Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Network inference”

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 325 records · Page 18
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

Continual Learning for Pattern Recognizers using Neurogenesis Deep Learning

Deep neural networks have emerged as a leading set of algorithms to infer information from a variety of data sources such as images and time series data. In their most basic form, neural networks lack the ability to adapt to new classes of information. Continual learning is a field of study attempting to give previously trained deep learning models the ability to adapt to a changing environment. Previous work developed a CL method called Neurogenesis for Deep Learning (NDL). Here, we combine NDL with a specific neural network architecture (the Ladder Network) to produce a system capable of automatically adapting a classification neural network to new classes of data. The NDL Ladder Network was evaluated against other leading CL methods. While the NDL and Ladder Network system did not match the cutting edge performance achieved by other CL methods, in most cases it performed comparably and is the only system evaluated that can learn new classes of information with no human intervention.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Uncertainty quantification of graph convolution neural network models of evolving processes

The application of neural network models to scientific machine learning tasks has proliferated in recent years. In particular, neural networks have proved to be adept at modeling processes with spatial–temporal complexity. Nevertheless, these highly parameterized models have garnered skepticism in their ability to produce outputs with quantified error bounds over the regimes of interest. Hence there is a need to find uncertainty quantification methods that are suitable for neural networks. In this work we present comparisons of the parametric uncertainty quantification of neural networks modeling complex spatial–temporal processes with Hamiltonian Monte Carlo and Stein variational gradient descent and its projected variant. Specifically we apply these methods to graph convolutional neural network models of evolving systems modeled with recurrent neural network and neural ordinary differential equations architectures. We show that Stein variational inference is a viable alternative to Monte Carlo methods with some clear advantages for complex neural network models. For our exemplars, Stein variational interference gave similar pushed forward uncertainty profiles through time compared to Hamiltonian Monte Carlo, albeit with generally more generous variance. As a result, projected Stein variational gradient descent also produced similar uncertainty profiles to the non-projected counterpart, but large reductions in the active weight space were confounded by the stability of the neural network predictions and the convoluted likelihood landscape.

36 MATERIALS SCIENCE↗
DOE OSTI2025

From sequence to protein structure and conformational dynamics with artificial intelligence/machine learning

The 2024 Nobel Prize in Chemistry was awarded in part for de novo protein structure prediction using AlphaFold2, an artificial intelligence/machine learning (AI/ML) model trained on vast amounts of sequence and three-dimensional structure data. AlphaFold2 and related models, including RoseTTAFold and ESMFold, employ specialized neural network architectures driven by attention mechanisms to infer relationships between sequence and structure. At a fundamental level, these AI/ML models operate on the long-standing hypothesis that the structure of a protein is determined by its amino acid sequence. More recently, AlphaFold2 has been adapted for the prediction of multiple protein conformations by subsampling multiple sequence alignments. Herein, we provide an overview of the deterministic relationship between sequence and structure, which was hypothesized over half a century ago with profound implications for the biological sciences ever since. We postulate that protein conformational dynamics are also determined, at least in part, by amino acid sequence and that this relationship may be leveraged for construction of AI/ML models dedicated to predicting protein conformational ensembles. Accordingly, we describe a conceptual model architecture, which may be trained on sequence data in combination with conformationally sensitive structural information, coming primarily from nuclear magnetic resonance (NMR) spectroscopy. Notwithstanding certain limitations in this context, NMR offers abundant structural heterogeneity conducive to conformational ensemble prediction. As NMR and other data continue to accumulate, sequence-informed prediction of protein structural dynamics with AI/ML has the potential to emerge as a transformative capability across the biological sciences.

