Search NASA⌕ Search

SEARCH · Search NASA

Results for “neural network enrichment”

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 37 records · Page 2
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Altered cortical thickness-based structural covariance networks in type 2 diabetes mellitus

Cognitive impairment is a common complication of type 2 diabetes mellitus (T2DM), and early cognitive dysfunction may be associated with abnormal changes in the cerebral cortex. This retrospective study aimed to investigate the cortical thickness-based structural topological network changes in T2DM patients without mild cognitive impairment (MCI). Fifty-six T2DM patients and 59 healthy controls underwent neuropsychological assessments and sagittal 3-dimensional T1-weighted structural magnetic resonance imaging. Then, we combined cortical thickness-based assessments with graph theoretical analysis to explore the abnormalities in structural covariance networks in T2DM patients. Correlation analyses were performed to investigate the relationship between the altered topological parameters and cognitive/clinical variables. T2DM patients exhibited significantly lower clustering coefficient (C) and local efficiency (Elocal) values and showed nodal property disorders in the occipital cortical, inferior temporal, and inferior frontal regions, the precuneus, and the precentral and insular gyri. Moreover, the structural topological network changes in multiple nodes were correlated with the findings of neuropsychological tests in T2DM patients. Thus, while T2DM patients without MCI showed a relatively normal global network, the local topological organization of the structural network was disordered. Moreover, the impaired ventral visual pathway may be involved in the neural mechanism of visual cognitive impairment in T2DM patients. This study enriched the characteristics of gray matter structure changes in early cognitive dysfunction in T2DM patients.

Huang, Yang↗
DOE OSTI2023

Predicting Failure Using Deep Learning SAND Report

Accurate prediction of ductile failure is critical to Sandia’s NW mission, but the models are computationally heavy. The costs of including high-fidelity physics and mechanics that are germane to the failure mechanisms are often too burdensome for analysts either because of the person-hours it requires to input them or because of the additional computational time, or both. In an effort to deliver analysts a tool for representing these phenomena with minimal impact to their existing workflow, our project sought to develop modern data-driven methods that would add microstructural information to business-as-usual calculations and expedite failure predictions. The goal is a tool that receives as input a structural model with stress and strain fields, as well as a machine-learned model, and output predictions of structural response in time, including failure. As such, our project spent substantial time performing high-fidelity, three-dimensional experiments to elucidate materials mechanisms of void nucleation and evolution. We developed crystal-plasticity finite-element models from the experimental observations to enrich the findings with fields not readily measured. We developed engineering length-scale simulations of replicated test specimens to understand how the engineering fields evolve in the presence of fine-scale defects. Finally, we developed deep learning convolutional neural networks, and graph-based neural networks to encode the findings of the experiments and simulations and make forward predictions in time for structural performance. This project demonstrated the power of data-driven methods for model development, which have the potential to vastly increase both the accuracy and speed of failure predictions. These benefits and the methods necessary to develop them are highlighted in this report. However, many challenges remain to implementing these in real applications, and these are discussed along with potential methods for overcoming them.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Data-driven based coordinated smart inverter control for distributed energy resources

Smart inverters (SI) for distributed energy resources (DER) are becoming popular since they have the ability to stabilize as well as restore the voltage and frequency of power systems. Aiming at establishing the mathematical models combined with SI control methods, multiple optimization methods are developed. However, the computational complexity of solving such a mathematical model with various uncertainties limits the real-time application of the SI control. To conquer this challenge, a data-driven-based SI control approach is developed to achieve coordinated control in the high penetration DER system. First, an optimization problem for maximizing the active power generation and minimizing the power loss is designed using the Volt/VAR control. To reduce the time consumption, the recurrent neural network (RNN) is proposed to model the relationship between the uncertainties and control actions during the offline site. The RNN with different sub-structures such as the long short-term memory cell and gated recurrent unit cell are included to enrich the diversity of features. In the last stage, different experiment comparisons, including multiple uncertainties maps and stateof- art machine learning methods, are conducted to verify the effectiveness of the proposed method based on the IEEE 123 bus power system. The results demonstrate that the proposed method can effectively achieve a rapid and coordinated control with a lower error rate.

