Search NASA⌕ Search

SEARCH · Search NASA

Results for “neural resources”

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 289 records · Page 16
All sourcesNASA NTRSDOE OSTI
NASA NTRSDate not supplied

Cislunar Trajectory Design and Maneuver Autonomy for NASA's Moon to Mars Architecture

NASA’s Moon to Mars architecture is an ambitious roadmap of manned cislunar and deep space exploration. The extensive amount of orbital assets required will place a significant burden on ground-based resources, such as communication networks and operations facilities. Spacecraft autonomy is essential for maintaining a vast number of complex missions beyond Earth orbit. To achieve full autonomy, spacecraft must be able to employ methods of robust maneuver design without an explicit dependence on commands sent from the ground. This level of autonomy is needed not only for stationkeeping, but also for outbound transfers. To address the need of spacecraft maneuver design autonomy, this work investigates the use of neural networks (NNs) in a supervised learning environment. A supervised learning approach for NNs allows for a curated training data set, consisting exclusively of perturbations applied to a desired mission concept of operations (ConOps). The proposed approach allows humans on the ground to design a specific mission ConOps before flight, then employ NNs to fly the mission robustly and autonomously. This investigation numerically tests maneuver autonomy in four highly sensitive regions of flight: orbit raising, translunar injection burns, powered lunar flybys, and invariant manifold insertion burns. These straining cases are contextualized by testing them in a demonstration mission, targeting an Earth-Moon L3 orbit. The study first establishes feasibility by automating impulsive burn maneuvers. However, some guidance algorithms will need more intensive commands, such as inertial pointing and angular rates. To validate this method, NN maneuver autonomy is applied to a finite burn model of the demonstration mission. The use of sequential, mission specific maneuvers provide an appropriate testbed to demonstrate the robustness of a NN trained on feasible perturbed states. Moreover, these scenarios provide preliminary proof-of-concept for fully autonomous missions that execute maneuvers without dependence upon explicit command uplinks. As a result, the technological advancement proposed in this work may significantly ease the strain on ground-based mission operations. This would enable complex and autonomous mission execution in cislunar and deep space regimes, filling a technology gap required to support future manned missions.

NASA↗
DOE OSTI2023

Data-Driven Affinely Adjustable Robust Volt/VAr Control

Recent years have seen the increasing proliferation of distributed energy resources with intermittent power outputs, posing new challenges to the voltage management in distribution networks. To this end, this paper proposes a data-driven affinely adjustable robust Volt/VAr control (AARVVC) scheme, which modulates the smart inverter’s reactive power in an affine function of its active power, based on the voltage sensitivities with respect to real/reactive power injections. To achieve a fast and accurate estimation of voltage sensitivities, we propose a data-driven method based on deep neural network (DNN), together with a rule-based bus-selection process using the bidirectional search method. Our method only uses the operating statuses of selected buses as inputs to DNN, thus significantly improving the training efficiency and reducing information redundancy. Finally, a distributed consensus-based solution, based on the alternating direction method of multipliers (ADMM), for the AARVVC is applied to decide the inverter’s reactive power adjustment rule with respect to its active power. Only limited information exchange is required between each local agent and the central agent to obtain the slope of the reactive power adjustment rule, and there is no need for the central agent to solve any (sub)optimization problems. Finally, numerical results on the modified IEEE-123 bus system validate the effectiveness and superiority of the proposed data-driven AARVVC method.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2026

Learned adaptive properties for mitigation of weight perturbations in embedded spiking networks

