Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Deep Neural Networks”

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 1,459 records · Page 81

Transmission Line Fault Location Using Deep Learning Techniques

This letter presents a novel single-ended fault location approach for transmission lines that uses modern deep learning methods. A mixed convolutional neural network and long short-term memory structure are proposed to preserve the translation invariance and capture the temporal correlation of the time-series input data. Advanced deep learning techniques such as adaptive moment estimation and dropout are used to efficiently train the neural network and prevent over-fitting. Our extensive studies have demonstrated the accuracy and effectiveness of the deep-learning-based, singled-ended fault location approach.

Fan, Rui↗

Uncertainties in Parameters Estimated with Neural Networks: Application to Strong Gravitational Lensing

In Hezaveh et al. (2017) we showed that deep learning can be used for model parameter estimation and trained convolutional neural networks to determine the parameters of strong gravitational lensing systems. Here we demonstrate a method for obtaining the uncertainties of these parameters. We review the framework of variational inference to obtain approximate posteriors of Bayesian neural networks and apply it to a network trained to estimate the parameters of the Singular Isothermal Ellipsoid plus external shear and total flux magnification. We show that the method can capture the uncertainties due to different levels of noise in the input data, as well as training and architecture-related errors made by the network. To evaluate the accuracy of the resulting uncertainties, we calculate the coverage probabilities of marginalized distributions for each lensing parameter. By tuning a single hyperparameter, the dropout rate, we obtain coverage probabilities approximately equal to the confidence levels for which they were calculated, resulting in accurate and precise uncertainty estimates. Our results suggest that neural networks can be a fast alternative to Monte Carlo Markov Chains for parameter uncertainty estimation in many practical applications, allowing more than seven orders of magnitude improvement in speed.

Perreault Levasseur, Laurence↗

Sparse Convolutional Neural Networks for particle classification in ProtoDUNE-SP events

Deep Learning (DL) methods and Computer Vision are becoming important tools for event reconstruction in particle physics detectors. In this work, we report on the use of submanifold sparse convolutional neural networks (SparseNets) for the classification of track and shower hits from a DUNE prototype liquid-argon detector at CERN (ProtoDUNE-SP). By taking advantage of the three-dimensional nature of the problem we use a set of nine input features to classify sparse and locally dense hits associated to track or shower particles. The SparseNet has been trained on a test sample and shows promising results: efficiencies and purities greater than 90%. This has also been achieved with a considerable speedup and substantially less resource utilization with respect to other DL networks such as graph neural networks. This method offers great scalability advantages for future large neutrino detectors such as the planned DUNE experiment.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Stable parallel training of Wasserstein conditional generative adversarial neural networks

In this work, we propose a stable, parallel approach to train Wasserstein conditional generative adversarial neural networks (W-CGANs) under the constraint of a fixed computational budget. Differently from previous distributed GANs training techniques, our approach avoids inter-process communications, reduces the risk of mode collapse and enhances scalability by using multiple generators, each one of them concurrently trained on a single data label. The use of the Wasserstein metric also reduces the risk of cycling by stabilizing the training of each generator. We illustrate the approach on the CIFAR10, CIFAR100, and ImageNet1k datasets, three standard benchmark image datasets, maintaining the original resolution of the images for each dataset. Performance is assessed in terms of scalability and final accuracy within a limited fixed computational time and computational resources. To measure accuracy, we use the inception score, the Fréchet inception distance, and image quality. An improvement in inception score and Fréchet inception distance is shown in comparison to previous results obtained by performing the parallel approach on deep convolutional conditional generative adversarial neural networks as well as an improvement of image quality of the new images created by the GANs approach. Weak scaling is attained on both datasets using up to 2000 NVIDIA V100 GPUs on the OLCF supercomputer Summit.

