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 901 records · Page 50
All sourcesNASA NTRSDOE OSTI
DOE OSTI2021

Unsupervised Resource Allocation with Graph Neural Networks

We present an approach for maximizing a global utility function by learning how to allocate resources in an unsupervised way. We expect interactions between allocation targets to be important and therefore propose to learn the reward structure for near-optimal allocation policies with a GNN. By relaxing the resource constraint, we can employ gradient-based optimization in contrast to more standard evolutionary algorithms. Our algorithm is motivated by a problem in modern astronomy, where one needs to select-based on limited initial information-among $10^9$ galaxies those whose detailed measurement will lead to optimal inference of the composition of the universe. Our technique presents a way of flexibly learning an allocation strategy by only requiring forward simulators for the physics of interest and the measurement process. We anticipate that our technique will also find applications in a range of resource allocation problems.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2026

Learning genetic perturbation effects with variational causal inference

Advances in sequencing technologies have enhanced the understanding of gene regulation in cells. In particular, Perturb-seq has enabled high-resolution profiling of the transcriptomic response to genetic perturbations at the single-cell level. This understanding has implications in functional genomics and potentially for identifying therapeutic targets. Various computational models have been developed to predict perturbational effects. While deep learning models excel at interpolating observed perturbational data, they tend to overfit in the lack of enough data and may not generalize well to unseen perturbations. In contrast, mechanistic models, such as linear causal models based on gene regulatory networks, hold greater potential for extrapolation, as they encapsulate regulatory information that can predict responses to unseen perturbations. However, their application has been limited to small studies due to overly simplistic assumptions, making them less effective in handling noisy, large-scale single-cell data. We propose a hybrid approach that combines a mechanistic causal model with variational deep learning, termed Single Cell Causal Variational Autoencoder (SCCVAE). The mechanistic model employs a learned regulatory network to represent perturbational changes as shift interventions that propagate through the learned network. SCCVAE integrates this mechanistic causal model into a variational autoencoder, generating rich, comprehensive transcriptomic responses. Our results indicate that SCCVAE exhibits superior performance over current state-of-the-art baselines for extrapolating to predict unseen perturbational responses. Additionally, for the observed perturbations, the latent space learned by SCCVAE allows for the identification of functional perturbation modules and simulation of single-gene knockdown experiments of varying penetrance, presenting a robust tool for interpreting and interpolating perturbational responses at the single-cell level.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2024

Accelerating data acquisition with FPGA-based edge machine learning: a case study with LCLS-II

New scientific experiments and instruments generate vast amounts of data that need to be transferred for storage or further processing, often overwhelming traditional systems. Edge machine learning (EdgeML) addresses this challenge by integrating machine learning (ML) algorithms with edge computing, enabling real-time data processing directly at the point of data generation. EdgeML is particularly beneficial for environments where immediate decisions are required, or where bandwidth and storage are limited. In this paper, we demonstrate a high-speed configurable ML model in a fully customizable EdgeML system using a field programmable gate array (FPGA). Our demonstration focuses on an angular array of electron spectrometers, referred to as the ‘CookieBox,’ developed for the Linac Coherent Light Source II project. The EdgeML system captures 51.2 Gbps from a 6.4 GS s −1 analog to digital converter and is designed to integrate data pre-processing and ML inside an FPGA. Our implementation achieves an inference latency of 0.2 µs for the ML model, and a total latency of 0.4 µs for the complete EdgeML system, which includes pre-processing, data transmission, digitization, and ML inference. The modular design of the system allows it to be adapted for other instrumentation applications requiring low-latency data processing.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Attend and Decode: 4D fMRI Task State Decoding Using Attention Models

Source code for Brain Attend and Decode paper. Functional magnetic resonance imaging (fMRI) is a neuroimaging modality that captures the blood oxygen level in a subject's brain while the subject either rests or performs a variety of functional tasks under different conditions. Given fMRI data, the problem of inferring the task, known as task state decoding, is challenging due to the high dimensionality (hundreds of million sampling points per datum) and complex spatio-temporal blood flow patterns inherent in the data. In this work, we propose to tackle the fMRI task state decoding problem by casting it as a 4D spatiotemporal classification problem. We present a novel architecture called Brain Attend and Decode (BAnD), that uses residual convolutional neural networks for spatial feature extraction and self-attention mechanisms for temporal modeling. We achieve significant performance gain compared to previous works on a 7-task benchmark from the large-scale Human Connectome Project-Young Adult (HCP-YA) dataset. We also investigate the transferability of BAnD's extracted features on unseen HCP tasks, either by freezing the spatial feature extraction layers and retraining the temporal model, or finetuning the entire model. The pre-trained features from BAnD are useful on similar tasks while finetuning them yields competitive results on unseen tasks/conditions.