Artificial intelligence↗
DOE OSTI2024

Predicting Missing Regions in Charged Particle Tracks Using a Sparse 3D Convolutional Neural Network

The 2x2 Demonstrator is a prototype of ND-LAr, the liquid argon time-projection chamber of the Deep Underground Neutrino Experiment’s Near Detector complex. Both the 2x2 Demonstrator and ND-LAr are modular detectors that will have pixelated charge readouts and inactive regions wherein there is no sensitivity to charge deposition and light signals that arise from charged particle interactions with liquid argon. In the 2x2, these inactive regions are located in between the active detector modules, which introduces the challenge of inferring what charge signals ought to look like in these regions. This study explores the use of a Sparse 3D Convolutional Neural Network (ConvNet) to infer missing regions in charged particle tracks. Hits corresponding to energy depositions are voxelized into a three-dimensional grid for each track. Voxels that fall into predefined inactive regions are removed to simulate the lack of detector output. The model is trained to infer the topology of the missing track voxels, with the ultimate goal of inferring the missing charge or energy values in these voxels as well. Results indicate that this approach shows promise in prediction of missing track regions with some accuracy.

Utaegbulam, Hilary↗
DOE OSTI2024

Learning likelihood ratios with neural network classifiers

The likelihood ratio is a crucial quantity for statistical inference in science that enables hypothesis testing, construction of confidence intervals, reweighting of distributions, and more. Many modern scientific applications, however, make use of data- or simulation-driven models for which computing the likelihood ratio can be very difficult or even impossible. By applying the so-called “likelihood ratio trick,” approximations of the likelihood ratio may be computed using clever parametrizations of neural network-based classifiers. A number of different neural network setups can be defined to satisfy this procedure, each with varying performance in approximating the likelihood ratio when using finite training data. We present a series of empirical studies detailing the performance of several common loss functionals and parametrizations of the classifier output in approximating the likelihood ratio of two univariate and multivariate Gaussian distributions as well as simulated high-energy particle physics datasets.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2024

Analyzing inference workloads for spatiotemporal modeling

Ensuring power grid resiliency, forecasting climate conditions, and optimization of transportation infrastructure are some of the many application areas where data is collected in both space and time. Spatiotemporal modeling is about modeling those patterns for forecasting future trends and carrying out critical decision-making by leveraging machine learning/deep learning. Once trained offline, field deployment of trained models for near real-time inference could be challenging because performance can vary significantly depending on the environment, available compute resources and tolerance to ambiguity in results. Users deploying spatiotemporal models for solving complex problems can benefit from analytical studies considering a plethora of system adaptations to understand the associated performance-quality trade-offs. To facilitate the co-design of next-generation hardware architectures for field deployment of trained models, it is critical to characterize the workloads of these deep learning (DL) applications during inference and assess their computational patterns at different levels of the execution stack. In this paper, we develop several variants of deep learning applications that use spatiotemporal data from dynamical systems. We study the associated computational patterns for inference workloads at different levels, considering relevant models (Long short-term Memory, Convolutional Neural Network and Spatio-Temporal Graph Convolution Network), DL frameworks (Tensorflow and PyTorch), precision (FP16, FP32, AMP, INT16 and INT8), inference runtime (ONNX and AI Template), post-training quantization (TensorRT) and platforms (Nvidia DGX A100 and Sambanova SN10 RDU). Overall, our findings indicate that although there is potential in mixed-precision models and post-training quantization for spatiotemporal modeling, extracting efficiency from contemporary GPU systems might be challenging. Instead, co-designing custom accelerators by leveraging optimized High Level Synthesis frameworks (such as SODA High-Level Synthesizer for customized FPGA/ASIC targets) can make workload-specific adjustments to enhance the efficiency.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Artificial intelligence inferred microstructural properties from voltage–capacity curves

