Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Neural 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 1,477 records · Page 82
All sourcesNASA NTRSDOE OSTI
DOE OSTI2026

Improving missing transverse momentum estimation with a deep neural network

At hadron colliders, the net transverse momentum of particles that do not interact with the detector (missing transverse momentum, $^→_𝑝$$^{miss}_{T}$) is a crucial observable in many analyses. In the standard model, $^→_𝑝$$^{miss}_{T}$ originates from neutrinos. Many beyond-the-standard-model particles, such as dark matter candidates, are also expected to leave the experimental apparatus undetected. This paper presents a novel deep neural network based $^→_𝑝$$^{miss}_{T}$ estimator, DeepMET, developed by the CMS Collaboration at the LHC. The DeepMET algorithm produces a weight for each reconstructed particle based on its properties. The estimator is based on the negative vector sum of the weighted transverse momenta of all reconstructed particles in an event. Compared with other estimators currently employed by CMS, DeepMET improves the $^→_𝑝$$^{miss}_{T}$ resolution by 10%–30%, shows improvement for a wide range of final states, is easier to train, and is more resilient against the effects of additional proton-proton interactions accompanying the collision of interest.

artificial neural networks↗
DOE OSTI2023

Accelerating discrete dislocation dynamics simulations with graph neural networks

Discrete dislocation dynamics (DDD) is a widely employed computational method to study plasticity at the mesoscale that connects the motion of dislocation lines to the macroscopic response of crystalline materials. However, the computational cost of DDD simulations remains a bottleneck that limits its range of applicability. Here, we introduce a new DDD-GNN framework in which the expensive time-integration of dislocation motion is entirely substituted by a graph neural network (GNN) model trained on DDD trajectories. As a first application, we demonstrate the feasibility and potential of our method on a simple yet relevant model of a dislocation line gliding through an array of obstacles. We show that the DDD-GNN model is stable and reproduces very well unseen ground-truth DDD simulation responses for a range of straining rates and obstacle densities, without the need to explicitly compute nodal forces or dislocation mobilities during time-integration. Our approach opens new promising avenues to accelerate DDD simulations and to incorporate more complex dislocation motion behaviors.

36 MATERIALS SCIENCE↗
DOE OSTI2013

Cancer risk at low doses of ionizing radiation: artificial neural networks inference from atomic bomb survivors

Cancer risk at low doses of ionizing radiation remains poorly defined because of ambiguity in the quantitative link to doses below 0.2 Sv in atomic bomb survivors in Hiroshima and Nagasaki arising from limitations in the statistical power and information available on overall radiation dose. To deal with these difficulties, a novel nonparametric statistics based on the ‘integrate-and-fire’ algorithm of artificial neural networks was developed and tested in cancer databases established by the Radiation Effects Research Foundation. The analysis revealed unique features at low doses that could not be accounted for by nominal exposure dose, including (i) the presence of a threshold that varied with organ, gender and age at exposure, and (ii) a small but significant bumping increase in cancer risk at low doses in Nagasaki that probably reflects internal exposure to 239 Pu. The threshold was distinct from the canonical definition of zero effect in that it was manifested as negative excess relative risk, or suppression of background cancer rates. Such a unique tissue response at low doses of radiation exposure has been implicated in the context of the molecular basis of radiation–environment interplay in favor of recently emerging experimental evidence on DNA double-strand break repair pathway choice and its epigenetic memory by histone marking.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2013

Imaging regenerating bone tissue based on neural networks applied to micro-diffraction measurements

We monitored bone regeneration in a tissue engineering approach. To visualize and understand the structural evolution, the samples have been measured by X-ray micro-diffraction. We find that bone tissue regeneration proceeds through a multi-step mechanism, each step providing a specific diffraction signal. The large amount of data have been classified according to their structure and associated to the process they came from combining Neural Networks algorithms with least square pattern analysis. In this way, we obtain spatial maps of the different components of the tissues visualizing the complex kinetic at the base of the bone regeneration.

