Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “residual network”

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 91 records · Page 5
All sourcesNASA NTRSDOE OSTI
DOE OSTI2026

DESI Strong Lens Foundry. I. HST Observations and Modeling with GIGA-Lens

We present the Dark Energy Spectroscopic Instrument (DESI) Strong Lens Foundry. We discovered ∼3500 new strong gravitational lens candidates in the DESI Legacy Imaging Surveys using residual neural networks (ResNet). We observed a subset (51) of our candidates using the Hubble Space Telescope (HST). Except for one ambiguous case, we have confirmed 50 of the 51 candidates to be strong lenses. We also briefly describe spectroscopic follow-up observations by DESI and Keck NIRES programs. From this very rich data set, a number of studies will be carried out, including evaluating the quality of the ResNet search candidates and lens modeling. In this paper, we present our initial effort in these directions. In particular, as a demonstration, we present the lens model for DESI-165.4754−06.0423, with imaging data from HST, and lens and source redshifts from DESI and Keck NIRES, respectively. In this effort, we have applied a fully forward-modeling Bayesian approach (GIGA-Lens), using multiple GPUs, to a strong lens with HST data, and achieved statistical convergence.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2026

Strong Lens Discoveries in DESI Legacy Imaging Surveys DR10 with Two Deep Learning Architectures

Abstract We have conducted a search for strong gravitational lensing systems in the Dark Energy Spectroscopic Instrument (DESI) Legacy Imaging Surveys Data Release 10 (DR10). This paper is the fourth in a series of searches. This is the first catalog of lens candidates covering nearly the entirety of the extragalactic sky south of declination δ ≈ +32 ∘ , all observed by DECam, covering ∼14,000 deg 2 . We impose a z -band magnitude cut of <20 in AB magnitude. We deploy a residual neural network and EfficientNet as an ensemble trained on a compilation of known lensing systems and high-grade candidates as well as nonlenses in the same footprint. The predictions from these two base models are aggregated using a meta-learner. After applying our ensemble to the survey data, we exclude known candidates and systems, and use our own visual inspection portal to rank images in the top 0.01 percentile of all neural network recommendations. We have found 811 lens candidates, five of which are confirmed through Euclid Quick Data Release (Q1). These include 484 new candidates in the Legacy Surveys DR9 footprint, all parts of which have been searched for strong lenses at least once before, either by our group or others. Combining the discoveries from this work with those from the first three papers in this series (335, 1210, and 1512), we have discovered a total of 3868 new candidates in the DESI Legacy Surveys.

Inchausti, Jose Carlos [University of San Francisc↗
DOE OSTI2024

New Strong Gravitational Lenses from the DESI Legacy Imaging Surveys Data Release 9

We have conducted a search for strong gravitational lensing systems in the Dark Energy Spectroscopic Instrument (DESI) Legacy Imaging Surveys Data Release 9. This is the third paper in a series. These surveys together cover ~19,000 deg 2 visible from the Northern Hemisphere, reaching a z-band AB magnitude of ~22.5. We use a deep residual neural network, trained on a compilation of known lensing systems and high-grade candidates as well as nonlenses in the same footprint. After applying our trained neural network to the survey data, we visually inspect and rank images with probabilities above a threshold which has been chosen to balance precision and recall. We have found 1895 lens candidates, of which 1512 are identified for the first time. Combining the discoveries from this work with those from Papers I (335) and II (1210), we have discovered a total of 3057 new candidates in the Legacy Surveys.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2020

Sampling and resolution characteristics in reduced order models of shallow water equations: Intrusive vs nonintrusive