Recent years have seen an increased importance of neural network inference in edge-based scenarios, which impose size and power constraints requiring novel computing devices. These same edge scenarios may require operating over long periods of time, or exposure to extreme environments, resulting in a drift of neural network weights that cause degraded performance. In searching for ways to develop neural network approaches that perform robustly under these conditions, we propose a biologically-inspired mechanism for the dynamic adaptation of within-neuron parameters that is guided by a global context signal carrying information about perturbations and variability in incoming stimuli. Specifically, we demonstrate that adaptive voltage thresholds or neuronal time constants, when informed by a global context signal, can enable network-level mechanisms to recover from perturbed synaptic weights. Consistent with prior literature, the context-modulated approach is effective for recurrent, but not feedforward networks, by modulating network level dynamics. We demonstrate this approach successfully recovers performance in image classification tasks and spatiotemporal tracking tasks under idealized and Gaussian noise as well as for realistic perturbations from a memristive device when exposed to ionizing radiation. Finally, we discuss how this approach enables the design of robust and energy-efficient neuromorphic systems that perform well, even in resource-constrained scenarios with extreme environments such as edge processing.

context modulation↗
DOE OSTI2023

Bi-fidelity modeling of uncertain and partially unknown systems using DeepONets

Recent advances in modeling large-scale, complex physical systems have shifted research focuses towards data-driven techniques. However, generating datasets by simulating complex systems can require significant computational resources. Similarly, acquiring experimental datasets can prove difficult. For these systems, often computationally inexpensive, but in general inaccurate models, known as the low-fidelity models, are available. Here in this paper, we propose a bi-fidelity modeling approach for complex physical systems, where we model the discrepancy between the true system's response and a low-fidelity response in the presence of a small training dataset from the true system's response using a deep operator network, a neural network architecture suitable for approximating nonlinear operators. We apply the approach to systems that have parametric uncertainty and are partially unknown. Three numerical examples are used to show the efficacy of the proposed approach to model uncertain and partially unknown physical systems.

MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Machine Learning–Adjusted WRF Forecasts to Support Wind Energy Needs in Black Start Operations

Abstract The push for increased capacity of renewable sources of electricity has led to the growth of wind-power generation, with a need for accurate forecasts of winds at hub height. Forecasts for these levels were uncommon until recently, and that, combined with the nocturnal collapse of the well-mixed boundary layer and daytime growth of the boundary layer through the levels important for energy generation, has contributed to errors in numerical modeling of wind generation resources. The present study explores several machine learning algorithms to both forecast and correct standard WRF Model forecasts of winds and temperature at hub height within wind turbine plants over several different time periods that are critical for the anticipation of potential blackouts and aiding in black start operations on the power grid. It was found that mean square error for day-2 wind forecasts from the WRF Model can be improved by over 90% with the use of a multioutput neural network, and that 60-min forecasts of WRF error, which can then be used to adjust forecasts, can be made with an LSTM with great accuracy. Nowcasting of temperature and wind speed over a 10-min period using an LSTM produced very low error and especially skillful forecasts of maximum and minimum values over the turbine plant area.

17 WIND ENERGY↗
DOE OSTI2021

Galaxy Zoo DECaLS: Detailed visual morphology measurements from volunteers and deep learning for 314,000 galaxies

We present Galaxy Zoo DECaLS: detailed visual morphological classifications for Dark Energy Camera Legacy Survey images of galaxies within the SDSS DR8 footprint. Deeper DECaLS images (r = 23.6 versus r = 22.2 from SDSS) reveal spiral arms, weak bars, and tidal features not previously visible in SDSS imaging. To best exploit the greater depth of DECaLS images, volunteers select from a new set of answers designed to improve our sensitivity to mergers and bars. Galaxy Zoo volunteers provide 7.5 million individual classifications over 314 000 galaxies. 140 000 galaxies receive at least 30 classifications, sufficient to accurately measure detailed morphology like bars, and the remainder receive approximately 5. All classifications are used to train an ensemble of Bayesian convolutional neural networks (a state-of-the-art deep learning method) to predict posteriors for the detailed morphology of all 314 000 galaxies. We use active learning to focus our volunteer effort on the galaxies which, if labelled, would be most informative for training our ensemble. When measured against confident volunteer classifications, the trained networks are approximately 99 per cent accurate on every question. Morphology is a fundamental feature of every galaxy; our human and machine classifications are an accurate and detailed resource for understanding how galaxies evolve.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2025

End-to-End Workflow for Machine-Learning-Based Qubit Readout With QICK and hls4ml