97 MATHEMATICS AND COMPUTING↗

Application of convolutional neural networks for stellar spectral classification

ABSTRACT Due to the ever-expanding volume of observed spectroscopic data from surveys such as SDSS and LAMOST, it has become important to apply artificial intelligence (AI) techniques for analysing stellar spectra to solve spectral classification and regression problems like the determination of stellar atmospheric parameters Teff, $\rm {\log g}$, and [Fe/H]. We propose an automated approach for the classification of stellar spectra in the optical region using convolutional neural networks (CNNs). Traditional machine learning (ML) methods with ‘shallow’ architecture (usually up to two hidden layers) have been trained for these purposes in the past. However, deep learning methods with a larger number of hidden layers allow the use of finer details in the spectrum which results in improved accuracy and better generalization. Studying finer spectral signatures also enables us to determine accurate differential stellar parameters and find rare objects. We examine various machine and deep learning algorithms like artificial neural networks, Random Forest, and CNN to classify stellar spectra using the Jacoby Atlas, ELODIE, and MILES spectral libraries as training samples. We test the performance of the trained networks on the Indo-U.S. Library of Coudé Feed Stellar Spectra (CFLIB). We show that using CNNs, we are able to lower the error up to 1.23 spectral subclasses as compared to that of two subclasses achieved in the past studies with ML approach. We further apply the trained model to classify stellar spectra retrieved from the SDSS data base with SNR > 20.

Sharma, Kaushal↗

Fault Detection on Seismic Structural Images Using a Nested Residual U-Net

Automatic identification of faults on seismic structural images is a challenging yet crucial task in quantitative seismic interpretation. Human picking or attribute-based fault detection methods may misidentify faults on noisy, complex seismic images. In this work, we develop a new automatic fault detection method using a nested residual U-shaped convolutional neural network. Each of the encoders and decoders in this neural network is a residual U-Net, leading to a nested architecture. The final fault map results from the fusion of three fault maps with low, medium, and high fault resolutions. We demonstrate the excellent fault-detection capability of our nested neural network using a series of synthetic and field seismic images. We find that our approach produces clearer and more interpretable fault maps than the current state-of-the-art U-Net fault detection method, particularly on noisy seismic images. Our new automatic fault detection method can facilitate reliable quantitative seismic interpretation on field seismic images.

58 GEOSCIENCES↗

A data analytical approach for assessing the efficacy of Operational Technology active defenses against insider threats

In recent years, the need for Operational Technology (OT) defenses has been recognized, serving as an additional line of defense when Information Technology (IT) defenses are bypassed. This is no longer considered an uncommon possibility when dealing with advanced persistent threat (APT) actors expected to be state-sponsored and receiving insider assistance. In these extreme adversarial situations, OT defenses aim to provide another layer of defense for the system, introduced directly at the physical process level, as described by the sensors data, the system model, and control actions. Just like IT defenses, two schools of thought, i.e., passive and active defenses, have emerged to address this challenge. In active defenses, representing the focus of this paper, known signatures, synthesized based on the system's unique characteristics, are inserted into the system. In contradistinction, passive methods rely solely on observing system behavior in search of patterns of normal behavior with deviations thereof representing abnormal behavior. In their most sophisticated implementations, both passive and active defenses rely on the use of data analytics to identify the patterns and synthesize the observed and/or inserted signatures. Past research has shown that passive defenses may be bypassed by APT actors relying on data analytics and their intimate knowledge of the system to evade detection by respecting the patterns identified by the defenders. Here this manuscript explores the use of active defenses under the assumption that the attacker has privileged access to the system, including access to the system's model and sensors data. Specifically, this manuscript assesses the ability of active defenses to remain invisible to the attackers, and discusses the associated challenges that must be addressed to ensure their resiliency against APT actors.