Qiu, Wei↗
DOE OSTI2023

Regional Heatwave Prediction Using Graph Neural Network and Weather Station Data

Abstract Heatwaves lead to catastrophic consequences on public health and the economy. Accurate and timely predictions of regional heatwaves can improve climate preparedness and foster decision‐making to alleviate the burdens due to climate change. In this paper, we propose a heatwave prediction algorithm based on a novel deep learning model, that is, Graph Neural Network (GNN). This new GNN framework can provide real time warnings of the sudden occurrence of regional heatwaves with high accuracy at lower costs of computation and data collection. In addition, its interpretable structure unravels the spatiotemporal patterns of regional heatwaves and helps to enrich our understanding of the general climate dynamics and the causal influences between locations. The proposed GNN framework can be applied for the detection and prediction of other extreme or compound climate events, which calls for future studies.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2021

Resampling and data augmentation for short-term PV output prediction based on an imbalanced sky images dataset using convolutional neural networks

Integrating photovoltaics (PV) into electricity grids is challenged by potentially large fluctuations in power generation. In recent years, sky image-based PV output prediction using convolutional neural networks (CNNs) has emerged as a promising approach to forecasting fluctuations. A key challenge is imbalanced sky image datasets: because of the geography of solar PV system installations, sky image datasets are often rich in sunny condition data but deficient in cloudy condition data. This imbalance contrasts with the fact that model errors are dominated by cloudy condition performance. In this study, we attempt to remedy this by exploring the enrichment and augmentation of an imbalanced sky images dataset for two PV output prediction tasks: nowcasting (predicting concurrent PV output) and forecasting (predicting 15-minute-ahead future PV output). We empirically examine the efficacy of using different resampling and data augmentation approaches to create a rebalanced dataset for model development. A three-stage greedy search is used to determine the optimal resampling approach, data augmentation techniques and over-sampling rate. The results show that for the nowcast problem, resampling and data augmentation can effectively enhance the model performance, reducing overall root mean squared error (RMSE) by an average of 4%, or a 15 std. (standard deviation) of improvement compared to the variability of the baseline model. In contrast, the treatment RMSE for the forecast problem nearly always overlaps the baseline performance at the ± 2 std. level. The optimal resampling approach expands on the original dataset by over-sampling the minority cloudy data, with the best results from large over-sampling rate (e.g., 4 ~ 6 times over-sampling of cloudy images).

14 SOLAR ENERGY↗
DOE OSTI2020

Solving differential equations using deep neural networks

Recent work on solving partial differential equations (PDEs) with deep neural networks (DNNs) is presented. The paper reviews and extends some of these methods while carefully analyzing a fundamental feature in numerical PDEs and nonlinear analysis: irregular solutions. First, the Sod shock tube solution to the compressible Euler equations is discussed and analyzed. This analysis includes a comparison of a DNN-based approach with conventional finite element and finite volume methods, and demonstrates that the DNN is competitive in terms of degrees of freedom required for a given accuracy. Further, the DNN-based approach is extended to consider performance improvements and simultaneous parameter space exploration. Next, a shock solution to compressible magnetohydrodynamics (MHD) is solved for, and used in a scenario where experimental data is utilized to enhance a PDE system that is a priori insufficient to validate against the observed/experimental data. This is accomplished by enriching the model PDE system with source terms that are then inferred via supervised training with synthetic experimental data. The resulting DNN framework for PDEs enables straightforward system prototyping and natural integration of large data sets (be they synthetic or experimental), all while simultaneously enabling single-pass exploration of an entire parameter space.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2026

NuGraph2 with context-aware inputs: physics-inspired improvements in semantic segmentation