We investigate the sensitivity of reduced order models (ROMs) to training data spatial resolution as well as sampling rate. In particular, we consider proper orthogonal decomposition (POD), coupled with Galerkin projection (POD-GP), as an intrusive reduced order modeling technique. For non-intrusive ROMs, we consider two frameworks. The first is using dynamic mode decomposition (DMD), and the second is based on artificial neural networks (ANNs). For ANN, we utilized a residual deep neural network, and for DMD we have studied two versions of DMD approaches; one with hard thresholding and the other with sorted bases selection. Also, we highlight the differences between mean-subtracting the data (centering) and using the data without mean-subtraction. We tested these ROMs using a system of 2D shallow water equations for four different numerical experiments, adopting combinations of sampling rates and spatial resolutions. For these cases, we found that the DMD basis obtained with hard threshodling is sensitive to sampling rate. The sorted DMD algorithm helps to mitigate this problem and yields more stabilized and converging solution. Furthermore, we demonstrate that both DMD approaches without mean subtraction provide significantly more accurate results than DMD with mean-subtracting the data. On the other hand, POD is relatively insensitive to sampling rate and yields better representation of the flow field. Meanwhile, spatial resolution has little effect on both POD and DMD performances. Here, the numerical results reveal that an ANN on POD subspace (POD-ANN) performs remarkably better than POD-GP and DMD in capturing system dynamics, even with a small number of modes.

42 ENGINEERING↗
DOE OSTI2022

A comprehensive study of non-adaptive and residual-based adaptive sampling for physics-informed neural networks

Physics-informed neural networks (PINNs) have shown to be effective tools for solving both forward and inverse problems of partial differential equations (PDEs). PINNs embed the PDEs into the loss of the neural network using automatic differentiation, and this PDE loss is evaluated at a set of scattered spatio-temporal points (called residual points). The location and distribution of these residual points are highly important to the performance of PINNs. However, in the existing studies on PINNs, only a few simple residual point sampling methods have mainly been used. Here, we present a comprehensive study of two categories of sampling for PINNs: non-adaptive uniform sampling and adaptive nonuniform sampling. We consider six uniform sampling methods, including (1) equispaced uniform grid, (2) uniformly random sampling, (3) Latin hypercube sampling, (4) Halton sequence, (5) Hammersley sequence, and (6) Sobol sequence. We also consider a resampling strategy for uniform sampling. To improve the sampling efficiency and the accuracy of PINNs, we propose two new residual-based adaptive sampling methods: residual-based adaptive distribution (RAD) and residual-based adaptive refinement with distribution (RAR-D), which dynamically improve the distribution of residual points based on the PDE residuals during training. Hence, we have considered a total of 10 different sampling methods, including six non-adaptive uniform sampling, uniform sampling with resampling, two proposed adaptive sampling, and an existing adaptive sampling. We extensively tested the performance of these sampling methods for four forward problems and two inverse problems in many setups. Our numerical results presented in this study are summarized from more than 6000 simulations of PINNs. Here, we show that the proposed adaptive sampling methods of RAD and RAR-D significantly improve the accuracy of PINNs with fewer residual points for both forward and inverse problems. Furthermore, the results obtained in this study can also be used as a practical guideline in choosing sampling methods.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Self-adaptive weights based on balanced residual decay rate for physics-informed neural networks and deep operator networks

Physics-informed deep learning has emerged as a promising alternative for solving partial differential equations. However, for complex problems, training these networks can still be challenging, often resulting in unsatisfactory accuracy and efficiency. In this work, we demonstrate that the failure of plain physics-informed neural networks arises from the significant discrepancy in the convergence rate of residuals at different training points, where the slowest convergence rate dominates the overall solution convergence. Based on these observations, we propose a pointwise adaptive weighting method that balances the residual decay rate across different training points. The performance of our proposed adaptive weighting method is compared with current state-of-the-art adaptive weighting methods on benchmark problems for both physics-informed neural networks and physics-informed deep operator networks. In conclusion, through extensive numerical results we demonstrate that our proposed approach of balanced residual decay rates offers several advantages, including bounded weights, high prediction accuracy, fast convergence rate, low training uncertainty, low computational cost, and ease of hyperparameter tuning.

