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 109 records · Page 6
All sourcesNASA NTRSDOE OSTI
DOE OSTI2021

Large-scale Gravitational Lens Modeling with Bayesian Neural Networks for Accurate and Precise Inference of the Hubble Constant

We investigate the use of approximate Bayesian neural networks (BNNs) in modeling hundreds of time delay gravitational lenses for Hubble constant (H 0 ) determination. Here, our BNN was trained on synthetic Hubble Space Telescope quality images of strongly lensed active galactic nuclei with lens galaxy light included. The BNN can accurately characterize the posterior probability density functions (PDFs) of model parameters governing the elliptical power-law mass profile in an external shear field. We then propagate the BNN-inferred posterior PDFs into an ensemble H 0 inference, using simulated time delay measurements from a plausible dedicated monitoring campaign. Assuming well-measured time delays and a reasonable set of priors on the environment of the lens, we achieve a median precision of 9.3% per lens in the inferred H 0 . A simple combination of a set of 200 test lenses results in a precision of 0.5 km s –1 Mpc –1 (0.7%), with no detectable bias in this H 0 recovery test. The computation time for the entire pipeline—including the generation of the training set, BNN training and H0 inference—translates to 9 minutes per lens on average for 200 lenses and converges to 6 minutes per lens as the sample size is increased. Being fully automated and efficient, our pipeline is a promising tool for exploring ensemble-level systematics in lens modeling for H 0 inference.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2021

Stochastic Gradient-Based Distributed Bayesian Estimation in Cooperative Sensor Networks

Distributed Bayesian inference provides a full quantification of uncertainty offering numerous advantages over point estimates that autonomous sensor networks are able to exploit. However, fully-decentralized Bayesian inference often requires large communication overheads and low network latency, resources that are not typically available in practical applications. In this paper, we propose a decentralized Bayesian inference approach based on stochastic gradient Langevin dynamics, which produces full posterior distributions at each of the nodes with significantly lower communication overhead. We provide analytical results on convergence of the proposed distributed algorithm to the centralized posterior, under typical network constraints. Finally, we also provide extensive simulation results to demonstrate the validity of the proposed approach.

42 ENGINEERING↗
DOE OSTI2023

Inference of cell type-specific gene regulatory networks on cell lineages from single cell omic datasets

Abstract Cell type-specific gene expression patterns are outputs of transcriptional gene regulatory networks (GRNs) that connect transcription factors and signaling proteins to target genes. Single-cell technologies such as single cell RNA-sequencing (scRNA-seq) and single cell Assay for Transposase-Accessible Chromatin using sequencing (scATAC-seq), can examine cell-type specific gene regulation at unprecedented detail. However, current approaches to infer cell type-specific GRNs are limited in their ability to integrate scRNA-seq and scATAC-seq measurements and to model network dynamics on a cell lineage. To address this challenge, we have developed single-cell Multi-Task Network Inference (scMTNI), a multi-task learning framework to infer the GRN for each cell type on a lineage from scRNA-seq and scATAC-seq data. Using simulated and real datasets, we show that scMTNI is a broadly applicable framework for linear and branching lineages that accurately infers GRN dynamics and identifies key regulators of fate transitions for diverse processes such as cellular reprogramming and differentiation.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2021

Deep Kronecker neural networks: A general framework for neural networks with adaptive activation functions

Here we propose a new type of neural networks, Kronecker neural networks (KNNs), that form a general framework for neural networks with adaptive activation functions. KNNs employ the Kronecker product, which provides an efficient way of constructing a very wide network while keeping the number of parameters low. Our theoretical analysis reveals that under suitable conditions, KNNs induce a faster decay of the loss than that by the feed-forward networks. This is also empirically verified through a set of computational examples. Furthermore, under certain technical assumptions, we establish global convergence of gradient descent for KNNs. As a specific case, we propose the Rowdy activation function that is designed to get rid of any saturation region by injecting sinusoidal fluctuations, which include trainable parameters. The proposed Rowdy activation function can be employed in any neural network architecture like feed-forward neural networks, Recurrent neural networks, Convolutional neural networks etc. The effectiveness of KNNs with Rowdy activation is demonstrated through various computational experiments including function approximation using feed-forward neural networks, solution inference of partial differential equations using the physics-informed neural networks, and standard deep learning benchmark problems using convolutional and fully-connected neural networks.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