Graph neural networks have recently shown strong promise for event reconstruction tasks in Liquid Argon Time Projection Chambers, yet their performance remains limited for underrepresented classes of particles, such as Michel electrons. In this work, we investigate physics-informed strategies to improve semantic segmentation within the NuGraph2 architecture. We explore three complementary approaches: (i) enriching the input representation with context-aware features derived from detector geometry and track continuity, (ii) introducing auxiliary decoders to capture class-level correlations, and (iii) incorporating energy-based regularization terms motivated by Michel electron energy distributions. Experiments on MicroBooNE public datasets show that physics-inspired feature augmentation yields the largest gains, particularly boosting Michel electron precision and recall by disentangling overlapping latent space regions. In contrast, auxiliary decoders and energy-regularization terms provided limited improvements, partly due to the hit-level nature of NuGraph2, which lacks explicit particle- or event-level representations. Our findings highlight that embedding physics context directly into node-level inputs is more effective than imposing task-specific auxiliary losses, and suggest that future hierarchical architectures such as NuGraph3, with explicit particle- and event-level reasoning, will provide a more natural setting for advanced decoders and physics-based regularization. The code for this work is publicly available on Github at https://github.com/vitorgrizzi/nugraph_phys/tree/main_phys.

Other Experiments↗
DOE OSTI2025

SOX2-driven enhancer landscape defines the transcriptional architecture of retinogenesis

Retinal neurogenesis is mediated by the coordinated activities of a complex gene regulatory network (GRN) of transcription factors (TFs) in multipotent retinal progenitor cells (RPCs). How this GRN mechanistically guides neural competence remains poorly understood. In this study, we present integrated transcriptional, genetic and genomic analyses to uncover the regulatory mechanisms of SOX2, a key factor in establishing neural identity in RPCs. We show that SOX2 is preferentially enriched in the RPC-specific enhancer landscape associated with essential regulators of retinogenesis. Disruption of SOX2 expression impairs retinogenesis, marked by a selective loss of enhancer activity near genes essential for RPC proliferation and lineage specification. We identified the RPC transcription factor VSX2 as a binding partner for SOX2 and, together, SOX2 and VSX2 co-target a core, retina-specific chromatin repertoire characterized by enhanced TF binding and robust chromatin accessibility. This cooperative binding establishes a shared SOX2-VSX2 transcriptional code that promotes the expression of crucial regulators of neurogenesis while repressing the acquisition of alternative lineage cell fate. Our data illuminate fundamental biological insights on how transcription factors act in concert to drive chromatin-based genetic programs underlying retinal neural identity.

Chromatin↗
DOE OSTI2021

Skip-Connected Self-Recurrent Spiking Neural Networks with Joint Intrinsic Parameter and Synaptic Weight Training

As an important class of spiking neural networks (SNNs), recurrent spiking neural networks (RSNNs) possess great computational power and have been widely used for processing sequential data like audio and text. However, most RSNNs suffer from two problems. 1. Due to the lack of architectural guidance, random recurrent connectivity is often adopted, which does not guarantee good performance. 2. Training of RSNNs is in general challenging, bottlenecking achievable model accuracy. To address these problems, we propose a new type of RSNNs called Skip-Connected Self-Recurrent SNNs (ScSr-SNNs). Recurrence in ScSr-SNNs is introduced in a stereotyped manner by adding self-recurrent connections to spiking neurons. The SNNs with self-recurrent connections can realize recurrent behaviors similar to those of more complex RSNNs while the error gradients can be more straightforwardly calculated due to the mostly feedforward nature of the network. The network dynamics is enriched by skip connections between nonadjacent layers. Moreover, we propose a new backpropagation (BP) method called backpropagated intrinsic plasticity (BIP) to further boost the performance of ScSr-SNNs by training intrinsic model parameters. Unlike standard intrinsic plasticity rules that adjust the neuron's intrinsic parameters according to neuronal activity, the proposed BIP method optimizes intrinsic parameters based on the backpropagated error gradient of a well-defined global loss function in addition to synaptic weight training. Here, based on challenging speech, neuromorphic speech, and neuromorphic image datasets, the proposed ScSr-SNNs can boost performance by up to 2.85% compared with other types of RSNNs trained by state-of-the-art BP methods.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Improve the Search of Very Metal-poor Stars Using the Deep Learning Method