Abstract The quantification of microstructural properties to optimize battery design and performance, to maintain product quality, or to track the degradation of LIBs remains expensive and slow when performed through currently used characterization approaches. In this paper, a convolution neural network-based deep learning approach (CNN) is reported to infer electrode microstructural properties from the inexpensive, easy to measure cell voltage versus capacity data. The developed framework combines two CNN models to balance the bias and variance of the overall predictions. As an example application, the method was demonstrated against porous electrode theory-generated voltage versus capacity plots. For the graphite|LiMn $$_2$$ 2 O $$_4$$ 4 chemistry, each voltage curve was parameterized as a function of the cathode microstructure tortuosity and area density, delivering CNN predictions of Bruggeman’s exponent and shape factor with 0.97 $$R^2$$ R 2 score within 2 s each, enabling to distinguish between different types of particle morphologies, anisotropies, and particle alignments. The developed neural network model can readily accelerate the processing-properties-performance and degradation characteristics of the existing and emerging LIB chemistries.

25 ENERGY STORAGE↗
DOE OSTI2023

Anticipating gelation and vitrification with medium amplitude parallel superposition (MAPS) rheology and artificial neural networks

Abstract Anticipating qualitative changes in the rheological response of complex fluids (e.g., a gelation or vitrification transition) is an important capability for processing operations that utilize such materials in real-world environments. One class of complex fluids that exhibits distinct rheological states are soft glassy materials such as colloidal gels and clay dispersions, which can be well characterized by the soft glassy rheology (SGR) model. We first solve the model equations for the time-dependent, weakly nonlinear response of the SGR model. With this analytical solution, we show that the weak nonlinearities measured via medium amplitude parallel superposition (MAPS) rheology can be used to anticipate the rheological aging transitions in the linear response of soft glassy materials. This is a rheological version of a technique called structural health monitoring used widely in civil and aerospace engineering. We design and train artificial neural networks (ANNs) that are capable of quickly inferring the parameters of the SGR model from the results of sequential MAPS experiments. The combination of these data-rich experiments and machine learning tools to provide a surrogate for computationally expensive viscoelastic constitutive equations allows for rapid experimental characterization of the rheological state of soft glassy materials. We apply this technique to an aging dispersion of Laponite ® clay particles approaching the gel point and demonstrate that a trained ANN can provide real-time detection of transitions in the nonlinear response well in advance of incipient changes in the linear viscoelastic response of the system.

Lennon, Kyle R. (ORCID:0000000212515461)↗
DOE OSTI2023

Mind the gap: the discrepancy between simulation and reality drives interpretations of the Galactic Center Excess

The Galactic Center Excess (GCE) in GeV gamma rays has been debated for over a decade, with the possibility that it might be due to dark matter annihilation or undetected point sources such as millisecond pulsars (MSPs). This study investigates how the gamma-ray emission model (γEM) used in Galactic center analyses affects the interpretation of the GCE's nature. To address this issue, we construct an ultra-fast and powerful inference pipeline based on convolutional Deep Ensemble Networks. We explore the two main competing hypotheses for the GCE using a set of γEMs with increasing parametric freedom. We calculate the fractional contribution (f src ) of a dim population of MSPs to the total luminosity of the GCE and analyze its dependence on the complexity of the γEM. For the simplest γEM, we obtain fsrc = 0.10 ± 0.07, while the most complex model yields f src = 0.79 ± 0.24. In conclusion, we find that the statement about the nature of the GCE (dark matter or not) strongly depends on the assumed γEM. The quoted results for f src do not account for the additional uncertainty arising from the fact that the observed gamma-ray sky is out-of-distribution concerning the investigated γEM iterations. We quantify the reality gap between our γEMs using deep-learning-based One-Class Deep Support Vector Data Description networks, revealing that all employed γEMs have gaps to reality. Finally, our study casts doubt on the validity of previous conclusions regarding the GCE and dark matter, and underscores the urgent need to account for the reality gap and consider previously overlooked "out of domain" uncertainties in future interpretations.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2022