In this article, we present an end-to-end workflow for superconducting qubit readout that embeds codesigned neural networks into the quantum instrumentation control kit (QICK). Capitalizing on the custom firmware and software of the QICK platform, which is built on Xilinx radiofrequency system-on-chip field-programmable gate arrays (FPGAs), we aim to leverage machine learning (ML) to address critical challenges in qubit readout accuracy and scalability. The workflow utilizes the hls4ml package and employs quantization-aware training to translate ML models into hardware-efficient FPGA implementations via user-friendly Python application programming interfaces. We experimentally demonstrate the design, optimization, and integration of an ML algorithm for single transmon qubit readout, achieving 96% single-shot fidelity with a latency of 32.25 ns and less than 16% FPGA lookup table resource utilization. Our results offer the community an accessible workflow to advance ML-driven readout and adaptive control in quantum information processing applications.

42 ENGINEERING↗
DOE OSTI2021

Spatial Mode Correction of Single Photons Using Machine Learning

Abstract Spatial modes of light constitute valuable resources for a variety of quantum technologies ranging from quantum communication and quantum imaging to remote sensing. Nevertheless, their vulnerabilities to phase distortions, induced by random media, impose significant limitations on the realistic implementation of numerous quantum‐photonic technologies. Unfortunately, this problem is exacerbated at the single‐photon level. Over the last two decades, this challenging problem has been tackled through conventional schemes that utilize optical nonlinearities, quantum correlations, and adaptive optics. In this article, the self‐learning and self‐evolving features of artificial neural networks are exploited to correct the complex spatial profile of distorted Laguerre–Gaussian modes at the single‐photon level. Furthermore, the potential of this technique is used to improve the channel capacity of an optical communication protocol that relies on structured single photons. The results have important implications for real‐time turbulence correction of structured photons and single‐photon images.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
NASA NTRS2007

Pyrolysis process for producing fuel gas

Solid waste resource recovery in space is effected by pyrolysis processing, to produce light gases as the main products (CH.sub.4, H.sub.2, CO.sub.2, CO, H.sub.2O, NH.sub.3) and a reactive carbon-rich char as the main byproduct. Significant amounts of liquid products are formed under less severe pyrolysis conditions, and are cracked almost completely to gases as the temperature is raised. A primary pyrolysis model for the composite mixture is based on an existing model for whole biomass materials, and an artificial neural network models the changes in gas composition with the severity of pyrolysis conditions.

Serio, Michael A.↗
NASA NTRS2007

Pyrolysis processing for solid waste resource recovery

Solid waste resource recovery in space is effected by pyrolysis processing, to produce light gases as the main products (CH.sub.4, H.sub.2, CO.sub.2, CO, H.sub.2O, NH.sub.3) and a reactive carbon-rich char as the main byproduct. Significant amounts of liquid products are formed under less severe pyrolysis conditions, and are cracked almost completely to gases as the temperature is raised. A primary pyrolysis model for the composite mixture is based on an existing model for whole biomass materials, and an artificial neural network models the changes in gas composition with the severity of pyrolysis conditions.

Serio, Michael A.↗
DOE OSTI2024

HGQ: High Granularity Quantization for Real-time Neural Networks on FPGAs

Neural networks with sub-microsecond inference latency are required by many critical applications. Targeting such applications deployed on FPGAs, we present High Granularity Quantization (HGQ), a quantization-aware training framework that optimizes parameter bit-widths through gradient descent. Unlike conventional methods, HGQ determines the optimal bit-width for each parameter independently, making it suitable for hardware platforms supporting heterogeneous arbitrary precision arithmetic. In our experiments, HGQ shows superior performance compared to existing network compression methods, achieving orders of magnitude reduction in resource consumption and latency while maintaining the accuracy on several benchmark tasks. These improvements enable the deployment of complex models previously infeasible due to resource or latency constraints. HGQ is open-source and is used for developing next-generation trigger systems at the CERN ATLAS and CMS experiments for particle physics, enabling the use of advanced machine learning models for real-time data selection with sub-microsecond latency.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2024