Balanced convergence rate↗
DOE OSTI2023

Pseudomonas aeruginosa Dps (PA0962) Functions in H 2 O 2 Mediated Oxidative Stress Defense and Exhibits In Vitro DNA Cleaving Activity

We report the structural, biochemical, and functional characterization of the product of gene PA0962 from Pseudomonas aeruginosa PAO1. The protein, termed Pa Dps, adopts the Dps subunit fold and oligomerizes into a nearly spherical 12-mer quaternary structure at pH 6.0 or in the presence of divalent cations at neutral pH and above. The 12-Mer Pa Dps contains two di-iron centers at the interface of each subunit dimer, coordinated by conserved His, Glu, and Asp residues. In vitro, the di-iron centers catalyze the oxidation of Fe 2+ utilizing H 2 O 2 (not O 2 ) as an oxidant, suggesting Pa Dps functions to aid P. aeruginosa to survive H 2 O 2 -mediated oxidative stress. In agreement, a P. aeruginosa Δdps mutant is significantly more susceptible to H 2 O 2 than the parent strain. The Pa Dps structure harbors a novel network of Tyr residues at the interface of each subunit dimer between the two di-iron centers, which captures radicals generated during Fe 2+ oxidation at the ferroxidase centers and forms di-tyrosine linkages, thus effectively trapping the radicals within the Dps shell. Surprisingly, incubating Pa Dps and DNA revealed unprecedented DNA cleaving activity that is independent of H 2 O 2 or O 2 but requires divalent cations and 12-mer Pa Dps.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2022

Gradient-enhanced physics-informed neural networks for forward and inverse PDE problems

Deep learning has been shown to be an effective tool in solving partial differential equations (PDEs) through physics-informed neural networks (PINNs). PINNs embed the PDE residual into the loss function of the neural network, and have been successfully employed to solve diverse forward and inverse PDE problems. However, one disadvantage of the first generation of PINNs is that they usually have limited accuracy even with many training points. Here, we propose a new method, gradient-enhanced physics-informed neural networks (gPINNs), for improving the accuracy of PINNs. gPINNs leverage gradient information of the PDE residual and embed the gradient into the loss function. We tested gPINNs extensively and demonstrated the effectiveness of gPINNs in both forward and inverse PDE problems. Our numerical results show that gPINN performs better than PINN with fewer training points. Additionally, we combined gPINN with the method of residual-based adaptive refinement (RAR), a method for improving the distribution of training points adaptively during training, to further improve the performance of gPINN, especially in PDEs with solutions that have steep gradients.

42 ENGINEERING↗
DOE OSTI2021

Behavior of an air-cooled thermosiphon during a non-air gas ingress event

Here, this study investigates the transient response of an air-cooled thermosiphon subjected to a sudden non-air gas ingress event. Results presented are from experimental testing conducted on a large-scale thermal hydraulic facility that examines heat removal performance of the Reactor Cavity Cooling System (RCCS) concept, a passive safety system for advanced nuclear reactors. Relying on buoyancy driven natural circulation flow, these systems feature a series of riser standpipes and coupled chimney network that provide a pathway for heat rejection to the atmosphere. In this work, the facility was modified to allow a transition of the draft intake from normal ambient air, to draft intake from an open-top volume containing high purity argon. Testing began by establishing normal operation and allowing the facility to reach steady-state thermal hydraulic flow conditions with natural air draft. The transitioned sequence was then initiated which simultaneously changed the inlet boundary from open air to a pathway from the quiescent argon volume. This event caused 1,200 cu-feet of the heavy gas, twice the internal volume of total facility flow path, to be drawn into the inlet plenum and ingress into the heated riser standpipes. With the upper chimney network still containing residual air, there was insufficient density difference to maintain buoyancy driven natural circulation. After a period of only 90 s past the ingress event, the facility experienced complete flow stagnation before entering an extended period of severely degraded system flow. Due to the cessation of bulk fluid movement and subsequent failure of its heat removal function, fluid and structural temperatures began to rise sharply. Re-circulation patterns developed within the multiple parallel riser standpipes, where hot gas near the outlets was observed to travel downward and re-enter the inlet of adjacent channels. After approximately 18-minutes, fluid temperatures and their associated density difference rose to a level sufficient to allow reestablishment of buoyancy driven system flow, and ultimately, recovery of facility operation to normal behavior.

42 ENGINEERING↗
DOE OSTI2022

Use of machine learning for a helium line intensity ratio method in Magnum-PSI

Optical emission spectroscopy (OES) of helium (He) line intensities has been used to measure the electron density, ne, and temperature, Te, in various plasma devices. In this study, a neural network with five hidden layers is introduced to model the relation between the OES data and ne/Te from laser Thomson scattering in the linear plasma device Magnum-PSI and compared to multiple regression analysis. It is shown that the neural network reduces the residual errors of prediction values (ne and Te) less than half those of the multiple regression analysis. We checked two different data splitting methods for training and validation data, i.e., with and without considering the unit of discharge. A comparison of the splitting methods suggests that the residual error will decrease to ~10% even for a new discharge data when accumulating a sufficient data set.