A Data Processing Pipeline To Extract A Knowledge Graph From Sec Documents For Socio-technical Analysis Of Critical Infrastructure Influence

The code is written in Python and consists of the following pipeline that is implemented in Apache Airflow. This pipeline intends to understand the companies that are directly or indirectly involved with a type of critical infrastructure system at some point in that system's lifecycle. The pipeline takes a configuration file that specifies a list of initial companies to consider, a geographic region of interest (disk) expressed as a latitude/longitude point and distance, and a set of SEC form types from which to extract entities and relations. There are three main components to this pipeline as currently implemented: Social Network Extraction, Critical Infrastructure Network Extraction, and Inference and Fusion. First, Social Network Extraction, implemented as the `organizations_sec` component of the workflow graph queries the SEC EDGAR webservice using the list of initial companies from the configuration file. Given this, it extracts metadata that documents the number of each type of form for the given set of companies and their location. This forms metadata represents a catalog of data sources for the extracted social network knowledge graph. The pipeline then downloads these forms from the website and saves them in a build directory for further processing. These documents are then parsed for entities and relations. Second, the Critical Network Extraction component extracts entities and relations for a critical infrastructure sector. Currently, we focus on Electric Vehicle charging stations and this information is available via the Department of Energy (DOE) database on fueling stations maintained by NREL. Third, the Inference and Fusion component relates the social network graph to the critical infrastructure graph in order to understand the impact of a company within a geographic region. Relations include ownership of the EV Charging Station asset as well as maintenance/ownership of the EV payment networks. The fused network can be represented in many ways and currently we emit a knowledge graph.

Weaver, GabrielA.↗
DOE OSTI2024

Integrated analysis of X-ray diffraction patterns and pair distribution functions for machine-learned phase identification

Abstract To bolster the accuracy of existing methods for automated phase identification from X-ray diffraction (XRD) patterns, we introduce a machine learning approach that uses a dual representation whereby XRD patterns are augmented with simulated pair distribution functions (PDFs). A convolutional neural network is trained directly on XRD patterns calculated using physics-informed data augmentation, which accounts for experimental artifacts such as lattice strain and crystallographic texture. A second network is trained on PDFs generated via Fourier transform of the augmented XRD patterns. At inference, these networks classify unknown samples by aggregating their predictions in a confidence-weighted sum. We show that such an integrated approach to phase identification provides enhanced accuracy by leveraging the benefits of each model’s input representation. Whereas networks trained on XRD patterns provide a reciprocal space representation and can effectively distinguish large diffraction peaks in multi-phase samples, networks trained on PDFs provide a real space representation and perform better when peaks with low intensity become important. These findings underscore the importance of using diverse input representations for machine learning models in materials science and point to new avenues for automating multi-modal characterization.

36 MATERIALS SCIENCE↗
DOE OSTI2026

Assessing the Application of a Genomic Network Analysis in Population Ecology: Inferring Patterns of Dispersal and Geographic Structure in the Emerging Pathogen, Coccidioides

A challenge in population ecology studies is identifying how to best group individuals into populations, especially when individual origin is unknown. Machine learning has improved upon traditional methods of identifying population structure and is more efficient at handling large, complex datasets. We demonstrate the applicability of a machine learning method to identify hierarchical population structure in an emerging pathogen, Coccidioides spp., the causative agent of Valley fever. We compared the network clusters to structure identified by traditional tools as a validation of the network performance. We used publicly available whole-genome data for 48 C. immitis and 102 C. posadasii, resulting in 168,211 genome-wide SNPs among the two species. The network analysis grouped samples into populations comparable to the literature for these species but also identified fine-scale geographic structure and travel-associated cases not reported thus far. Exploring different resolutions in the network made it easy to identify unique genotypes specific to California and possibly Nevada, as well as Phoenix- and Tucson-acquired infections in non-endemic areas, regardless of reported travel history. The present study provides a promising example of how a ML-based network analysis can improve our ability to understand pathogen ecology, group cases into populations and infer travel-associated infections.