Variational data augmentation for a learning-based granular predictive model of power outages

As the trend in climate change continues, extreme weather events are expected to occur with increasing frequency and severity and pose a significant threat to the electric power infrastructure. Regardless of the efforts a utility puts towards hardening the grid, storm-induced damage to the utility assets such as cables and distributed energy resources (DERs) that are particularly vulnerable to such events is unavoidable. Access to a highly granular, in space and time, outage forecasting tool with long lead times (i.e., days ahead) will enhance the efficiency of service restoration efforts. Here, in this study, we propose to develop and implement a multi-model framework as an operational tool based on a granular and multi-day outage forecasting model using operational numerical weather prediction model forecasts and detailed component outage information. An innovative two-layered recurrent neural network, i.e., a long-short-term-memory (LSTM)-based variational autoencoder (VAE) framework and a sliding window are used to address the uneven distribution of different types of weather events and make better use of the time-series data. Case studies are performed to demonstrate the performance of the new framework.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2021

Accelerating phase-field-based microstructure evolution predictions via surrogate models trained by machine learning methods

Abstract The phase-field method is a powerful and versatile computational approach for modeling the evolution of microstructures and associated properties for a wide variety of physical, chemical, and biological systems. However, existing high-fidelity phase-field models are inherently computationally expensive, requiring high-performance computing resources and sophisticated numerical integration schemes to achieve a useful degree of accuracy. In this paper, we present a computationally inexpensive, accurate, data-driven surrogate model that directly learns the microstructural evolution of targeted systems by combining phase-field and history-dependent machine-learning techniques. We integrate a statistically representative, low-dimensional description of the microstructure, obtained directly from phase-field simulations, with either a time-series multivariate adaptive regression splines autoregressive algorithm or a long short-term memory neural network. The neural-network-trained surrogate model shows the best performance and accurately predicts the nonlinear microstructure evolution of a two-phase mixture during spinodal decomposition in seconds, without the need for “on-the-fly” solutions of the phase-field equations of motion. We also show that the predictions from our machine-learned surrogate model can be fed directly as an input into a classical high-fidelity phase-field model in order to accelerate the high-fidelity phase-field simulations by leaping in time. Such machine-learned phase-field framework opens a promising path forward to use accelerated phase-field simulations for discovering, understanding, and predicting processing–microstructure–performance relationships.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Variation in forest root image annotation by experts, novices, and AI

Abstract Background The manual study of root dynamics using images requires huge investments of time and resources and is prone to previously poorly quantified annotator bias. Artificial intelligence (AI) image-processing tools have been successful in overcoming limitations of manual annotation in homogeneous soils, but their efficiency and accuracy is yet to be widely tested on less homogenous, non-agricultural soil profiles, e.g., that of forests, from which data on root dynamics are key to understanding the carbon cycle. Here, we quantify variance in root length measured by human annotators with varying experience levels. We evaluate the application of a convolutional neural network (CNN) model, trained on a software accessible to researchers without a machine learning background, on a heterogeneous minirhizotron image dataset taken in a multispecies, mature, deciduous temperate forest. Results Less experienced annotators consistently identified more root length than experienced annotators. Root length annotation also varied between experienced annotators. The CNN root length results were neither precise nor accurate, taking ~ 10% of the time but significantly overestimating root length compared to expert manual annotation ( p = 0.01). The CNN net root length change results were closer to manual ( p = 0.08) but there remained substantial variation. Conclusions Manual root length annotation is contingent on the individual annotator. The only accessible CNN model cannot yet produce root data of sufficient accuracy and precision for ecological applications when applied to a complex, heterogeneous forest image dataset. A continuing evaluation and development of accessible CNNs for natural ecosystems is required.