Kajita, Shin↗
DOE OSTI2020

A Moist Physics Parameterization Based on Deep Learning

Abstract Current moist physics parameterization schemes in general circulation models (GCMs) are the main source of biases in simulated precipitation and atmospheric circulation. Recent advances in machine learning make it possible to explore data‐driven approaches to developing parameterization for moist physics processes such as convection and clouds. This study aims to develop a new moist physics parameterization scheme based on deep learning. We use a residual convolutional neural network (ResNet) for this purpose. It is trained with 1‐year simulation from a superparameterized GCM, SPCAM. An independent year of SPCAM simulation is used for evaluation. In the design of the neural network, referred to as ResCu, the moist static energy conservation during moist processes is considered. In addition, the past history of the atmospheric states, convection, and clouds is also considered. The predicted variables from the neural network are GCM grid‐scale heating and drying rates by convection and clouds, and cloud liquid and ice water contents. Precipitation is derived from predicted moisture tendency. In the independent data test, ResCu can accurately reproduce the SPCAM simulation in both time mean and temporal variance. Comparison with other neural networks demonstrates the superior performance of ResNet architecture. ResCu is further tested in a single‐column model for both continental midlatitude warm season convection and tropical monsoonal convection. In both cases, it simulates the timing and intensity of convective events well. In the prognostic test of tropical convection case, the simulated temperature and moisture biases with ResCu are smaller than those using conventional convection and cloud parameterizations.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

DASEventNet: AI‐Based Microseismic Detection on Distributed Acoustic Sensing Data From the Utah FORGE Well 16A (78)‐32 Hydraulic Stimulation

Abstract Distributed acoustic sensing (DAS) has emerged as a promising seismic technology for monitoring microearthquakes (MEQs) with high spatial resolution. Efficient algorithms are needed for processing large DAS data volumes. This study introduces a deep learning (DL) model based on a Residual Convolutional Neural Network (ResNet) for detecting MEQs using DAS data, named as DASEventNet. The test data were collected from the Utah FORGE 16A (78)‐32 hydraulic stimulation experiments conducted in April 2022. The DASEventNet model achieves a remarkable accuracy of 100% when discriminating MEQs from noise in the raw test set of 260 examples. Surprisingly, the model identified weak MEQ signatures that have been manually categorized as noise. The decision‐making process with the model is decoded by the classic activation map, which illuminates learning features of the DASEventNet model. These features provide clear illustrations of weak MEQs and varied noise types. Finally, we apply the trained model to the entire period (∼7 days) of continuous DAS recordings and find that it discovers >5,700 new MEQs, previously unregistered in the public Silixa DAS catalog. The DASEventNet model significantly outperforms the traditional seismic method Short‐Term Average/Long‐Term Average (STA/LTA), which detected only 1,307 MEQs. The DASEventNet detection threshold is M w −1.80 compared to the minimum magnitude of M w −1.14 detected by STA/LTA. The spatiotemporal distribution of the newly identified MEQs defines an extensive stimulation zone and more accurately characterizes fracture geometry. Our results highlight the potential of DL for long‐term, real‐time microseismic monitoring that can improve enhanced geothermal systems and other activities that include subsurface hydraulic fracturing.