Ng, BrendaM.↗
DOE OSTI2022

QuantumNAT: quantum noise-aware training with noise injection, quantization and normalization

Parameterized Quantum Circuits (PQC) are promising towards quantum advantage on near-term quantum hardware. However, due to the large quantum noises (errors), the performance of PQC models has a severe degradation on real quantum devices. Take Quantum Neural Network (QNN) as an example, the accuracy gap between noise-free simulation and noisy results on IBMQ-Yorktown for MNIST-4 classification is over 60%. Existing noise mitigation methods are general ones without leveraging unique characteristics of PQC; on the other hand, existing PQC work does not consider noise effect. To this end, we present QuantumNAT, a PQC-specific framework to perform noise-aware optimizations in both training and inference stages to improve robustness. We experimentally observe that the effect of quantum noise to PQC measurement outcome is a linear map from noise-free outcome with a scaling and a shift factor. Motivated by that, we propose post-measurement normalization to mitigate the feature distribution differences between noise-free and noisy scenarios. Furthermore, to improve the robustness against noise, we propose noise injection to the training process by inserting quantum error gates to PQC according to realistic noise models of quantum hardware. Lastly, post-measurement quantization is introduced to quantize the measurement outcomes to discrete values, achieving the denoising effect. Extensive experiments on 8 classification tasks using 6 quantum devices demonstrate that QuantumNAT improves accuracy by up to 43%, and achieves over 94% 2-class, 80% 4-class, and 34% 10-class classification accuracy measured on real quantum computers. The code for construction and noise-aware training of PQC is available in the TorchQuantum library.

Wang, Hanrui↗
DOE OSTI2022

Learning Global Proliferation Expertise Evolution Using AI-Driven Analytics and Public Information

Detecting and anticipating global proliferation expertise and capability evolution from unstructured, noisy, and incomplete public data streams is a highly desired, but extremely challenging task. Here, in this article, we present our pioneering data-driven approach to support the non-proliferation mission to detect and explain the evolution of proliferation expertise and capability development globally from terabytes of publicly available information (PAI), focusing on our knowledge extraction pipeline and descriptive analytics. We first discuss how we fuse nine open-source data streams, including multilingual data, to convert 4 TB of unstructured data to structured knowledge and encode dynamically evolving proliferation expertise representations—content and context graphs. For this, we rely on natural language processing (NLP) and deep learning (DL) models to perform information extraction, topic modeling, and distributed text representation (aka embedding) learning. We then present interactive, usable, and explainable descriptive analytics to refine domain knowledge and present it in a human-understandable form. Finally, we introduce future work avenues that will leverage our dynamic knowledge representations and descriptive analytics to enable predictive and prescriptive inferences to achieve real-time domain understanding and contextual reasoning about global proliferation expertise and capability evolution.

98 NUCLEAR DISARMAMENT, SAFEGUARDS, AND PHYSICAL P↗
DOE OSTI2026

Discovery of Probabilistic Dirichlet-to-Neumann Maps on Graphs

Dirichlet-to-Neumann maps enable the coupling of multiphysics simulations across computational subdomains by ensuring continuity of state variables and fluxes at artificial interfaces. We present a novel method for learning Dirichlet-to-Neumann maps on graphs using Gaussian processes, specifically for problems where the data obey a conservation law arising from an underlying partial differential equation. Our approach combines discrete exterior calculus and nonlinear optimal recovery to infer relationships between vertex and edge values. This framework yields data-driven predictions with uncertainty quantification across the entire graph, even when observations are limited to a subset of vertices and edges. By minimizing the reproducing kernel Hilbert space norm while penalizing kernel complexity through maximum likelihood estimation, our method ensures that the resulting surrogate strictly enforces conservation laws without overfitting. We demonstrate our method on two representative applications: subsurface flow in fracture networks and arterial blood flow. Finally, the results demonstrate that the method maintains high accuracy and well-calibrated uncertainty estimates even under severe data scarcity, highlighting its potential for scientific applications where limited data and reliable uncertainty quantification are critical.