98 NUCLEAR DISARMAMENT, SAFEGUARDS, AND PHYSICAL P↗

QC-GN 2 oMS 2 : a Graph Neural Net for High Resolution Mass Spectra Prediction

Predicting the mass spectrum of a molecular ion is often accomplished via three generalized approaches: rules-based methods for bond breaking, deep learning, or quantum chemical (QC) modeling. Rules-based approaches are often limited by the conditions for different chemical subspaces and perform poorly under chemical regimes with few defined rules. QC modeling is theoretically robust but requires significant amounts of computational time to produce a spectrum for a given target. Among deep learning techniques, graph neural networks (GNNs) have performed better than previous work with fingerprint-based neural networks in mass spectra prediction. To explore this technique further, we investigate the effects of including quantum chemically derived information as edge features in the GNN to increase predictive accuracy. The models we investigated include categorical bond order, bond force constants derived from extended tight-binding (xTB) quantum chemistry, and acyclic bond dissociation energies. Throughout this work, we evaluated these models against a control GNN with no edge features in the input graphs. Bond dissociation enthalpies yielded the best improvement with a cosine similarity score of 0.462 relative to the baseline model (0.437). In this work we also apply dynamic graph attention which improves performance on benchmark problems and supports the inclusion of edge features. Between implementations, we investigate the nature of the molecular embedding for spectra prediction and discuss the recognition of fragment topographies in distinct chemistries for further development in tandem mass spectrometry prediction.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Toward Electrochemical Studies on the Nanometer and Atomic Scales: Progress, Challenges, and Opportunities

Electrochemical reactions and ionic transport underpin the operation of a broad range of devices and applications, from energy storage and conversion to information technologies, as well as biochemical processes, artificial muscles, and soft actuators. Understanding the mechanisms governing function of these applications requires probing local electrochemical phenomena on the relevant time and length scales. Here, we discuss the challenges and opportunities for extending electrochemical characterization probes to the nanometer and ultimately atomic scales, including challenges in down-scaling classical methods, the emergence of novel probes enabled by nanotechnology and based on emergent physics and chemistry of nanoscale systems, and the integration of local data into macroscopic models. Scanning probe microscopy (SPM) methods based on strain detection, potential detection, and hysteretic current measurements are discussed. We further compare SPM to electron beam probes and discuss the applicability of electron beam methods to probe local electrochemical behavior on the mesoscopic and atomic levels. Similar to a SPM tip, the electron beam can be used both for observing behavior and as an active electrode to induce reactions. We briefly discuss new challenges and opportunities for conducting fundamental scientific studies, matter patterning, and atomic manipulation arising in this context.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Advancing energy storage through solubility prediction: leveraging the potential of deep learning

Solubility prediction plays a crucial role in energy storage applications, such as redox flow batteries, because it directly affects the efficiency and reliability. Researchers have developed various methods that utilize quantum calculations and descriptors to predict the aqueous solubilities of organic molecules. Notably, machine learning models based on descriptors have shown promise for solubility prediction. As deep learning tools, graph neural networks (GNNs) have emerged to capture complex structure–property relationships for material property prediction. Specifically, MolGAT, a type of GNN model, was designed to incorporate n-dimensional edge attributes, enabling the modeling of intricacies in molecular graphs and enhancing the prediction capabilities. In a previous study, MolGAT successfully screened 23 467 promising redox-active molecules from a database of over 500 000 compounds, based on redox potential predictions. This study focused on applying the MolGAT model to predict the aqueous solubility (log S) of a broad range of organic compounds, including those previously screened for redox activity. The model was trained on a diverse sample of 8494 organic molecules from AqSolDB and benchmarked against literature data, demonstrating superior accuracy compared with other state of the art graph-based and descriptor-based models. Subsequently, the trained MolGAT model was employed to screen redox-active organic compounds identified in the first phase of high-throughput virtual screening, targeting favorable solubility in energy storage applications. The second round of screening, which considered solubility, yielded 12 332 promising redox-active and soluble organic molecules suitable for use in aqueous redox flow batteries. Thus, the two-phase high-throughput virtual screening approach utilizing MolGAT, specifically trained for redox potential and solubility, is an effective strategy for selecting suitable intrinsically soluble redox-active molecules from extensive databases, potentially advancing energy storage through reliable material development. This indicates that the model is reliable for predicting the solubility of various molecules and provides valuable insights for energy storage, pharmaceutical, environmental, and chemical applications.