Realistic galaxy image simulation via score-based generative models

ABSTRACT We show that a denoising diffusion probabilistic model (DDPM), a class of score-based generative model, can be used to produce realistic mock images that mimic observations of galaxies. Our method is tested with Dark Energy Spectroscopic Instrument (DESI) grz imaging of galaxies from the Photometry and Rotation curve OBservations from Extragalactic Surveys (PROBES) sample and galaxies selected from the Sloan Digital Sky Survey. Subjectively, the generated galaxies are highly realistic when compared with samples from the real data set. We quantify the similarity by borrowing from the deep generative learning literature, using the ‘Fréchet inception distance’ to test for subjective and morphological similarity. We also introduce the ‘synthetic galaxy distance’ metric to compare the emergent physical properties (such as total magnitude, colour, and half-light radius) of a ground truth parent and synthesized child data set. We argue that the DDPM approach produces sharper and more realistic images than other generative methods such as adversarial networks (with the downside of more costly inference), and could be used to produce large samples of synthetic observations tailored to a specific imaging survey. We demonstrate two potential uses of the DDPM: (1) accurate inpainting of occluded data, such as satellite trails, and (2) domain transfer, where new input images can be processed to mimic the properties of the DDPM training set. Here we ‘DESI-fy’ cartoon images as a proof of concept for domain transfer. Finally, we suggest potential applications for score-based approaches that could motivate further research on this topic within the astronomical community.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2020

A Deep Generative Model for Non-Intrusive Identification of EV Charging Profiles

The proliferation of electric vehicles (EVs) brings environmental benefits and technical challenges to power grids. An identification algorithm which can accurately extract individual EV charging profiles out of widely available smart meter measurements has attracted great interests. This paper proposes a non-intrusive identification framework for EV charging profile extraction, which is driven by deep generative models (DGM). First, the proposed DGM is designed as a representation layer embedded into the Markov process and used to model the joint probability distribution of available time-series data. A novel contribution is to approximate posterior distributions by neural networks whose parameters are obtained by variational inference and supervised learning. Second, the EV charging status is inferred from the DGM via dynamic programming. Lastly, the desired EV charging profile can be reconstructed by the rated power of EV models and inferred status. Compared with the benchmark Hidden Markov Models, the proposed framework can better handle noise in data with less computational complexity and better overall accuracy performances with smaller recall. The proposed framework is validated by numerical experiments on the Pecan Street dataset.

33 ADVANCED PROPULSION SYSTEMS↗
DOE OSTI2023

Bayesian quantum state reconstruction with a learning-based tuned prior

We demonstrate machine-learning-enhanced Bayesian quantum state tomography on near-term intermediate-scale quantum hardware. Our approach to selecting prior distributions leverages pre-trained neural networks incorporating measurement data and enables improved inference times over standard prior distributions.

Regmi, Sangita↗
NASA NTRS1976

The dark component of the photospheric network

We examine a high quality Zeeman-analyzed lambda-scan through Ca I 6103, using a 0.1 A filter. We find that filter shifts of 0.01 A produce substantial changes in the contrast seen in the photospheric network in the core of the line, implying that the Doppler velocity in the network is constant to within 0.25 km/sec or less. Relative line profiles constructed from the lambda-scan indicate that the bright network points have smaller equivalent widths than does the background photosphere and are systematically Doppler shifted toward the red. However, we also find numerous small dark points within the magnetic network which exhibit increased equivalent widths. We infer these to be due to magnetic flux tubes which are highly inclined through the photosphere.

Schoolman, S. A.↗
NASA NTRS1982

The use of stereoscopic satellite observation in the determination of the emissivity of cirrus

The feasibility of determining cirrus 'emissivity' from combined stereoscopic and infrared satellite observations in conjunction with radiosounding data is investigated for a particular case study. Simultaneous visible images obtained during SESAME-1979 from two geosynchronous GOES meteorological satellites were processed on the NASA Goddard interactive system (AOIPS) and were used to determine the stereo cloud top height Z sub C as described by Hasler (1981). Iso-contours of radiances were outlined on the corresponding infrared image. Total brightness temperature T sub B and ground surface brightness temperature T sub S were inferred from the radiances. The special SESAME network of radiosoundings was used to determine the cloud top temperature T sub CLD at the level defined by Z sub C. The 'effective cirrus emissivity' NE where N is the fractional cirrus cloudiness and E is the emissivity in a GOES infrared picture element of about 10 km x 10 km is then computed from T sub B, T sub S and T sub CLD.