Very metal-poor (VMP) stars have [Fe/H] < -2.0 dex. They are among the oldest stars in the universe, and their unique metallicity can help explore the enrichment mechanism and evolutionary history of the chemical elements of stars in the early universe. However, most current stellar parameter estimation methods do not perform well in determining the stellar parameters of VMP stars, which limits our ability to discover and exploit the properties of VMP stars. In this study, we propose a new model based on a convolutional neural network to determine the stellar atmospheric parameters of VMP stars. We tested our model on the LAMOST spectra; our model can determine the effective temperature (T {sub eff}), surface gravity (log g), metallicity ([Fe/H]), and carbon abundance ([C/Fe]) of the LAMOST spectra with precisions σ(T {sub eff}) = 134.82 K, σ(log g) = 0.33 dex, σ ([Fe/H]) = 0.20 dex, and σ([C/Fe]) = 0.35 dex. Furthermore, our model can distinguish VMP stars from normal stars with an accuracy of 88.65%. We also compared this model with other widely used methods, and found that this method performs better than other methods. It can be applied to the stellar parameter pipelines of upcoming large surveys such as 4MOST, WEAVES, and MOONS to search for VMP stars and identify carbon-enhanced metal-poor stars.

36 MATERIALS SCIENCE↗
DOE OSTI2025

Uncovering Structure–Conductivity Relationships in Anion Exchange Membranes (AEMs) Using Interpretable Machine Learning

Anion exchange membranes (AEMs) play a vital role in the performance of water electrolyzers and fuel cells, yet their discovery and optimization remain challenging due to the complexity of structure–property relationships. In this study, we introduce a machine learning framework that leverages conditional graph neural networks (cGNNs) and descriptor-based models and a hybrid graph neural network (HGARE) to predict and interpret ionic conductivity. The descriptor-based pipeline employs principal component analysis (PCA), ablation, and SHAP analysis to identify factors governing anion conductivity, revealing electronic, topological, and compositional descriptors as key contributors. Beyond prediction, dimensionality reduction and clustering are performed by employing t-SNE and KMeans as well as SOM, which reveal distinct membranes clusters, some of which were enriched with high anion conductivity. Among graph-based approaches, the graph convolutional (GCN) achieved strong predictive performance, while the Hybrid Graph Autoencoder-Regressor Ensemble (HGARE) achieved the highest accuracy. Additionally, atom-level saliency maps from GCN provide spatial explanations for conductive behavior, revealing the importance of polarizable and flexible regions. This work contributes to the accelerated and data-driven design of high-performance AEMs.

Naghshnejad, Pegah [Department of Chemical Enginee↗
DOE OSTI2022

Data reduction in deterministic neutron transport calculations using machine learning

Neutron cross section matrices for fission and scattering data are required for each material, temperature, and enrichment level to calculate the neutron transport equation accurately. Here, this information can be a limiting factor when using the multigroup discrete ordinates (S N ) method when the number of energy groups is large. Machine Learning (ML) can be used to replace the need for the cross section matrices by reproducing the function that maps the scalar flux to the scattering and fission sources. Through the use of autoencoders and Deep Jointly-Informed Neural Networks (DJINN), the data storage requirements are reduced by 94% of the original data for a 618 group problem. This is accomplished while preserving the scalar flux, maintaining generality, and decreasing wall clock times.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2023

Search for a light charged Higgs boson in t → H±b decays, with H± → cb, in the lepton+jets final state in proton-proton collisions at $\sqrt{s}$ = 13 TeV with the ATLAS detector