Handy, Grace↗
DOE OSTI2022

Large Scale Caching and Streaming of Training Data for Online Deep Learning

The training of deep neural network models on large data remains a difficult problem, despite progress towards scalable techniques. In particular, there is a mismatch between the random but predetermined order in which AI flows select training samples and the streaming I/O patterns for which traditional HPC data storage (e.g., parallel file systems) are designed. In addition, as more data are obtained, it is feasible neither simply to train learning models incrementally, due to catastrophic forgetting (i.e., bias towards new samples), nor to train frequently from scratch, due to prohibitive time and/or resource constraints. In this paper, we study data management techniques that combine caching and streaming with rehearsal support in order to enable efficient access to training samples in both offline training and continual learning. We revisit state-of-art streaming approaches based on data pipelines that transparently handle prefetching, caching, shuffling, and data augmentation, and discuss the challenges and opportunities that arise when combining these methods with data-parallel training techniques. We also report on preliminary experiments that evaluate the I/O overheads involved in accessing the training samples from a parallel file system (PFS) under several concurrency scenarios, highlighting the impact of the PFS on the design of the data pipelines.

data pipelines↗
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 OSTI2024

Rapid, antibiotic incubation-free determination of tuberculosis drug resistance using machine learning and Raman spectroscopy

Tuberculosis (TB) is the world’s deadliest infectious disease, with over 1.5 million deaths and 10 million new cases reported anually. The causative organism Mycobacterium tuberculosis (Mtb) can take nearly 40 d to culture, a required step to determine the pathogen’s antibiotic susceptibility. Both rapid identification and rapid antibiotic susceptibility testing of Mtb are essential for effective patient treatment and combating antimicrobial resistance. Here, we demonstrate a rapid, culture-free, and antibiotic incubation-free drug susceptibility test for TB using Raman spectroscopy and machine learning. We collect few-to-single-cell Raman spectra from over 25,000 cells of the Mtb complex strain Bacillus Calmette-Guérin (BCG) resistant to one of the four mainstay anti-TB drugs, isoniazid, rifampicin, moxifloxacin, and amikacin, as well as a pan-susceptible wildtype strain. By training a neural network on this data, we classify the antibiotic resistance profile of each strain, both on dried samples and on patient sputum samples. On dried samples, we achieve >98% resistant versus susceptible classification accuracy across all five BCG strains. In patient sputum samples, we achieve ~79% average classification accuracy. We develop a feature recognition algorithm in order to verify that our machine learning model is using biologically relevant spectral features to assess the resistance profiles of our mycobacterial strains. Finally, we demonstrate how this approach can be deployed in resource-limited settings by developing a low-cost, portable Raman microscope that costs <$5,000. We show how this instrument and our machine learning model enable combined microscopy and spectroscopy for accurate few-to-single-cell drug susceptibility testing of BCG.

60 APPLIED LIFE SCIENCES↗
NASA NTRS1995

Automated Propulsion Data Screening demonstration system

A fully-instrumented firing of a propulsion system typically generates a very large quantity of data. In the case of the Space Shuttle Main Engine (SSME), data analysis from ground tests and flights is currently a labor-intensive process. Human experts spend a great deal of time examining the large volume of sensor data generated by each engine firing. These experts look for any anomalies in the data which might indicate engine conditions warranting further investigation. The contract effort was to develop a 'first-cut' screening system for application to SSME engine firings that would identify the relatively small volume of data which is unusual or anomalous in some way. With such a system, limited and expensive human resources could focus on this small volume of unusual data for thorough analysis. The overall project objective was to develop a fully operational Automated Propulsion Data Screening (APDS) system with the capability of detecting significant trends and anomalies in transient and steady-state data. However, the effort limited screening of transient data to ground test data for throttle-down cases typical of the 3-g acceleration, and for engine throttling required to reach the maximum dynamic pressure limits imposed on the Space Shuttle. This APDS is based on neural networks designed to detect anomalies in propulsion system data that are not part of the data used for neural network training. The delivered system allows engineers to build their own screening sets for application to completed or planned firings of the SSME. ERC developers also built some generic screening sets that NASA engineers could apply immediately to their data analysis efforts.

Hoyt, W. Andes↗