59 BASIC BIOLOGICAL SCIENCES↗
NASA NTRS2017

Network Analysis of Rodent Transcriptomes in Spaceflight

Network analysis methods leverage prior knowledge of cellular systems and the statistical and conceptual relationships between analyte measurements to determine gene connectivity. Correlation and conditional metrics are used to infer a network topology and provide a systems-level context for cellular responses. Integration across multiple experimental conditions and omics domains can reveal the regulatory mechanisms that underlie gene expression. GeneLab has assembled rich multi-omic (transcriptomics, proteomics, epigenomics, and epitranscriptomics) datasets for multiple murine tissues from the Rodent Research 1 (RR-1) experiment. RR-1 assesses the impact of 37 days of spaceflight on gene expression across a variety of tissue types, such as adrenal glands, quadriceps, gastrocnemius, tibalius anterior, extensor digitorum longus, soleus, eye, and kidney. Network analysis is particularly useful for RR-1 -omics datasets because it reinforces subtle relationships that may be overlooked in isolated analyses and subdues confounding factors. Our objective is to use network analysis to determine potential target nodes for therapeutic intervention and identify similarities with existing disease models. Multiple network algorithms are used for a higher confidence consensus.

genomics↗
DOE OSTI2022

Locating fast-varying line disturbances with the frequency mismatch

In an attempt to provide an efficient method for line disturbance identification in complex networks of diffusively coupled agents, we recently proposed to leverage the frequency mismatch. The frequency mismatch filters out the intricate combination of interactions induced by the network structure and quantifies to what extent the trajectory of each agent is affected by the disturbance. In this previous work, we provided some analytical evidence of its efficiency when the perturbation is assumed to be slow. Here we claim that the frequency mismatch performs actually well for most disturbance regimes. This is shown through a series of simulations and is backed up by an analytical argument. Therefore, we argue that the frequency mismatch is an efficient and elegant tool for line disturbance location in complex networks of diffusively coupled agents.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS2021

Identifying Planetary Transit Candidates in TESS Full-frame Image Light Curves via Convolutional Neural Networks

The Transiting Exoplanet Survey Satellite(TESS)mission measured light from stars in∼75% of the sky throughout its 2 yr primary mission, resulting in millions of TESS 30-minute-cadence light curves to analyze in the search for transiting exoplanets. To search this vast data trove for transit signals, we aim to provide an approach that both is computationally efficient and produces highly performant predictions. This approach minimizes the required human search effort. We present a convolutional neural network, which we train to identify planetary transit signals and dismiss false positives. To make a prediction for a given light curve, our network requires no prior transit parameters identified using other methods. Our network performs inference on a TESS 30-minute-cadence light curve in∼5 ms on a single GPU, enabling large-scale archival searches. We present 181 new planet candidates identified by our network, which pass subsequent human vetting designed to rule out false positives.Our neural network model is additionally provided as open-source code for public use and extension

Gregory Olmschenk↗
NASA NTRS2024

Short–Period Variables in TESS Full–Frame Image Light Curves Identified via Convolutional Neural Networks

The Transiting Exoplanet Survey Satellite (TESS) mission measured light from stars in ∼85% of the sky throughout its 2 yr primary mission, resulting in millions of TESS 30-minute-cadence light curves to analyze in the search for transiting exoplanets. To search this vast data set, we aim to provide an approach that is computationally efficient, produces accurate predictions, and minimizes the required human search effort. We present a convolutional neural network that we train to identify short-period variables. To make a prediction for a given light curve, our network requires no prior target parameters identified using other methods. Our network performs inference on a TESS 30-minute-cadence light curve in ∼5 ms on a single GPU, enabling large-scale archival searches. We present a collection of 14,156 short-period variables identified by our network. The majority of our identified variables fall into two prominent populations, one of close-orbit main-sequence binaries and another of δ Scuti stars. Our neural network model and related code are additionally provided as open-source code for public use and extension.