A search for a charged Higgs boson, H ± , produced in top-quark decays, t → H ± b, is presented. The search targets H ± decays into a bottom and a charm quark, H ± → cb. The analysis focuses on a selection enriched in top-quark pair production, where one top quark decays into a leptonically decaying W boson and a bottom quark, and the other top quark decays into a charged Higgs boson and a bottom quark. This topology leads to a lepton-plus-jets final state, characterised by an isolated electron or muon and at least four jets. The search exploits the high multiplicity of jets containing b-hadrons, and deploys a neural network classifier that uses the kinematic differences between the signal and the background. The search uses a dataset of proton-proton collisions collected at a centre-of-mass energy $\sqrt{s}$ = 13 TeV between 2015 and 2018 with the ATLAS detector at CERN’s Large Hadron Collider, amounting to an integrated luminosity of 139 fb -1 . Observed (expected) 95% confidence-level upper limits between 0.15% (0.09%) and 0.42% (0.25%) are derived for the product of branching fractions $\mathscr{B}$ (t → H ± b) × $\mathscr{B}$(H ± → cb) for charged Higgs boson masses between 60 and 160 GeV, assuming the SM production of the top-quark pairs.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2023

Applying Physics-Informed Neural Networks to Solve Navier–Stokes Equations for Laminar Flow around a Particle

In recent years, Physics-Informed Neural Networks (PINNs) have drawn great interest among researchers as a tool to solve computational physics problems. Unlike conventional neural networks, which are black-box models that “blindly” establish a correlation between input and output variables using a large quantity of labeled data, PINNs directly embed physical laws (primarily partial differential equations) within the loss function of neural networks. By minimizing the loss function, this approach allows the output variables to automatically satisfy physical equations without the need for labeled data. The Navier–Stokes equation is one of the most classic governing equations in thermal fluid engineering. This study constructs a PINN to solve the Navier–Stokes equations for a 2D incompressible laminar flow problem. Flows passing around a 2D circular particle are chosen as the benchmark case, and an elliptical particle is also examined to enrich the research. The velocity and pressure fields are predicted by the PINNs, and the results are compared with those derived from Computational Fluid Dynamics (CFD). Additionally, the particle drag force coefficient is calculated to quantify the discrepancy in the results of the PINNs as compared to CFD outcomes. The drag coefficient maintained an error within 10% across all test scenarios.

Hu, Beichao (ORCID:0009000163215151)↗
DOE OSTI2022

A Review on the State of the Art of Machine Learning and Satellite Imaging: Detecting Scene Changes in Selected Nuclear Fuel Cycle Datasets

The timely detection of clandestine nuclear facilities is one of the greatest challenges faced by the International Atomic Energy Agency’s (IAEA). Idaho National Laboratory is currently applying machine learning (ML) to existing satellite imagery (SI) datasets to find facilities within the nuclear fuel life cycle, with primary focus placed on identifying critical predecessor (i.e., fuel fabrication and fuel enrichment) and successor (i.e., nuclear power plants) facilities. This could provide a satellite image methodology that the IAEA could leverage to discover clandestine facilities. The work presented in this paper describes the evolution of a workflow developed by this team for object detection related to critical infrastructure by expanding that workflow for the purpose of identifying nuclear fuel cycle components and automating dependency assessments. This will be done using two methods housed within a single pipeline. The first method involves implementing a DenseNet161 convolutional neural network to classify the images and explain the results using Local Interpretable Model-Agnostic Explanations (LIME). The second method implements You Only Look Once version 5 (YoloV5), to detect objects within images, provide a probability for the detection, and provide a bounding box that corresponds to the object of interest. The results of this work are anticipated to provide a clear picture of this portion of the nuclear fuel cycle and perform as a stand-alone tool for image assessment that can be expanded to additional fuel cycle components and implemented in international safeguards and national security domains. This capability addresses the IAEA’s need to detect undeclared nuclear materials and activities within a state while encompassing the entire nuclear fuel cycle.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

Heterotrimeric G‐protein, Gi1, is involved in the regulation of proliferation, neuronal migration, and dendrite morphology during cortical development in vivo