62 RADIOLOGY AND NUCLEAR MEDICINE↗
DOE OSTI2021

Hierarchical Convolutional Neural Networks for Event Classification on PMU Measurements

Event classification is one of the central components of automated disturbance analysis based on PMU measurements. Obtaining high-quality event labels remains a challenge for supervised learning-based classification of local and system-wide events in power grids due to its labor-intensive requirement. We present a sensitivity study considering rapidly refined, partially and fully inspected event labels that leads to evidence that hierarchical convolutional neural networks (HCNNs) outperform traditional classification models regardless of the quality of the available event labels. Furthermore, it is demonstrated that performance similar to the one obtained using entirely domain-driven labeling can be achieved as long as the involved expert does not mislabel more than ~5% of the event data captured by PMU measurements.

47 OTHER INSTRUMENTATION↗
DOE OSTI2019

An artificial neural network framework for reduced order modeling of transient flows

Here, this paper proposes a supervised machine learning framework for the non-intrusive model order reduction of unsteady fluid flows to provide accurate predictions of non-stationary state variables when the control parameter values vary. Our approach utilizes a training process from full-order scale direct numerical simulation data projected on proper orthogonal decomposition (POD) modes to achieve an artificial neural network (ANN) model with reduced memory requirements. This data-driven ANN framework allows for a nonlinear time evolution of the modal coefficients without performing a Galerkin projection. Our POD-ANN framework can thus be considered an equation-free approach for latent space dynamics evolution of nonlinear transient systems and can be applied to a wide range of physical and engineering applications. Within this framework we introduce two architectures, namely sequential network (SN) and residual network (RN), to train the trajectory of modal coefficients. We perform a systematic analysis of the performance of the proposed reduced order modeling approaches on prediction of a nonlinear wave-propagation problem governed by the viscous Burgers equation, a simplified prototype setting for transient flows. We find that the POD-ANN-RN yields stable and accurate results for test problems assessed both within inside and outside of the database range and performs significantly better than the standard intrusive Galerkin projection model. Finally, our results show that the proposed framework provides a non-intrusive alternative to the evolution of transient physics in a POD basis spanned space, and can be used as a robust predictive model order reduction tool for nonlinear dynamical systems.

42 ENGINEERING↗
DOE OSTI2024

Equivariant graph convolutional neural networks for the representation of homogenized anisotropic microstructural mechanical response

Composite materials with different microstructural material symmetries are common in engineering applications where grain structure, alloying and particle/fiber packing are optimized via controlled manufacturing. In fact these microstructural tunings can be done throughout a part to achieve functional gradation and optimization at a structural level. To predict the performance of particular microstructural configuration and thereby overall performance, constitutive models of materials with microstructure are needed. In this work we provide neural network architectures that provide effective homogenization models of materials with anisotropic components. These models satisfy equivariance and material symmetry principles inherently through a combination of equivariant and tensor basis operations. We demonstrate them on datasets of stochastic volume elements with different textures and phases where the material undergoes elastic and plastic deformation, and show that the these network architectures provide significant performance improvements.

anisotropy↗
DOE OSTI2013

Application of a fuzzy neural network model in predicting polycyclic aromatic hydrocarbon-mediated perturbations of the Cyp1b1 transcriptional regulatory network in mouse skin

Polycyclic aromatic hydrocarbons (PAHs) are present in the environment as complex mixtures with components that have diverse carcinogenic potencies and mostly unknown interactive effects. Non-additive PAH interactions have been observed in regulation of cytochrome P450 (CYP) gene expression in the CYP1 family. To better understand and predict biological effects of complex mixtures, such as environmental PAHs, an 11 gene input-1 gene output fuzzy neural network (FNN) was developed for predicting PAH-mediated perturbations of dermal Cyp1b1 transcription in mice. Input values were generalized using fuzzy logic into low, medium, and high fuzzy subsets, and sorted using k-means clustering to create Mamdani logic functions for predicting Cyp1b1 mRNA expression. Model testing was performed with data from microarray analysis of skin samples from FVB/N mice treated with toluene (vehicle control), dibenzo[def,p]chrysene (DBC), benzo[a]pyrene (BaP), or 1 of 3 combinations of diesel particulate extract (DPE), coal tar extract (CTE) and cigarette smoke condensate (CSC) using leave-one-out cross-validation. Predictions were within 1 log{sub 2} fold change unit of microarray data, with the exception of the DBC treatment group, where the unexpected down-regulation of Cyp1b1 expression was predicted but did not reach statistical significance on the microarrays. Adding CTE to DPE was predicted to increase Cyp1b1 expression, whereas adding CSC to CTE and DPE was predicted to have no effect, in agreement with microarray results. The aryl hydrocarbon receptor repressor (Ahrr) was determined to be the most significant input variable for model predictions using back-propagation and normalization of FNN weights. - Highlights: ► Tested a model to predict PAH mixture-mediated changes in Cyp1b1 expression ► Quantitative predictions in agreement with microarrays for Cyp1b1 induction ► Unexpected difference in expression between DBC and other treatments predicted ► Model predictions for combining PAH mixtures in agreement with microarrays ► Predictions highly dependent on aryl hydrocarbon receptor repressor expression.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2017