15 GEOTHERMAL ENERGY↗
DOE OSTI2024

Structural insights reveal interplay between LAG-3 homodimerization, ligand binding, and function

Lymphocyte activation gene-3 (LAG-3) is an inhibitory receptor expressed on activated T cells and an emerging immunotherapy target. Domain 1 (D1) of LAG-3, which has been purported to directly interact with major histocompatibility complex class II (MHCII) and fibrinogen-like protein 1 (FGL1), has been the major focus for the development of therapeutic antibodies that inhibit LAG-3 receptor-ligand interactions and restore T cell function. Here, we present a high-resolution structure of glycosylated mouse LAG-3 ectodomain, identifying that cis-homodimerization, mediated through a network of hydrophobic residues within domain 2 (D2), is critically required for LAG-3 function. Additionally, we found a previously unidentified key protein-glycan interaction in the dimer interface that affects the spatial orientation of the neighboring D1 domain. Mutation of LAG-3 D2 residues reduced dimer formation, dramatically abolished LAG-3 binding to both MHCII and FGL1 ligands, and consequentially inhibited the role of LAG-3 in suppressing T cell responses. Intriguingly, we showed that antibodies directed against D1, D2, and D3 domains are all capable of blocking LAG-3 dimer formation and MHCII and FGL-1 ligand binding, suggesting a potential allosteric model of LAG-3 function tightly regulated by dimerization. Furthermore, our work reveals unique epitopes, in addition to D1, that can be targeted for immunotherapy of cancer and other human diseases.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2021

Attend and Decode: 4D fMRI Task State Decoding Using Attention Models

Source code for Brain Attend and Decode paper. Functional magnetic resonance imaging (fMRI) is a neuroimaging modality that captures the blood oxygen level in a subject's brain while the subject either rests or performs a variety of functional tasks under different conditions. Given fMRI data, the problem of inferring the task, known as task state decoding, is challenging due to the high dimensionality (hundreds of million sampling points per datum) and complex spatio-temporal blood flow patterns inherent in the data. In this work, we propose to tackle the fMRI task state decoding problem by casting it as a 4D spatiotemporal classification problem. We present a novel architecture called Brain Attend and Decode (BAnD), that uses residual convolutional neural networks for spatial feature extraction and self-attention mechanisms for temporal modeling. We achieve significant performance gain compared to previous works on a 7-task benchmark from the large-scale Human Connectome Project-Young Adult (HCP-YA) dataset. We also investigate the transferability of BAnD's extracted features on unseen HCP tasks, either by freezing the spatial feature extraction layers and retraining the temporal model, or finetuning the entire model. The pre-trained features from BAnD are useful on similar tasks while finetuning them yields competitive results on unseen tasks/conditions.

Ng, BrendaM.↗
DOE OSTI2024

RhizoNet: semantic segmentation of plant roots using CNN (RhizoNet) v0.0.1

RhizoNet is designed for the semantic segmentation of plant root scans, utilizing a sophisticated deep learning network known as Residual Unet. It specializes in processing color images of plants cultivated in a hydroponic EcoFAB system, captured using an Epson scanner. The core of the algorithm is based on Residual U-nets, which significantly improve prediction accuracy. This is achieved through the implementation of a convex hull operation, which effectively delineates the primary root component by leveraging spatio-temporal image data. This enables researchers to accurately assess predicted biomass and monitor plant growth over time.

Ushizima, Daniela↗
DOE OSTI2026

Gravitational Lenses in UNIONS and Euclid (GLUE). I. A Search for Strong Gravitational Lenses in UNIONS with Subaru, CFHT, and Pan-STARRS Data

We present the results of our pipeline for discovering strong gravitational lenses in the ongoing Ultraviolet Near-Infrared Optical Northern Survey (UNIONS). We successfully train a deep residual convolutional neural network based on CMU-Deeplens architecture, which is designed to detect strong lenses in ground-based imaging surveys. We train on images of real strong lenses and deploy on a sample of 8 million galaxies in areas with full coverage in the g, r, and i filters—the first multiband search for strong gravitational lenses in UNIONS. Following human inspection and grading, we report the discovery of a total of 1346 new strong-lens candidates, of which 146 are Grade A, 199 are Grade B, and 1001 are Grade C. Of these candidates, 283 have lens galaxy spectroscopic redshifts from the Sloan Digital Sky Survey, and an additional 297 have them from the Dark Energy Spectroscopic Instrument Data Release 1. We find 15 of these systems display evidence of both lens and source galaxy redshifts in spectral superposition. We also report the spectroscopic confirmation of seven lensed sources in high-quality systems, all with z > 2.1, using the Keck Near Infrared Echellette Spectrograph and the Gemini Near-Infrared Spectrograph.

Storfer, Christopher J. [University of Hawaii, Hon↗