Dirichlet-to-Neumann map↗
NASA NTRS2008

Classification of Small Negative Lightning Reports at the KSC-ER

The NASA Kennedy Space Center (KSC) and Air Force Eastern Range (ER) operate an extensive suite of lightning sensors because Florida experiences the highest area density of ground strikes in the United States, with area densities approaching 16 fl/sq km/yr when accumulated in 10x10 km (100 sq km) grids. The KSC-ER use data derived from two cloud-to-ground (CG) lightning detection networks, the "Cloud-to-Ground Lightning Surveillance System" (CGLSS) and the U.S. National Lightning Detection Network (TradeMark) (NLDN) plus a 3-dimensional lightning mapping system, the Lightning Detection and Ranging (LDAR) system, to provide warnings for ground operations and to insure mission safety during space launches. For operational applications at the KSC-ER it is important to understand the performance of each lightning detection system in considerable detail. In this work we examine a specific subset of the CGLSS stroke reports that have low values of the negative inferred peak current, Ip, i.e. values between 0 and -7 kA, and were thought to produce a new ground contact (NGC). When possible, the NLDN and LDAR systems were used to validate the CGLSS classification and to determine how many of these reported strokes were first strokes, subsequent strokes in a pre-existing channel (PEC), or cloud pulses that the CGLSS misclassified as CG strokes. It is scientifically important to determine the smallest current that can reach the ground either in the form of a first stroke or by way of a subsequent stroke that creates a new ground contact. In Biagi et al (2007), 52 low amplitude, negative return strokes ([Ip] < or = 10 kA) were evaluated in southern Arizona, northern Texas, and southern Oklahoma. The authors found that 50-87% of the small NLDN reports could be classified as CG (either first or subsequent strokes) on the basis of video and waveform recordings. Low amplitude return strokes are interesting because they are usually difficult to detect, and they are thought to bypass conventional lightning protection that relies on a sufficient attractive radius to prevent "shielding failure" (Golde, 1977). They also have larger location errors compared to the larger current events. In this study, we use the estimated peak current provided by the CGLSS and the results of our classification to determine the minimum Ip for each category of CG stroke and its probability of occurrence. Where possible, these results are compared to the findings in the literature.

Ward, Jennifer G.↗
NASA NTRS2019

The Entry Descent and Landing Instrumentation (MEDLI2) Suite for the Mars 2020 Mission

This presentation will discuss the current state of each of the main measurements systems for MEDLI2. The first system is a network of pressure transducers, the Mars Entry Atmospheric Data System (MEADS). Improving upon MEDLI, separate MEDLI2 pressure transducers span the measurement range suitable for both hypersonic and supersonic flows. The MEADS will also measure pressure on the backshell of the vehicle to better characterize the contribution of backshell pressure on the overall forces and moments on the entry probe. The second system is the thermal instrumentation, or Mars Instrumented Sensor Plugs. This system includes a network of high-temperature thermocouples embedded in the thermal protection system across the heatshield and backshell. The MISP also includes two types of sensors for directly measuring incident heatflux on the backshell of the vehicle. In addition, a radiometer is included on the backshell to measure radiative heating. The presentation will also cover the current state of the MEDLI2 hardware, expected environments that will be measured, and data analysis techniques being developed to infer vehicle entry performance from both the MISP and MEADS sensor systems.