Protein Mutation Stability Ternary Classification using Neural Networks and Rigidity Analysis

Discerning how a mutation affects the stability of a protein is central to the study of a wide range of diseases. Machine learning and statistical analysis techniques can inform how to allocate limited resources to the considerable time and cost associated with wet lab mutagenesis experiments. In this work we explore the effectiveness of predicting the change in the stability of a protein due to a mutation using a neural network classfier. Assessing the accuracy of our approach is dependent on the use of experimental data about the effects of mutations performed in vitro. Because the experimental data is prone to discrepancies when similar experiments have been performed by multiple laboratories, the use of the data near the juncture of stabilizing and destabilizing mutations is question- able. We address this later problem via a systematic approach in which we explore the use of a three-way classification scheme with stabilizing, destabilizing, and inconclusive labels. For a systematic search of potential classification cutoff values our classfier achieved 68 percent accuracy on ternary classification for cutoff values of -0.6 and 0.7 with a low rate of classifying stabilizing as destabilizing and vice versa.

Neural Network, Classification, protein stability,↗
NASA NTRS1994

(abstract) Application of Neural Networks to Hyperspectral Unmixing

The emergence, in recent years, of hyperspectral sensors provides a tremendous opportunity for advancing the process of detailed and direct remote detection and identification from space of targets or surface materials. Such sensors exploit the uniqueness of the corresponding spectral reflectance signatures, which enables high resolution imaging spectrometer data to be processed on a pixel-by-pixel basis. This has implications both for defense-related applications (e.g., surveillance tasks) and in the civilian domain (e.g., for science applications). The purpose of this talk is to discuss a number of strong arguments that support neural networks as a choice for the generalized analysis (e.g., unmixing) of remotely sensed hyperspectral data.

signatures moving object detection surveillance co↗
DOE OSTI2025

Charting the chemical space of Zintl phases with graph neural networks and bonding insights

A large number of Zintl phases have been discovered by solid-state chemists driven by empirical knowledge, chemical intuition and in some cases, through serendipitous accidents. These discoveries have only scratched the surface, given the vast compositional and structural diversity that Zintl phases can accommodate. The large chemical space of Zintl phases, as well as intermetallic compounds in general, remain under-explored. Here, we use graph neural networks and the upper bound energy minimization approach to efficiently scan a large chemical space of >90 000 hypothetical Zintl phases and accurately discover 1810 new thermodynamically stable phases with 90% precision, as validated with first-principles calculations. We show that our approach is more than 2× more accurate in predicting DFT stability than M3GNet (40% precision) on the same dataset. Using a random forest model and SHAP analysis, we demonstrate the critical role of ionic bonding in the thermodynamic stability of Zintl phases. Our results not only expand the known chemical landscape of Zintl phases but also highlight the efficacy of machine learning frameworks combined with domain knowledge in uncovering chemically meaningful insights across complex intermetallics.