25 ENERGY STORAGE↗

Isotope effects in x-ray absorption spectra of liquid water

The isotope effects in x-ray absorption spectra of liquid water are studied by a many-body approach within electron-hole excitation theory. The molecular structures of both light and heavy water are modeled by path-integral molecular dynamics based on the advanced deep-learning technique. The neural network is trained on ab initio data obtained with SCAN density functional theory. The experimentally observed isotope effect in x-ray absorption spectra is reproduced semiquantitatively in theory. Compared to the spectrum in normal water, the blueshifted and less pronounced pre- and main-edge in heavy water reflect that the heavy water is more structured at short- and intermediate-range of the hydrogen-bond network. In contrast, we find the isotope effect on the spectrum is negligible at post-edge, which is consistent with the identical long-range ordering in both liquids as observed in the diffraction experiment.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

ARMing the Edge: Designing Edge Computing–Capable Machine Learning Algorithms to Target ARM Doppler Lidar Processing

Abstract There is a need for long-term observations of cloud and precipitation fall speeds in validating and improving rainfall forecasts from climate models. To this end, the U.S. Department of Energy Atmospheric Radiation Measurement (ARM) user facility Southern Great Plains (SGP) site at Lamont, Oklahoma, hosts five ARM Doppler lidars that can measure cloud and aerosol properties. In particular, the ARM Doppler lidars record Doppler spectra that contain information about the fall speeds of cloud and precipitation particles. However, due to bandwidth and storage constraints, the Doppler spectra are not routinely stored. This calls for the automation of cloud and rain detection in ARM Doppler lidar data so that the spectral data in clouds can be selectively saved and further analyzed. During the ARMing the Edge field experiment, a Waggle node capable of performing machine learning applications in situ was deployed at the ARM SGP site for this purpose. In this paper, we develop and test four algorithms for the Waggle node to automatically classify ARM Doppler lidar data. We demonstrate that supervised learning using a ResNet50-based classifier will classify 97.6% of the clear-air images and 94.7% of cloudy images correctly, outperforming traditional peak detection methods. We also show that a convolutional autoencoder paired with k -means clustering identifies 10 clusters in the ARM Doppler lidar data. Three clusters correspond to mostly clear conditions with scattered high clouds, and seven others correspond to cloudy conditions with varying cloud-base heights.

54 ENVIRONMENTAL SCIENCES↗

Deep Learning Parameterization of Vertical Wind Velocity Variability via Constrained Adversarial Training

Atmospheric models with typical resolution in the tenths of kilometers cannot resolve the dynamics of air parcel ascent, which varies on scales ranging from tens to hundreds of meters. Small-scale wind fluctuations are thus characterized by a subgrid distribution of vertical wind velocity W with standard deviation σ W . The parameterization of σ W is fundamental to the representation of aerosol–cloud interactions, yet it is poorly constrained. Using a novel deep learning technique, this work develops a new parameterization for σ W merging data from global storm-resolving model simulations, high-frequency retrievals of W , and climate reanalysis products. The parameterization reproduces the observed statistics of σ W and leverages learned physical relations from the model simulations to guide extrapolation beyond the observed domain. Incorporating observational data during the training phase was found to be critical for its performance. The parameterization can be applied online within large-scale atmospheric models, or offline using output from weather forecasting and reanalysis products.

54 ENVIRONMENTAL SCIENCES↗

Automated Threat Recognition For Aviation Security Applications

We have developed a framework for automated threat recognition (ATR) of explosive threat materials for both single-energy and dual-energy X-ray CT systems. Under this framework, two different types of ATR have been developed. The first type of ATR employs supervised machine learning with statistical characterization of target materials for threat identification training. The reliance only on statistical characterization information for threat training uniquely enables this style of ATR to adapt quickly to evolving threats. The second type of ATR employs deep learning through convolutional neural networks. Convolutional neural networks are attractive due to their human-like capacity for learning and strong ability to identify trends and patterns. Although this method is more powerful than the first type, it requires large amounts of training data and therefore is less agile. Each ATR performs threat characterization at the voxel neighborhood level. This approach avoids the use of threat shape as a detection criterion, which is prohibited by DHS and TSA guidelines.