White, Todd↗
DOE OSTI2025

Single-qubit multi-party transmission using universal symmetric quantum cloning

This study considers the hypothetical quantum network case where Alice wishes to transmit one qubit of information (specifically a pure quantum state) to M parties, where M is some large number. The remote receivers locally perform single-qubit quantum state tomography on the transmitted qubits in order to compute the quantum state within some error rate (dependent on the tomography technique and the number of transmitted qubits). We show that with the use of an intermediate optimal symmetric universal quantum cloning machine (between Alice and the remote receivers) as a repeater-type node in a hypothetical quantum network, Alice can send significantly fewer qubits compared to direct transmission of the message qubits to each of the M remote receivers. This is possible due to two properties of quantum cloning. The first is that single qubit quantum clones retain the same Bloch angle as the initial quantum state. This means that if the mixed state of the quantum clone can be computed to high enough accuracy, the original pure quantum state can be inferred by extrapolating that vector to the surface of the Bloch sphere. The second property is that the state overlap of approximate quantum clones, with respect to the original pure quantum state, quickly converges (specifically for 1 → M , the limit of the fidelity as M goes to infinity is $\frac{2}{3}$). This means that Alice can prepare a constant number of qubits (which are then passed through the quantum cloning machine) in order to achieve a desired error rate if M is large enough. Combined, these two properties mean that for a large M , Alice can prepare many orders of magnitude fewer qubits in order to achieve the same single qubit transmission accuracy compared to the naive direct qubit transmission approach.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2023

Smart Pixels: towards on-sensor inference of charged particle track parameters and uncertainties

The combinatorics of track seeding has long been a computational bottleneck for triggering and offline computing in High Energy Physics (HEP), and remains so for the HL-LHC. Next-generation pixel sensors will be sufficiently fine-grained to determine angular information of the charged particle passing through from pixel-cluster properties. This detector technology immediately improves the situation for offline tracking, but any major improvements in physics reach are unrealized since they are dominated by lowest-level hardware trigger acceptance. We will demonstrate track angle and hit position prediction, including errors, using a mixture density network within a single layer of silicon as well as the progress towards and status of implementing the neural network in hardware on both FPGAs and ASICs.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2023

Smart Pixels: towards on-sensor inference of charged particle track parameters and uncertainties

The combinatorics of track seeding has long been a computational bottleneck for triggering and offline computing in High Energy Physics (HEP), and remains so for the HL-LHC. Next-generation pixel sensors will be sufficiently fine-grained to determine angular information of the charged particle passing through from pixel-cluster properties. This detector technology immediately improves the situation for offline tracking, but any major improvements in physics reach are unrealized since they are dominated by lowest-level hardware trigger acceptance. We will demonstrate track angle and hit position prediction, including errors, using a mixture density network within a single layer of silicon as well as the progress towards and status of implementing the neural network in hardware on both FPGAs and ASICs.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2023

Smartpixels: Towards on-sensor inference of charged particle track parameters and uncertainties

The combinatorics of track seeding has long been a computational bottleneck for triggering and offline computing in High Energy Physics (HEP), and remains so for the HL-LHC. Next-generation pixel sensors will be sufficiently fine-grained to determine angular information of the charged particle passing through from pixel-cluster properties. This detector technology immediately improves the situation for offline tracking, but any major improvements in physics reach are unrealized since they are dominated by lowest-level hardware trigger acceptance. We will demonstrate track angle and hit position prediction, including errors, using a mixture density network within a single layer of silicon as well as the progress towards and status of implementing the neural network in hardware on both FPGAs and ASICs.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2021

Measuring Fault Zone and Host Rock Hydraulic Properties Using Tidal Responses

Pore pressure diffusion along faults influences induced seismicity and rupture mechanics. In situ hydraulic diffusivity measurements along faults are rare and generally lower than inferred from seismicity migration. Here we use the tidal response of deep geothermal boreholes to measure fault diffusivity and permeability. Initial interpretations of the observation with a homogeneous confined aquifer model result in diffusivities of 10 -3 –10 -1 m 2 /s. However, this model mixes signals from both the conduit and the host rock. We develop a model for tidal response with a fault passing through the aquifer based on the fault-guided fracture network and solve for hydraulic properties in both the fault and the host rock. The resulting fault permeability is 2 × 10 -14 –7 × 10 -14 m 2 (90% confidence interval[CI]) and fault diffusivity is 0.08–0.33 m 2 /s (90% CI), which is 2 orders of magnitude higher than the host rock diffusivity in some wells, thus highlighting the role of faults as fluid conduits.