36 MATERIALS SCIENCE↗
DOE OSTI2022

Using Artificial Neural Networks to Predict Physical Properties of Membrane Polymers

Membrane polymers are a promising technology for use in many challenging gas separation applications. Here, the techniques of computer-aided molecular design can be used to search through the massive molecular space of heteropolymers and develop a set of likely candidate repeat units matching specific physical property targets. However, reasonably accurate property prediction algorithms are needed, but these algorithms must be very fast in order to be combined with an optimization framework. Artificial neural networks (ANNs), a branch of machine learning, are applied in this work to predict the physical properties of polymers. All of the physical properties investigated were found to be predicted by ANNs with R 2 scores exceeding 0.82.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2025

Graph Neural Networks for Surrogate Modeling of Offshore Floating Platforms

Floating offshore wind turbines (FOWTs) present an significant opportunity to increase renewable energy generation. However, significant challenges remain before FOWTs can be widely commercialized and deployed. In particular, hydrodynamic loading on the platforms can stress the overall structure, damage the mooring systems, and impact power generation. Studying these loads is difficult and often relies on computationally expensive models or experiments. In this work, we explore the use of graph neural networks (GNNs) to construct flexible, data-driven surrogates for hydrodynamic loads on platforms. We leverage the natural graph-like structure of offshore wind platform designs to enable the GNN model to learn to approximate the loads for different wave conditions and structural designs. We demonstrate potential uses for the surrogate by performing parameter sweeps and ridge analysis on the trained model to identify the impacts of different wave and structural features on the loads.

floating offshore wind turbines↗
NASA NTRSDate not supplied

Snow Depth from AMSR-2 Using Multispectral Satellite Data in an Artificial Neural Network

By using diffusion theory and Monte Carlo lidar radiative transfer simulations, Hu et al. (2022b) has derived snow depth from the first-, second- and third-order moments of the lidar backscattering pathlength distribution. Lu et al. (2022) calculated the snow depth by applying the methods to the satellite ICESat-2 lidar measurements over the Arctic sea ice, as well as land surfaces of Northern Hemisphere. In this paper, an artificial neural network (ANN) algorithm, employing several channels from Advanced Microwave Scanning Radiometer 2 (AMSR-2) and the humidity vertical profiles from Global Modeling and Assimilation Office (GMAO) Goddard Earth Observing System for Instrument Teams (GEOS-IT) product, is trained to determine snow depth identified by time and geolocation matched 2019 ICESat-2 snow-depth data during winter months over the Arctic sea ice. The trained ANN snow-depth was applied to 2018 AMSR-2 clear pixel data, although the algorithms perform reasonably well in thinner clouds. The validation data (different from the training set) of ANN snow depth from AMSR-2 showed a good agreement with time matched and co-located snow-depth values from ICESat-2. The bias was near zero, with mean absolute error (MAE) 0.05 cm and a root-mean-square-error (RMSE) 0.08 cm. Prior applying the trained ANN snow depth to AMSR-2 data, a cloud screening algorithm was developed with a similar approach. A separate ANN cloud mask was trained to determine an AMSR-2 pixel is clear or cloudy with time and geolocation matched 2015 CALIOP Vertical Feature Mask (VFM) over Arctic sea ice. The ANN cloud mask from AMSR-2 under-estimated cloud fraction by 3-6% compared to CALIOP . The additional research is needed to conclusively evaluate the ANN cloud mask accuracy. Finally, this paper will lay the foundation for a sustained long-term snowfall and snow-storm monitoring system. The future Cloud Aerosol LIdar for Global scale Observations of the ocean-Land Atmosphere system (CALIGOLA) mission will provide a means to calculate snow depth from the lidar backscattering pathlength distribution, benefiting from the UV, visible and infrared pulses. With the calculated snow depth as the truth one could develop a machine learning algorithm, as it was done in this paper, using a passive microwave instrument available at that time to generate a wide range of snow depth data, covering extensive spatial areas in the cross-orbit direction.

Neural Network↗
DOE OSTI2012

Neural network and area method interpretation of pulsed experiments

The determination of the subcriticality level is an important issue in accelerator-driven system technology. The area method, originally introduced by N. G. Sjoestrand, is a classical technique to interpret flux measurement for pulsed experiments in order to reconstruct the reactivity value. In recent times other methods have also been developed, to account for spatial and spectral effects, which were not included in the area method, since it is based on the point kinetic model. The artificial neural network approach can be an efficient technique to infer reactivities from pulsed experiments. In the present work, some comparisons between the two methods are carried out and discussed. (authors)