Convolutional neural networks↗
NASA NTRS1992

Evaluation Of Threshold Functions For Searches Among Data

Paper presents information-theoretical analysis of problem of building system of inferences from large collection of data (data base). More specifically, problem to design searches of data base for informative conjunctive production rules. Results of analysis may lead to design of more-economical and more-effective electronic neural networks drawing inferences from data bases.

Goodman, Rodney M.↗
DOE OSTI2024

Neuro-Spark: A Submicrosecond Spiking Neural Networks Architecture for In-Sensor Filtering

Neuro-Spark, which is a new neuromorphic architecture with a field-programmable gate array (FPGA) implementation for ultrafast spiking neural network (SNN) inference at the edge, facilitates smart-pixel in-sensor filtering for high-energy physics experiments at the Large Hadron Collider (LHC). Utilizing the evolutionary optimization for neuromorphic systems (EONS) training method, we generate compact SNN models with 91% signal efficiency, akin to convolutional neural networks but with half the parameters. However, deploying near the detector poses a challenge because the SNN must handle a sustained input data rate exceeding 1013 GB/s. To overcome this, we propose a novel hardware architecture that uses high-level synthesis to construct a tuned architecture for the EONS-trained SNN. In addition to the analysis and validation with an AMD Xilinx Artix-A7 FPGA, our solution consumes only ç24% of FPGA LUT and flipflops. We also introduce an innovative quantization method that reduces FPGA resource utilization by ç15% without compromising accuracy. Our FPGA implementation achieves computing latency of ç10 ns for smart-pixel application inference on an edge FPGA.

Miniskar, Narasinga Rao↗
DOE OSTI2023

Iterative multi-task learning and inference from seismic images

Seismic interpretation aims to extract quantitative and interpretable attributes from a seismic image produced using some migration method to inform characteristics of a subsurface reservoir or target of interest. Current paradigms for computing seismic attributes mostly rely on single-task algorithms. We develop an iterative, multi-task machine learning method to learn and infer multiple attributes from a seismic image. This method is composed of two stages: a multi-task inference stage and a multi-modal, multi-task refinement stage. The basic mechanism of this method is that we train a multi-task inference neural network (NN) to estimate a set of attributes, including a relative geological time (RGT), a denoised higher-resolution (DHR) seismic image, and multiple fault attributes (including probability, dip, and strike), from a low-resolution, noisy seismic image; then we input the inferred attributes to a multi-task refinement NN to enhance the raw inference results iteratively. The two multi-task NNs are trained separately based on synthetic seismic images and associated attributes generated by a geological modeling algorithm. The software we intend to release is a PyTorch implementation of this multi-task learning method for both 2D and 3D cases along with scripts to run the training/validation. The algorithm and software can be a useful tool for automatic seismic interpretation.

Gao, Kai↗
DOE OSTI2022

Deep-learning-guided high-resolution subsurface reflectivity imaging with application to ground-penetrating radar data

Subsurface reflectivity imaging is one of the most important geophysical characterization methods for revealing subsurface structures. In many cases, accurate subsurface reflectivity imaging is challenging because of, for example, random or coherent noise in the data and sparse source-receiver observation geometry. Here, we develop a deep-learning-guided iterative imaging method to improve subsurface structure imaging. Specifically, we train a supervised neural network to infer a noise-free, high-resolution image from a noisy, low-resolution image and use this estimated image as guidance to regularize least-squares imaging. We develop a systematic method to generate high-quality synthetic training data (data-label pairs) to train the guidance neural network. The trained neural network can provide high-fidelity predictions even for field-data images that are not in the training data. We validate our new imaging method using one synthetic and two field ground-penetrating radar data examples, and find that our method can produce clean, high-resolution subsurface reflectivity images where existing single-pass and least-squares imaging methods fail due to noise and insufficient data coverage.