Szejwach, G.↗
DOE OSTI2021

Recent Developments at the Raft River Geothermal Field

The Raft River geothermal field, located in Cassia County in southwestern Idaho, is the site of a Department of Energy Enhanced Geothermal System project. U.S. Geothermal, Inc. currently produces about 11 MWe from Precambrian metamorphic rocks. These lie beneath ~5,000 ft of Quaternary and Tertiary volcaniclastic and volcanic deposits. Maximum temperatures range from 271°F to 300°F. Well RRG-9 ST1, the well targeted for stimulation is located approximately 1 mile south of the main bore field. The open hole section of the well, from 5,551 to 5,900 ft MD, consists of Precambrian Elba Quartzite, the stimulation target, granite and minor diabase. Prior to setting the casing acoustic, gamma ray, and density logs were run. After completing the well, a step rate/step down test was conducted. The maximum injection rate achieved was 18 bpm at a wellhead pressure of 1,150 psig. A borehole televiewer run in the open hole section showed evidence of more than eighty fractures. The majority of these fractures trend from N20⁰W to N20°E and dip from 40° to 60°W. Permeable fractures were encountered in the Elba Quartzite at 5,640-5,660 ft MD. Analysis of the injection test indicates that the minimum in-situ principal stress in this zone is 3,050-3,200 psi, corresponding to a fracture gradient of 0.59-0.62 psi/ft. A discrete fracture network model was developed using measured and inferred fracture orientations, distributions and dimensions. A three-phase stimulation program is proposed for RRG-9 ST-1. During the first two stages, water at 140°F, and later 40°F, will be injected to pre-condition and thermally fracture the reservoir. Here, the third stage will consist of a high rate, large volume conventional hydraulic stimulation.

Bradford, Jacob↗
DOE OSTI2022

Graph link prediction in computer networks using Poisson matrix factorisation

Graph link prediction is an important task in cybersecurity: relationships between entities within a computer network, such as users interacting with computers or system libraries and the corresponding processes that use them, can provide key insights into adversary behaviour. Poisson matrix factorisation (PMF) is a popular model for link prediction in large networks, particularly useful for its scalability. In this article PMF is extended to include scenarios that are commonly encountered in cybersecurity applications. Specifically, an extension is proposed to explicitly handle binary adjacency matrices and include known categorical covariates associated with the graph nodes. A seasonal PMF model is also presented to handle seasonal networks. To allow the methods to scale to large graphs, variational methods are discussed for performing fast inference. The results show an improved performance over the standard PMF model and other statistical network models.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

GNET2: an R package for constructing gene regulatory networks from transcriptomic data

Abstract Motivation The Gene Network Estimation Tool (GNET) is designed to build gene regulatory networks (GRNs) from transcriptomic gene expression data with a probabilistic graphical model. The data preprocessing, model construction and visualization modules of the original GNET software were developed on different programming platforms, which were inconvenient for users to deploy and use. Results Here, we present GNET2, an improved implementation of GNET as an integrated R package. GNET2 provides more flexibility for parameter initialization and regulatory module construction based on the core iterative modeling process of the original algorithm. The data exchange interface of GNET2 is handled within an R session automatically. Given the growing demand for regulatory network reconstruction from transcriptomic data, GNET2 offers a convenient option for GRN inference on large datasets. Availability and implementation The source code of GNET2 is available at https://github.com/jianlin-cheng/GNET2. Supplementary information Supplementary data are available at Bioinformatics online.

59 BASIC BIOLOGICAL SCIENCES↗