principled framework for SO(3)-invariant PCA that implicitly accounts for all rotations without explicit data augmentation. By exploiting underlying algebraic structure, we demonstrate that the computation involves only the square root of the total number of covariance entries, resulting in a substantial reduction in complexity. We validate the method on real-world molecular datasets, demonstrating its effectiveness and opening up new possibilities for large-scale, high-dimensional reconstruction problems.

Fraiman, Michael [Tel Aviv Univ., Tel Aviv (Israel↗
DOE OSTI2023

Improving Frequency Stability and Minimizing Load Shedding Events by Adopting Grid-Scale Energy Storage with Grid Forming Inverters

The upward adoption trend of renewable generation not only means cleaner energy integrated into modern power grids, but also that most new generation sources are based on front-end inverter bridges, used as interfaces to most wind generation and all the solar PV. It is well known that due to their power electronics-based construction rather than rotational shafts, these sources do not provide inertia inherently, nor substantial amounts of short-circuit currents. However, stable energy such as what can be stored in energy storage systems, although interfaced via inverters, can be controlled to respond to system disturbances in a manner that emulates inertial behavior. This paper focuses on the application of such energy storage systems to augment inertia in the island of Puerto Rico. To do so, a user defined inverter model that contains grid forming capabilities and fast frequency response is modeled and integrated into the real transmission system in power flow and dynamics software. Energy storage is then connected to two selected areas so that it not only provides frequency regulation to avoid widespread load shedding events, but also other tangible benefits. The simulated cases suggest that even relatively small energy storage systems can avert load shedding events if adequately placed in the transmission network.

Grid-forming inverters, IBR, Inertia↗
DOE OSTI2015

Secure information transmission in filter bank multi-carrier spread spectrum systems

This report discusses the issue of secure information transmission for a spread-spectrum system, which in our case is Filter-Bank Multi-Carrier spread spectrum (FB-MC SS). We develop a novel method for generating a secret key to augment the security of the spread spectrum system. The proposed key generation takes advantage of the channel reciprocity exhibited between two communicating parties.We validate the key generation aspect of our system by using real-world measurements. It is found that our augmentation of strongest path cancellation (SPC) is shown to be highly effective in our measurement scenarios where the adversary’s key would otherwise be significantly correlated with the legitimate nodes. Our approach in using the proposed key generation method as a part of FB-MC SS allows for it to be fault tolerant and it is not necessarily limited to FB-MC SS or spread-spectrum system in general. However, the advantage that our approach has in the domain of spread-spectrum security is that it significantly decorrelates the adversary’s key from the authentic parties. This aspect is crucial because if the adversary’s key is similar to the legitamate parties, then the adversary obtains a sizable advantage due to the fault tolerance nature of the developed spread spectrum key.

45 MILITARY TECHNOLOGY, WEAPONRY, AND NATIONAL DEF↗
DOE OSTI2016

A Comparative Study of Distribution System Parameter Estimation Methods

In this paper, we compare two parameter estimation methods for distribution systems: residual sensitivity analysis and state-vector augmentation with a Kalman filter. These two methods were originally proposed for transmission systems, and are still the most commonly used methods for parameter estimation. Distribution systems have much lower measurement redundancy than transmission systems. Therefore, estimating parameters is much more difficult. To increase the robustness of parameter estimation, the two methods are applied with combined measurement snapshots (measurement sets taken at different points in time), so that the redundancy for computing the parameter values is increased. The advantages and disadvantages of both methods are discussed. The results of this paper show that state-vector augmentation is a better approach for parameter estimation in distribution systems. Simulation studies are done on a modified version of IEEE 13-Node Test Feeder with varying levels of measurement noise and non-zero error in the other system model parameters.

distribution system analysis↗