58 GEOSCIENCES↗
NASA NTRS2015

Prediction of Tensile Strength of Friction Stir Weld Joints with Adaptive Neuro-Fuzzy Inference System (ANFIS) and Neural Network

Friction-stir-welding (FSW) is a solid-state joining process where joint properties are dependent on welding process parameters. In the current study three critical process parameters including spindle speed (𝑁), plunge force (𝐹𝑧), and welding speed (𝑉) are considered key factors in the determination of ultimate tensile strength (UTS) of welded aluminum alloy joints. A total of 73 weld schedules were welded and tensile properties were subsequently obtained experimentally. It is observed that all three process parameters have direct influence on UTS of the welded joints. Utilizing experimental data, an optimized adaptive neuro-fuzzy inference system (ANFIS) model has been developed to predict UTS of FSW joints. A total of 1200 models were developed by varying the number of membership functions (MFs), type of MFs, and combination of four input variables (𝑁,𝑉,𝐹𝑧,𝐸𝐹𝐼) utilizing a MATLAB platform. Note EFI denotes an empirical force index derived from the three process parameters. For comparison, optimized artificial neural network (ANN) models were also developed to predict UTS from FSW process parameters. By comparing ANFIS and ANN predicted results, it was found that optimized ANFIS models provide better results than ANN. This newly developed best ANFIS model could be utilized for prediction of UTS of FSW joints.

Mohammad W Dewan↗
NASA NTRS2012

Are the Basins of Tui Regio and Hotei Arcus Sites of Former Titanian Seas?

Features observed in the basins of Tui Regio and Hotei Arcus on Titan have attracted the attention of the Cassini-era investigators. At both locations, VIMS observed discrete 5-micron bright approx.500-km wide features described as lobate in shape. Several studies have proposed that these materials are cryo-volcanic flows; in the case of the Hotei Arcus feature this inference was buttressed with SAR RADAR images showing bright and dark patches with lobate margins. We propose an alternative explanation. First we note that all landforms on Titan that are unambiguously identifiable can be explained by exogenic processes (aeolian, fluvial, impact cratering, and mass wasting). Suggestions of endogenically produced cryovolcanic constructs and flows have, without exception, lacked conclusive diagnostic evidence. Recently published topographic profiles across Tui Regio and the lobate feature region north of Hotei Arcus indicate these features appear to occur in large regional basins, at least along the direction of the profiles. SAR images show that the terrains surrounding both 5-micron bright features exhibit fluvial networks that appear to converge and debauch into the probable basins. The 5-micron bright features themselves correspond to fields of discrete radar-bright depressions whose bounding edges are commonly rounded and cumulate in planform in SAR images. These fields of discrete radar-bright depressions strongly resemble fields of features seen at Titan s high latitudes usually attributed to be dry lakes. Thus the combination of (1) the resemblance to high-latitude dry lakes, (2) location in the centers of probable regional depressions, and (3) convergence of fluvial networks are inferred by us to best explain the 5-micron bright regions at Tui Regio and Hotei Arcus as sites of dry seas or at least paleolake clusters. Such equatorial seas, if real, may be evidence of substantially larger inventories of liquid alkanes in Titan s past.

Moore, Jeffrey Morgan↗
DOE OSTI2020

Adapting In Situ Accelerators for Sparsity With Granular Matrix Reordering

Neural network (NN) inference is an essential part of modern systems and is found at the heart of numerous applications ranging from image recognition to natural language processing. In situ NN accelerators can efficiently perform NN inference using resistive crossbars, which makes them a promising solution to the data movement challenges faced by conventional architectures. Although such accelerators demonstrate significant potential for dense NNs, they often do not benefit from sparse NNs, which contain relatively few non-zero weights. Processing sparse NNs on in situ accelerators results in wasted energy to charge the entire crossbar where most elements are zeros. To address this limitation, this paper proposes Granular Matrix Reordering (GMR): a preprocessing technique that enables an energy-efficient computation of sparse NNs on in situ accelerators. GMR reorders the rows and columns of sparse weight matrices to maximize the crossbars' utilization and minimize the total number of crossbars needed to be charged. The reordering process does not rely on sparsity patterns and incurs no accuracy loss. Finally, GMR achieves an average of 28% and up to 34% reduction in energy consumption over seven pruned NNs across four different pruning methods and network architectures.

97 MATHEMATICS AND COMPUTING↗