43 PARTICLE ACCELERATORS↗
DOE OSTI2024

Street-level temperature estimation using graph neural networks: Performance, feature embedding and interpretability

Estimating street-level air temperature is a challenging task due to the highly heterogeneous urban surfaces, canyon-like street morphology, and the diverse physical processes in the built environment. Though pioneering studies have embarked on investigations via data-driven approaches, many questions remain to be answered. Here, in this study, we leveraged an innovative framework and redefined the street-level temperature estimation problem using Graph Neural Networks (GNN) with spatial embedding techniques. The results showed that GNN models are more capable and consistent of estimating street-level temperature among tested locations, benefiting from its unique strength in handling extensive data over unstructured graph topology. In addition, we conducted in-depth analysis of feature importance to enhance the model interpretability. Among the urban features analyzed in this study, the time-variant canopy density and meter-level land use data emerge as crucial factors. Our findings highlight GNN 's high potential in capturing the complex dynamics between urban elements and their impacts on microclimate, thus offering valuable insights for comprehensive urban data collection and urban climate modeling in general. Collectively, this study also contributes to urban planning and policy by providing avenues to enhance city resilience against climate change, thereby advancing the agenda for environmental stewardship and urban sustainability.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

Enhancing Drinking Water Quality Modeling: Leveraging Physics Informed Neural Networks for Learning with Imperfect Reaction Models and Partial Data

Chemical kinetics models, typically formulated as systems of ordinary or partial differential equations, are valuable tools for simulating drinking water quality. However, these models often face inaccuracies due to discrepancies between the laboratory and the real-world conditions, as well as limitations in experimental analytical methods, hindering the accurate representation of the true underlying chemical mechanisms. In this study, we propose a Physics Informed Neural Network (PINN), using the eXtreme Theory of Functional Connections, to improve the prediction of chemical concentrations over time. The PINN method accounts for imperfect chemical models and incorporates partial data to improve predictions. Focusing on reactions describing water disinfection residual and disinfectant byproduct formation, which are crucial for public health and regulatory compliance, we demonstrate that the PINN model is able to accurately predict the concentrations of chemical species across various pH values. Notably, the model extends its accuracy to predict concentrations of chemical species not originally included in its training data. The developed method can be extended to a variety of chemical systems, offering a wide array of potential applications.

13 HYDRO ENERGY↗
DOE OSTI2023

Efficient Bayesian inference with latent Hamiltonian neural networks in No-U-Turn Sampling

When sampling for Bayesian inference, one popular approach in the computational field is to use Hamiltonian Monte Carlo (HMC) and specifically the No-U-Turn Sampler (NUTS), which automatically decides the end time of the Hamiltonian trajectory. However, HMC and NUTS can require numerous numerical gradients of the target density and can prove slow in practice when relying on computationally expensive forward models. We propose Latent Hamiltonian neural networks (L-HNNs) with HMC and NUTS for solving Bayesian inference problems. Once trained, L-HNNs do not require numerical gradients of the target density during sampling, and hence numerous evaluations of the forward computational model. Moreover, L-HNNs satisfy important properties such as perfect time reversibility and Hamiltonian conservation, making them well-suited for use within HMC and NUTS because stationarity can be shown. We also propose the integration of L-HNNs in an online error monitoring scheme, in which numerical gradients of the target density are used for a few samples whenever the L-HNNs prediction errors are large. This online error monitor scheme prevents sample degeneracy in regions of low probability density and ensures robust uncertainty quantification. We demonstrate L-HNNs in NUTS with online error monitoring on several analytical examples involving complex, heavy-tailed, and high-local-curvature probability densities. We then demonstrate the applicability of L-HNNs in NUTS to two computational case studies, namely the Allen-Cahn stochastic partial differential equation and an elliptic partial differential equation with 25 and 50 inference parameters, respectively. Overall, the L-HNNs in NUTS with online error monitoring satisfactorily inferred these probability densities. In conclusion, compared to traditional NUTS, L-HNNs in NUTS with online error monitoring required 1–2 orders of magnitude fewer numerical gradients of the target density and improved the effective sample size (ESS) per gradient (which is a measure of both the sampling quality and the computational expense) by an order of magnitude.

97 MATHEMATICS AND COMPUTING↗