97 MATHEMATICS AND COMPUTING↗

Predicting departure from nucleate boiling with advanced data- and physics-driven approaches

The subcooled and low-quality saturated flow boiling critical heat flux (CHF) corresponding to the departure from nucleate boiling (DNB) is one of the major limiting factors in the design and operation of pressurized water reactors (PWRs). Due to lack of agreement on its physical mechanisms, development of an accurate DNB-type CHF model has been elusive. The various steady-state (SS) predictive tools that have been proposed can be grouped into two categories: (1) data-driven methods—namely best-fit empirical correlations and look-up tables that result in relatively good agreement with specific experimental datasets but often fail to extend beyond their ranges of validity, and (2) the physics-based mechanistic models that rely on reasonable yet limited understanding of the underlying physics and apply constitutive relations to close the conservation equations. On one hand, with recent advances in computational capabilities and optimization techniques, machine learning (ML)-based methods constitute an alternative and a more advanced, data-driven approach. With enough data, they can be particularly useful in engineering fields where the physical phenomena are complex and challenging to model. On the other hand, a state-of-the-art physics-driven approach would not only provide more accurate prediction of SS CHF, but it would also help better understand and model transient applications. The data-driven regression models use deep feed-forward neural networks (NNs) and random forests to cross-validate with 1,865 CHF test cases, covering a wide range of flow conditions and channel geometries. The best-estimate ML-based predictors compare favorably with the widely used look-up table for annulus and plate, and sensitivity analysis has confirmed their effectiveness. The key advantage of ML-based methods is their online extensibility of applicability domain. The proposed physics-driven approach combines key assumptions and parameters in the relatively well-accepted theories of liquid sublayer dryout and near-wall bubble crowding. A more realistic understanding of local mechanisms has been modeled. The new model has been optimized and validated against 1,439 tube data, and it shows considerably improved performance when compared to a recent mechanistic model, demonstrating unbiased close agreement with measurements over a wide range of operating conditions. Future work will extend the improved physics-driven model to non-tube geometry applications and will couple the model with ML via a hybrid approach. The mechanistic SS work will also serve to improve understanding and to model transient CHF scenarios.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗

Day-Ahead Probabilistic Forecasting of Net-Load and Demand Response Potentials with High Penetration of Behind-the-Meter Solar-plus-Storage

The goal of this project is to develop advanced methods for day-ahead net-load forecasting, by leveraging the state-of-the-art machine learning techniques. The developed models produce both point and probabilistic forecasts for a variety of use cases, and are versatile to work with different types of data sets. The innovation lies in the novel design of the architectures, leveraging the most recent advances in machine learning that have not been explored in power systems, accompanied by techniques in the broader artificial intelligence fields such as fuzzy systems. This project has achieved the following accomplishments: (1) preprocessing of over 10 data sets covering varying geographical regions, time horizons, and system levels, which form a robust foundation for training and evaluating forecasting models across a wide range of realistic grid scenarios; (2) development of an interactive web app that enables exploratory analysis of load and generation data, and supports better understanding of data trends, anomalies, and correlations, facilitating model development and stakeholder engagement; (3) implementation of over 10 benchmark models for point and probabilistic forecasting, which include a mix of conventional machine learning methods and state-of-the-art deep learning approaches, providing a comprehensive baseline for performance comparison and validation of the proposed models; (4) development of a fuzzy system based gradient boosting model, tailored for small (less than 3 years) data sets, which achieves a mean absolute percentage error (MAPE) of 4% for point forecasting and a 20% improvement in average pinball loss for probabilistic forecasting; (5) development of a Transformer (a state-of-the-art deep learning architecture) based neural network model, tailored for large (3 years or more) data sets, which achieves a MAPE of 2% for point forecasting and a 20% improvement in average pinball loss for probabilistic forecasting; (6) development of a methodology for quantifying DR potential, and extensions of the previous models for multi-target forecasting of net load and DR potential, which achieve a MAPE of 10% for DR potential.

24 POWER TRANSMISSION AND DISTRIBUTION↗