58 GEOSCIENCES↗
DOE OSTI2023

Early Alarm: Robust Event Analysis for Power Systems using 1-D Fully Convolutional Network

This work presents a novel deep learning model for early, accurate, and robust detection, recognition, and temporal localization of multi-type events in large-scale power systems. The proposed method develops a unified 1-D fully convolutional network (FCN) model that takes time series of raw frequency signals measured from a power system as input, extracts distinguishing features, and predicts at every temporal point in the time series if an event is happening and what the type of the event is. Compared to existing methods, the proposed model eliminates the necessity for hand-crafted feature extraction or complicated data pre-processing, can flexibly handle input signals of arbitrary length, and precisely infer the event occurrence time. Most importantly, the model is intentionally trained with incomplete patterns, such that it is more robust to partial features of an event which is common in real-world online recognition, resulting in early alarm for power system failures. Extensive experimental results demonstrate that the proposed method achieves superior performance to the state-of-the-art, and also shows strong robustness to noise and system oscillations.

Li, Chengcheng↗
NASA NTRS1993

Structure identification in fuzzy inference using reinforcement learning

In our previous work on the GARIC architecture, we have shown that the system can start with surface structure of the knowledge base (i.e., the linguistic expression of the rules) and learn the deep structure (i.e., the fuzzy membership functions of the labels used in the rules) by using reinforcement learning. Assuming the surface structure, GARIC refines the fuzzy membership functions used in the consequents of the rules using a gradient descent procedure. This hybrid fuzzy logic and reinforcement learning approach can learn to balance a cart-pole system and to backup a truck to its docking location after a few trials. In this paper, we discuss how to do structure identification using reinforcement learning in fuzzy inference systems. This involves identifying both surface as well as deep structure of the knowledge base. The term set of fuzzy linguistic labels used in describing the values of each control variable must be derived. In this process, splitting a label refers to creating new labels which are more granular than the original label and merging two labels creates a more general label. Splitting and merging of labels directly transform the structure of the action selection network used in GARIC by increasing or decreasing the number of hidden layer nodes.

Berenji, Hamid R.↗
NASA NTRS2007

OTD Observations of Continental US Ground and Cloud Flashes

Lightning optical flash parameters (e.g., radiance, area, duration, number of optical groups, and number of optical events) derived from almost five years of Optical Transient Detector (OTD) data are analyzed. Hundreds of thousands of OTD flashes occurring over the continental US are categorized according to flash type (ground or cloud flash) using US National Lightning Detection Network TM (NLDN) data. The statistics of the optical characteristics of the ground and cloud flashes are inter-compared on an overall basis, and as a function of ground flash polarity. A standard two-distribution hypothesis test is used to inter-compare the population means of a given lightning parameter for the two flash types. Given the differences in the statistics of the optical characteristics, it is suggested that statistical analyses (e.g., Bayesian Inference) of the space-based optical measurements might make it possible to successfully discriminate ground and cloud flashes a reasonable percentage of the time.

Koshak, William↗
NASA NTRS2017

Deriving Global OH Abundance and Atmospheric Lifetimes for Long-Lived Gases: A Search for CH3CCl3 Alternatives

An accurate estimate of global hydroxyl radical (OH) abundance is important for projections of air quality, climate, and stratospheric ozone recovery. As the atmospheric mixing ratios of methyl chloroform (CH3CCl3) (MCF), the commonly used OH reference gas, approaches zero, it is important to find alternative approaches to infer atmospheric OH abundance and variability. The lack of global bottom-up emission inventories is the primary obstacle in choosing a MCF alternative. We illustrate that global emissions of long-lived trace gases can be inferred from their observed mixing ratio differences between the Northern Hemisphere (NH) and Southern Hemisphere (SH), given realistic estimates of their NH-SH exchange time, the emission partitioning between the two hemispheres, and the NH versus SH OH abundance ratio. Using the observed long-term trend and emissions derived from the measured hemispheric gradient, the combination of HFC-32 (CH2F2), HFC-134a (CH2FCF3, HFC-152a (CH3CHF2), and HCFC-22 (CHClF2), instead of a single gas, will be useful as a MCF alternative to infer global and hemispheric OH abundance and trace gas lifetimes. The primary assumption on which this multispecies approach relies is that the OH lifetimes can be estimated by scaling the thermal reaction rates of a reference gas at 272 K on global and hemispheric scales. Thus, the derived hemispheric and global OH estimates are forced to reconcile the observed trends and gradient for all four compounds simultaneously. However, currently, observations of these gases from the surface networks do not provide more accurate OH abundance estimate than that from MCF.

Lifetime↗