Abstract Heterotrimeric G‐proteins are composed of α, β, and γ subunits, and function as signal transducers. Critical roles of the α‐subunits of Gi/o family heterotrimeric G‐proteins, Gαi2, and Gαo1, have so far been reported in brain development and neurodevelopmental disorders. In this study, we tried to clarify the role of Gαi1, α‐subunit of another Gi/o family member Gi1, during corticogenesis, based on the recent identification of its gene abnormalities in neurodevelopmental disorders. In western blot analyses, Gαi1 was found to be expressed in mouse brain in a developmental stage‐dependent manner. Morphological analyses revealed that Gαi1 was broadly distributed in cerebral cortex with relatively high expression in the ventricular zone (VZ) at embryonic day (E) 14. Meanwhile, Gαi1 was enriched in membrane area of yet unidentified early mitotic cells in the VZ and the marginal zone at E14. Acute knockdown of Gαi1 with in utero electroporation in cerebral cortex caused cell cycle elongation of the neural progenitor cells and promoted their cell cycle exit. Gαi1‐deficient cortical neurons also exhibited delayed radial migration during corticogenesis, with abnormally elongated leading processes and hampered nucleokinesis. In addition, silencing of Gαi1 prevented basal dendrite development. The migration and dendritic phenotypes were at least partially rescued by an RNAi‐resistant version of Gαi1. Collectively, these results strongly suggest a crucial role of Gi1 in cortical development, and disturbance of its function may cause deficits in synaptic network formation, leading to neurodevelopmental disorders. image

Hamada, Nanako↗
DOE OSTI2020

Genomic analyses implicate noncoding de novo variants in congenital heart disease

A genetic etiology is identified for one-third of patients with congenital heart disease (CHD), with 8% of cases attributable to coding de novo variants (DNVs). To assess the contribution of noncoding DNVs to CHD, we compared genome sequences from 749 CHD probands and their parents with those from 1,611 unaffected trios. Neural network prediction of noncoding DNV transcriptional impact identified a burden of DNVs in individuals with CHD (n = 2,238 DNVs) compared to controls (n = 4,177; P = 8.7 × 10 -4 ). Independent analyses of enhancers showed an excess of DNVs in associated genes (27 genes versus 3.7 expected, P = 1 × 10 -5 ). We observed significant overlap between these transcription-based approaches (odds ratio (OR) = 2.5, 95% confidence interval (CI) 1.1-5.0, P = 5.4 × 10 -3 ). CHD DNVs altered transcription levels in 5 of 31 enhancers assayed. Finally, we observed a DNV burden in RNA-binding-protein regulatory sites (OR = 1.13, 95% CI 1.1-1.2, P = 8.8 × 10 -5 ). Overall, our findings demonstrate an enrichment of potentially disruptive regulatory noncoding DNVs in a fraction of CHD at least as high as that observed for damaging coding DNVs.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2025

Self-Diffusivity Measurement of Eutectic F 7 LiNaK with and without Additives Using Quasi-Elastic Neutron Scattering

The atomic scale relaxation dynamics of eutectic F 7 LiNaK (46.5 LiF–11.5 NaF–42 KF mol %, Li-7 enriched) were measured using quasi-elastic neutron scattering (QENS) over a temperature range of 500–750 °C. Here, the effect of adding 0.988 mol % cerium, 0.499 mol % cesium, and 1.21 mol % zirconium individually to the dynamics of F 7 LiNaK was also investigated. The relaxation process in both pure and doped F 7 LiNaK molten salts was fit with a stretched exponential function and the temperature dependence follows an Arrhenius behavior over a wavevector transfer range of 0.4 Å –1 < Q < 0.9 Å –1 . The measured activation energy for self-diffusion is E a = 0.77 ± 0.02 eV/atom for pure molten F 7 LiNaK. The QENS response with additives added to F 7 LiNaK was also fit with a stretched exponential and the associated Arrhenius behavior was characterized with activation energies of E a = 0.88 ± 0.01 eV/atom for zirconium (1.21 mol %), E a = 1.02 ± 0.02 eV/atom for cerium (0.988 mol %), and E a = 0.71 ± 0.03 eV/atom for cesium (0.499 mol %). The measured diffusivities are compared to those simulated with a neural network force field model by Lee et al. [Lee, S.-C. Comparative Studies of the Structural and Transport Properties of Molten Salt FLiNaK Using the Machine-Learned Neural Network and Reparametrized Classical Forcefields. J. Phys. Chem. B 2021, 125(37), 10562–10570].

FLiNaK↗